% Type: Inproceedings % Encoding: utf-8 @InProceedings{Zabrovskiy2021c, author = {Anatoliy Zabrovskiy and Prateek Agrawal and Christian Timmerer and Radu Prodan}, booktitle = {2021 30th Conference of Open Innovations Association (FRUCT)}, title = {{FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machine Learning}}, year = {2021}, month = {oct}, pages = {292--302}, publisher = {IEEE}, abstract = {HTTP adaptive video streaming is a widespread and sought-after technology on the Internet that allows clients to dynamically switch between different stream qualities presented in the bitrate ladder to optimize overall received video quality. Currently, there exist several approaches of different complexity for building such a ladder. The simplest method is to use a static bitrate ladder, and the more complex one is to compute a per-title encoding ladder. The main drawback of these approaches is that they do not provide bitrate ladders for scenes with different visual complexity within the video. Moreover, most modern methods require additional computationally-intensive test encodings of the entire video to construct the convex hull, used to calculate the bitrate ladder. This paper proposes a new fast per-scene encoding approach called FAUST based on 1) quick entropy-based scene detection and 2) prediction of optimized bitrate ladder for each scene using an artificial neural network. The results show that our model reduces the mean absolute error to 0.15, the mean square error to 0.08, and the bitrate to 13.5 % while increasing the difference in video multimethod assessment fusion to 5.6 points.}, doi = {10.23919/fruct53335.2021.9599963}, keywords = {Visualization, Technological innovation, Bit rate, Switches, Mean square error methods, Streaming media, Encoding}, url = {https://ieeexplore.ieee.org/document/9599963} } @InProceedings{Tashtarian2021, author = {Farzad Tashtarian and Abdelhak Bentaleb and Reza Farahani and Minh Nguyen and Christian Timmerer and Hellwagner, Hermann and Roger Zimmermann}, booktitle = {2021 IEEE 46th Conference on Local Computer Networks (LCN)}, title = {{A Distributed Delivery Architecture for User Generated Content Live Streaming over HTTP}}, year = {2021}, month = {oct}, pages = {162--169}, publisher = {IEEE}, abstract = {Live User Generated Content (UGC) has become very popular in today’s video streaming applications, in particular with gaming and e-sport. However, streaming UGC presents unique challenges for video delivery. When dealing with the technical complexity of managing hundreds or thousands of concurrent streams that are geographically distributed, UGC systems are forces to made difficult trade-offs with video quality and latency. To bridge this gap, this paper presents a fully distributed architecture for UGC delivery over the Internet, termed QuaLA (joint Quality-Latency Architecture). The proposed architecture aims to jointly optimize video quality and latency for a better user experience and fairness. By using the proximal Jacobi alternating direction method of multipliers (ProxJ-ADMM) technique, QuaLA proposes a fully distributed mechanism to achieve an appropriate solution. We demonstrate the effectiveness of the proposed architecture through real-world experiments using the CloudLAB testbed. Experimental results show the outperformance of QuaLA in achieving high quality with more than 57% improvement while preserving a good level of fairness and respecting a given target latency among all clients compared to conventional client-driven solutions.}, doi = {10.1109/lcn52139.2021.9525027}, keywords = {UGC streaming, low latency live streaming, fairness, QoE, HAS, DASH, ABR, adaptive streaming, ADMM}, url = {https://ieeexplore.ieee.org/document/9525027} } @InProceedings{Taraghi2021b, author = {Babak Taraghi}, booktitle = {Proceedings of the 29th {ACM} International Conference on Multimedia}, title = {{End-to-end Quality of Experience Evaluation for HTTP Adaptive Streaming}}, year = {2021}, month = {oct}, pages = {2936--2939}, publisher = {ACM}, abstract = {Exponential growth in multimedia streaming traffic over the Internet motivates the research and further investigation of the user's perceived quality of such services. Enhancement of experienced quality by the users becomes more substantial when service providers compete on establishing superiority by gaining more subscribers or customers. Quality of Experience (QoE) enhancement would not be possible without an authentic and accurate assessment of the streaming sessions. HTTP Adaptive Streaming (HAS) is today's prevailing technique to deliver the highest possible audio and video content quality to the users. An end-to-end evaluation of QoE in HAS covers the precise measurement of the metrics that affect the perceived quality, eg. startup delay, stall events, and delivered media quality. Mentioned metrics improvements could limit the service's scalability, which is an important factor in real-world scenarios. In this study, we will investigate the stated metrics, best practices and evaluations methods, and available techniques with an aim to (i) design and develop practical and scalable measurement tools and prototypes, (ii) provide a better understanding of current technologies and techniques (eg. Adaptive Bitrate algorithms), (iii) conduct in-depth research on the significant metrics in a way that improvements of QoE with scalability in mind would be feasible, and finally (iv) provide a comprehensive QoE model which outperforms state-of-the-art models.}, doi = {10.1145/3474085.3481025}, keywords = {HTTP Adaptive Streaming, Quality of Experience, Subjective Evaluation, Objective Evaluation, Adaptive Bitrate, QoE model}, url = {https://dl.acm.org/doi/10.1145/3474085.3481025} } @InProceedings{Taraghi2021, author = {Babak Taraghi and Abdelhak Bentaleb and Christian Timmerer and Roger Zimmermann and Hellwagner, Hermann}, booktitle = {Proceedings of the 31st ACM Workshop on Network and Operating Systems Support for Digital Audio and Video}, title = {{Understanding quality of experience of heuristic-based HTTP adaptive bitrate algorithms}}, year = {2021}, month = {jul}, pages = {82--89}, publisher = {ACM}, abstract = {Adaptive bitrate (ABR) algorithms play a crucial role in delivering the highest possible viewer's Quality of Experience (QoE) in HTTP Adaptive Streaming (HAS). Online video streaming service providers use HAS - the dominant video streaming technique on the Internet - to deliver the best QoE for their users. A viewer's delight relies heavily on how the ABR of a media player can adapt the stream's quality to the current network conditions. QoE for video streaming sessions has been assessed in many research projects to give better insight into the significant quality metrics such as startup delay and stall events. The ITU Telecommunication Standardization Sector (ITU-T) P.1203 quality evaluation model allows to algorithmically predict a subjective Mean Opinion Score (MOS) by considering various quality metrics. Subjective evaluation is the best assessment method for examining the end-user opinion over a video streaming session's experienced quality. We have conducted subjective evaluations with crowdsourced participants and evaluated the MOS of the sessions using the ITU-T P.1203 quality model. This paper's main contribution is to investigate the correspondence of subjective and objective evaluations for well-known heuristic-based ABRs.}, doi = {10.1145/3458306.3458875}, keywords = {HTTP Adaptive Streaming, ABR Algorithms, Quality of Experience, Crowdsourcing, Subjective Evaluation, Objective Evaluation, MOS}, url = {https://dl.acm.org/doi/10.1145/3458306.3458875} } @InProceedings{Steinkellner2021, author = {Philip Steinkellner and Klaus Schöffmann}, booktitle = {2021 International Conference on Content-Based Multimedia Indexing (CBMI)}, title = {{Evaluation of Object Detection Systems and Video Tracking in Skiing Videos}}, year = {2021}, month = {jun}, pages = {1--6}, publisher = {IEEE}, abstract = {Nowadays, modern ski resorts provide additional services to customers, such as recording videos of specific moments from their skiing experience. This and similar tasks can be achieved by using computer vision methods. In this work, we evaluate the detection performance of current object detection methods and the tracking performance of a detection-based tracking algorithm. The evaluation is based on videos of skiers and snowboarders from ski resorts. We collect videos of race tracks from different resorts and compile a public dataset of images and videos, where skiers and snowboarders are annotated with bounding boxes. Based on this data, we evaluate the performance of four state-of-the-art object detection methods. This evaluation is performed with general models trained on the MS COCO dataset as well as with custom models trained on our dataset. In addition, we review the performance of the detection-based, multi-object tracking algorithm Deep SORT, which we adapt for skier tracking.The results show promising performance and reveal that the MS COCO models already achieve high Precision, while training a custom model additionally improves the performance. Bigger models profit from custom training in terms of more accurate bounding box placement and higher Precision, while smaller models have an overall high training payoff. The modified Deep SORT tracker manages to follow a skier’s trajectory over an extended period and operates with high accuracy, which indicates that the tracker is overall well suited for tracking of skiers and snowboarders on race tracks. Even when exposed to strong camera and skier movement changes, the tracker stays latched onto the target.}, doi = {10.1109/cbmi50038.2021.9461905}, keywords = {Object Detection, Object Tracking, YOLOv4, Faster R-CNN, Deep SORT, Skiing, Sports Video Analysis}, url = {http://dx.doi.org/10.1109/cbmi50038.2021.9461905} } @InProceedings{Schoeffmann2021, author = {Klaus Schoeffmann and Jakub Lokoc and Werner Bailer}, booktitle = {Proceedings of the 2nd ACM International Conference on Multimedia in Asia}, title = {{10 years of video browser showdown}}, year = {2021}, month = {mar}, pages = {1--3}, publisher = {ACM}, abstract = {The Video Browser Showdown (VBS) has influenced the Multimedia community already for 10 years now. More than 30 unique teams from over 21 countries participated in the VBS since 2012 already. In 2021, we are celebrating the 10th anniversary of VBS, where 17 international teams compete against each other in an unprecedented contest of fast and accurate multimedia retrieval. In this tutorial we discuss the motivation and details of the VBS contest, including its history, rules, evaluation metrics, and achievements for multimedia retrieval. We talk about the properties of specific VBS retrieval systems and their unique characteristics, as well as existing open-source tools that can be used as a starting point for participating for the first time. Participants of this tutorial get a detailed understanding of the VBS and its search systems, and see the latest developments of interactive video retrieval.}, doi = {10.1145/3444685.3450215}, url = {https://dl.acm.org/doi/10.1145/3444685.3450215} } @InProceedings{Roman2021, author = {Dumitru Roman and Nikolay Nikolov and Ahmet Soylu and Brian Elvesaeter and Hui Song and Radu Prodan and Dragi Kimovski and Andrea Marrella and Francesco Leotta and Mihhail Matskin and Giannis Ledakis and Konstantinos Theodosiou and Anthony Simonet-Boulogne and Fernando Perales and Evgeny Kharlamov and Alexandre Ulisses and Arnor Solberg and Raffaele Ceccarelli}, booktitle = {2021 IEEE Symposium on Computers and Communications (ISCC)}, title = {{Big Data Pipelines on the Computing Continuum: Ecosystem and Use Cases Overview}}, year = {2021}, month = {sep}, pages = {1--4}, publisher = {IEEE}, abstract = {Organisations possess and continuously generate huge amounts of static and stream data, especially with the proliferation of Internet of Things technologies. Collected but unused data, i.e., Dark Data, mean loss in value creation potential. In this respect, the concept of Computing Continuum extends the traditional more centralised Cloud Computing paradigm with Fog and Edge Computing in order to ensure low latency pre-processing and filtering close to the data sources. However, there are still major challenges to be addressed, in particular related to management of various phases of Big Data processing on the Computing Continuum. In this paper, we set forth an ecosystem for Big Data pipelines in the Computing Continuum and introduce five relevant real-life example use cases in the context of the proposed ecosystem.}, doi = {10.1109/iscc53001.2021.9631410}, keywords = {Big Data, Computing Continuum, Dark Data, Data Pipelines, Cloud-Fog-Edge Computing}, url = {https://ieeexplore.ieee.org/document/9631410} } @InProceedings{Pasandi2021a, author = {Hannaneh Barahouei Pasandi and Tamer Nadeem and Hadi Amirpour and Christian Timmerer}, booktitle = {Proceedings of the 27th Annual International Conference on Mobile Computing and Networking}, title = {{A cross-layer approach for supporting real-time multi-user video streaming over WLANs*}}, year = {2021}, month = {oct}, pages = {849--851}, publisher = {ACM}, abstract = {MU-MIMO is a high-speed technique in IEEE 802.11ac and upcoming 802.11ax technologies that improves spectral efficiency by allowing concurrent communication between one Access Point and multiple users. In this paper, we present MuVIS, a novel framework that proposes MU-MIMO-aware optimization for multi-user multimedia applications over IEEE 802.11ac/ax. Taking a cross-layer approach, MuVIS first optimizes the MU-MIMO user group selection for the users with the same characteristics in the PHY/MAC layer. It then optimizes the video bitrate for each group accordingly. We present our design and its evaluation on smartphones and laptops over 802.11ac WiFi.}, doi = {10.1145/3447993.3482868}, url = {https://dl.acm.org/doi/abs/10.1145/3447993.3482868} } @InProceedings{Pasandi2021, author = {Hannaneh Barahouei Pasandi and Hadi Amirpour and Tamer Nadeem and Christian Timmerer}, booktitle = {Proceedings of the Workshop on Design, Deployment, and Evaluation of Network-assisted Video Streaming}, title = {{Learning-driven MU-MIMO Grouping for Multi-User Multimedia Applications Over Commodity WiFi}}, year = {2021}, month = {dec}, pages = {15--21}, publisher = {ACM}, abstract = {MU-MIMO is a high-speed technique in IEEE 802.11ac and upcoming ax technologies that improves spectral efficiency by allowing concurrent communication between one Access Point and multiple users. In this paper, we present LATTE, a novel framework that proposes MU-MIMO-aware optimization for multi-user multimedia applications over IEEE 802.11ac/ax. Taking a cross-layer approach, LATTE first optimizes the MU-MIMO user group selection for the users with the same characteristics in the PHY/MAC layer. It then optimizes the video bitrate for each group accordingly. We present our design and its evaluation on smartphones and laptops over 802.11ac WiFi. Our experimental evaluations indicate that LATTE can outperform other video rate adaptation algorithms.}, doi = {10.1145/3488662.3493828}, url = {https://dl.acm.org/doi/10.1145/3488662.3493828} } @InProceedings{Nguyen2021, author = {Minh Nguyen}, booktitle = {Proceedings of the 12th ACM Multimedia Systems Conference}, title = {{Policy-driven Dynamic HTTP Adaptive Streaming Player Environment}}, year = {2021}, month = {jun}, pages = {408--412}, publisher = {ACM}, abstract = {Video streaming services account for the majority of today's traffic on the Internet. Although the data transmission rate has been increasing significantly, the growing number and variety of media and higher quality expectations of users have led networked media applications to fully or even over-utilize the available throughput. HTTP Adaptive Streaming (HAS) has become a predominant technique for multimedia delivery over the Internet today. However, there are critical challenges for multimedia systems, especially the tradeoff between the increasing content (complexity) and various requirements regarding time (latency) and quality (QoE). This thesis will cover the main aspects within the end user's environment, including video consumption and interactivity, collectively referred to as player environment, which is probably the most crucial component in today's multimedia applications and services. We will investigate the methods that can enable the specification of various policies reflecting the user's needs in given use cases. Besides, we will also work on schemes that allow efficient support for server-assisted, and network-assisted HAS systems. Finally, those approaches will be considered to combine into policies that fit the requirements of all use cases (e.g., live streaming, video on demand, etc.).}, doi = {10.1145/3458305.3478466}, url = {https://dl.acm.org/doi/10.1145/3458305.3478466} } @InProceedings{Najafabadi2021, author = {Zahra Najafabadi Samani and Nishant Saurabh and Radu Prodan}, booktitle = {2021 IEEE 5th International Conference on Fog and Edge Computing (ICFEC)}, title = {{Multilayer Resource-aware Partitioning for Fog Application Placement}}, year = {2021}, month = {may}, pages = {9--18}, publisher = {IEEE}, abstract = {Fog computing emerged as a crucial platform for the deployment of IoT applications. The complexity of such applications require methods that handle the resource diversity and network structure of Fog devices, while maximizing the service placement and reducing the resource wastage. Prior studies in this domain primarily focused on optimizing application-specific requirements and fail to address the network topology combined with the different types of resources encountered in Fog devices. To overcome these problems, we propose a multilayer resource-aware partitioning method to minimize the resource wastage and maximize the service placement and deadline satisfaction rates in a Fog infrastructure with high multi-user application placement requests. Our method represents the heterogeneous Fog resources as a multilayered network graph and partitions them based on network topology and resource features. Afterwards, it identifies the appropriate device partitions for placing an application according to its requirements, which need to overlap in the same network topology partition. Simulation results show that our multilayer resource-aware partitioning method is able to place twice as many services, satisfy deadlines for three times as many application requests, and reduce the resource wastage by up to 15–32 times compared to two availability-aware and resource-aware state-of-the-art methods.}, doi = {10.1109/icfec51620.2021.00010}, keywords = {Fog computing, application placement, resource partitioning, resource wastage, deadline satisfaction}, url = {https://ieeexplore.ieee.org/document/9458908} } @InProceedings{Menon2021a, author = {Vignesh V Menon and Hadi Amirpour and Mohammad Ghanbari and Christian Timmerer}, booktitle = {2021 IEEE International Conference on Image Processing (ICIP)}, title = {{Efficient Content-Adaptive Feature-Based Shot Detection for HTTP Adaptive Streaming}}, year = {2021}, month = {sep}, pages = {2174--2178}, publisher = {IEEE}, abstract = {Video delivery over the Internet has been becoming a commodity in recent years, owing to the widespread use of Dynamic Adaptive Streaming over HTTP (DASH). The DASH specification defines a hierarchical data model for Media Presentation Descriptions (MPDs) in terms of segments. This paper focuses on segmenting video into multiple shots for encoding in Video on Demand (VoD) HTTP Adaptive Streaming (HAS) applications. Therefore, we propose a novel Discrete Cosine Transform (DCT) feature-based shot detection and successive elimination algorithm for shot detection and compare it against the default shot detection algorithm of the x265 implementation of the High Efficiency Video Coding (HEVC) standard. Our experimental results demonstrate that our proposed feature-based pre-processor has a recall rate of 25% and an F-measure of 20% greater than the benchmark algorithm for shot detection.}, doi = {10.1109/icip42928.2021.9506092}, keywords = {HTTP Adaptive Streaming, Video-on-Demand, Shot detection, multi-shot encoding}, url = {https://ieeexplore.ieee.org/document/9506092} } @InProceedings{Menon2021, author = {Vignesh Menon and Hadi Amirpourazarian and Christian Timmerer and Mohammad Ghanbari}, booktitle = {2021 Picture Coding Symposium (PCS)}, title = {{Efficient Multi-Encoding Algorithms for HTTP Adaptive Bitrate Streaming}}, year = {2021}, month = jun, pages = {1--5}, publisher = {IEEE}, abstract = {Since video accounts for the majority of today’s internet traffic, the popularity of HTTP Adaptive Streaming (HAS) is increasing steadily. In HAS, each video is encoded at multiple bitrates and spatial resolutions (i.e., representations) to adapt to a heterogeneity of network conditions, device characteristics, and end-user preferences. Most of the streaming services utilize cloud-based encoding techniques which enable a fully parallel encoding process to speed up the encoding and consequently to reduce the overall time complexity. State-of-the-art approaches further improve the encoding process by utilizing encoder analysis information from already encoded representation(s) to improve the encoding time complexity of the remaining representations. In this paper, we investigate various multi-encoding algorithms (i.e., multi-rate and multi-resolution) and propose novel multi- encoding algorithms for large-scale HTTP Adaptive Streaming deployments. Experimental results demonstrate that the proposed multi-encoding algorithm optimized for the highest compression efficiency reduces the overall encoding time by 39% with a 1.5% bitrate increase compared to stand-alone encodings. Its optimized version for the highest time savings reduces the overall encoding time by 50% with a 2.6% bitrate increase compared to stand-alone encodings.}, doi = {10.1109/pcs50896.2021.9477499}, keywords = {HTTP Adaptive Streaming, HEVC, Multi-rate Encoding, Multi-encoding}, url = {https://ieeexplore.ieee.org/document/9477499} } @InProceedings{Mehran2021, author = {Narges Mehran and Dragi Kimovski and Radu Prodan}, booktitle = {2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid)}, title = {{A Two-Sided Matching Model for Data Stream Processing in the Cloud textendash Fog Continuum}}, year = {2021}, month = {may}, pages = {514--524}, publisher = {IEEE}, abstract = {Latency-sensitive and bandwidth-intensive stream processing applications are dominant traffic generators over the Internet network. A stream consists of a continuous sequence of data elements, which require processing in nearly real-time. To improve communication latency and reduce the network congestion, Fog computing complements the Cloud services by moving the computation towards the edge of the network. Unfortunately, the heterogeneity of the new Cloud – Fog continuum raises important challenges related to deploying and executing data stream applications. We explore in this work a two-sided stable matching model called Cloud – Fog to data stream application matching (CODA) for deploying a distributed application rep-resented as a workflow of stream processing microservices on heterogeneous computing continuum resources. In CODA, the application microservices rank the continuum resources based on their microservice stream processing time, while resources rank the stream processing microservices based on their residual bandwidth. A stable many-to-one matching algorithm assigns microservices to resources based on their mutual preferences, aiming to optimize the complete stream processing time on the application side, and the total streaming traffic on the resource side. We evaluate the CODA algorithm using simulated and real-world Cloud – Fog experimental scenarios. We achieved 11-45% lower stream processing time and 1.3-20% lower streaming traffic compared to related state-of-the-art approaches.}, doi = {10.1109/ccgrid51090.2021.00061}, keywords = {Cloud - fog computing, Distributed databases, Bandwidth, Games, Streaming media, Data models, Real-time systems}, url = {https://ieeexplore.ieee.org/document/9499353} } @InProceedings{Matha2021, author = {Roland Matha and Dragi Kimovski and Anatoliy Zabrovskiy and Christian Timmerer and Radu Prodan}, booktitle = {2021 IEEE 17th International Conference on eScience (eScience)}, title = {{Where to Encode: A Performance Analysis of x86 and Arm-based Amazon EC2 Instances}}, year = {2021}, month = {sep}, pages = {118--127}, publisher = {IEEE}, abstract = {Video streaming became an undivided part of the Internet. To efficiently utilise the limited network bandwidth it is essential to encode the video content. However, encoding is a computationally intensive task, involving high-performance resources provided by private infrastructures or public clouds. Public clouds, such as Amazon EC2, provide a large portfolio of services and instances optimized for specific purposes and budgets. The majority of Amazon’s instances use x86 processors, such as Intel Xeon or AMD EPYC. However, following the recent trends in computer architecture, Amazon introduced Arm based instances that promise up to 40% better cost performance ratio than comparable x86 instances for specific workloads. We evaluate in this paper the video encoding performance of x86 and Arm instances of four instance families using the latest FFmpeg version and two video codecs. We examine the impact of the encoding parameters, such as different presets and bitrates, on the time and cost for encoding. Our experiments reveal that Arm instances show high time and cost saving potential of up to 33.63% for specific bitrates and presets, especially for the x264 codec. However, the x86 instances are more general and achieve low encoding times, regardless of the codec.}, doi = {10.1109/escience51609.2021.00022}, keywords = {Amazon EC2, Arm instances, AVC, Cloud computing, FFmpeg, Graviton2, HEVC, Performance analysis, Video encoding}, url = {https://www.computer.org/csdl/proceedings-article/escience/2021/036100a118/1y14GC0fb6o} } @InProceedings{Lv2021, author = {Zezhong Lv and Qing Xu and Klaus Schoeffmann and Simon Parkinson}, booktitle = {2021 IEEE International Conference on Multimedia and Expo (ICME)}, title = {{A Jensen-Shannon Divergence Driven Metric of Visual Scanning Efficiency Indicates Performance of Virtual Driving}}, year = {2021}, month = {jul}, pages = {1--6}, publisher = {IEEE}, abstract = {Visual scanning plays an important role in sampling visual information from the surrounding environments for a lot of everyday sensorimotor tasks, such as driving. In this paper, we consider the problem of visual scanning mechanism underpinning sensorimotor tasks in 3D dynamic environments. We exploit the use of eye tracking data as a behaviometric, for indicating the visuo-motor behavioral measure in the context of virtual driving. A new metric of visual scanning efficiency (VSE), which is defined as a mathematical divergence between a fixation distribution and a distribution of optical flows induced by fixations, is proposed by making use of a widely-known information theoretic tool, namely the square root of Jensen-Shannon divergence. Psychophysical eye tracking studies, in virtual reality based driving, are conducted to reveal that the new metric of visual scanning efficiency can be employed very well as a proxy evaluation for driving performance. These results suggest that the exploitation of eye tracking data provides an effective behaviometric for sensorimotor activities.}, doi = {10.1109/icme51207.2021.9428109}, keywords = {visual scanning efficiency, eye tracking, Jensen-Shannon divergence (JSD), behaviometric}, url = {https://ieeexplore.ieee.org/document/9428109} } @InProceedings{Lorenzi2021, author = {Daniele Lorenzi and Minh Nguyen and Farzad Tashtarian and Simone Milani and Hellwagner, Hermann and Christian Timmerer}, booktitle = {Proceedings of the 2021 Workshop on Evolution, Performance and Interoperability of QUIC}, title = {{Days of future past}}, year = {2021}, month = {dec}, pages = {8--14}, publisher = {ACM}, abstract = {HTTP Adaptive Streaming (HAS) has become a predominant technique for delivering videos in the Internet. Due to its adaptive behavior according to changing network conditions, it may result in video quality variations that negatively impact the Quality of Experience (QoE) of the user. In this paper, we propose Days of Future Past, an optimization-based Adaptive Bitrate (ABR) algorithm over HTTP/3. Days of Future Past takes advantage of an optimization model and HTTP/3 features, including (i) stream multiplexing and (ii) request cancellation. We design a Mixed Integer Linear Programming (MILP) model that determines the optimal video qualities of both the next segment to be requested and the segments currently located in the buffer. If better qualities for buffered segments are found, the client will send corresponding HTTP GET requests to retrieve them. Multiple segments (i.e., retransmitted segments) might be downloaded simultaneously to upgrade some buffered but not yet played segments to avoid quality decreases using the stream multiplexing feature of QUIC. HTTP/3's request cancellation will be used in case retransmitted segments will arrive at the client after their playout time. The experimental results shows that our proposed method is able to improve the QoE by up to 33.9%.}, doi = {10.1145/3488660.3493802}, keywords = {HTTP/3, QUIC, Days of Future Past, HAS, QoE}, url = {https://dl.acm.org/doi/10.1145/3488660.3493802} } @InProceedings{Leibetseder2021b, author = {Andreas Leibetseder and Klaus Schoeffmann}, booktitle = {Proceedings of the 4th Annual on Lifelog Search Challenge}, title = {{lifeXplore at the Lifelog Search Challenge 2021}}, year = {2021}, month = {aug}, pages = {23--28}, publisher = {ACM}, abstract = {Since its first iteration in 2018, the Lifelog Search Challenge (LSC) continues to rise in popularity as an interactive lifelog data retrieval competition, co-located at the ACM International Conference on Multimedia Retrieval (ICMR). The goal of this annual live event is to search a large corpus of lifelogging data for specifically announced memories using a purposefully developed tool within a limited amount of time. As long-standing participants, we present our improved lifeXplore -- a retrieval system combining chronologic day summary browsing with interactive combinable concept filtering. Compared to previous versions, the tool is improved by incorporating temporal queries, advanced day summary features as well as usability improvements.}, doi = {10.1145/3463948.3469060}, keywords = {lifelogging, evaluation campaign, interactive image retrieval, image search}, url = {https://dl.acm.org/doi/10.1145/3463948.3469060} } @InProceedings{Leibetseder2021, author = {Andreas Leibetseder and Klaus Schoeffmann and Joerg Keckstein and Simon Keckstein}, booktitle = {2021 International Conference on Content-Based Multimedia Indexing (CBMI)}, title = {{Post-surgical Endometriosis Segmentation in Laparoscopic Videos}}, year = {2021}, month = {jun}, pages = {1--4}, publisher = {IEEE}, abstract = {Endometriosis is a common women's condition exhibiting a manifold visual appearance in various body-internal locations. Having such properties makes its identification very difficult and error-prone, at least for laymen and non-specialized medical practitioners. In an attempt to provide assistance to gynecologic physicians treating endometriosis, this demo paper describes a system that is trained to segment one frequently occurring visual appearance of endometriosis, namely dark endometrial implants. The system is capable of analyzing laparoscopic surgery videos, annotating identified implant regions with multi-colored overlays and displaying a detection summary for improved video browsing.}, doi = {10.1109/cbmi50038.2021.9461900}, keywords = {Endometriosis, Lesion Segmentation, Mask R-CNN}, url = {http://dx.doi.org/10.1109/cbmi50038.2021.9461900} } @InProceedings{Kashansky2021b, author = {Vladislav Kashansky and Radu Prodan and Gleb Radchenko}, booktitle = {9th International Conference "Distributed Computing and Grid Technologies in Science and Education"}, title = {{Some aspects of the workflow scheduling in the computing continuum systems}}, year = {2021}, month = {dec}, pages = {106--110}, publisher = {Crossref}, abstract = {Contemporary computing systems are commonly characterized in terms of data-intensive workflows, that are managed by utilizing large number of heterogeneous computing and storage elements interconnected through complex communication topologies. As the scale of the system grows and workloads become more heterogeneous in both inner structure and the arrival patterns, scheduling problem becomes exponentially harder, requiring problem-specifc heuristics. Despite several decades of the active research on it, one issue that still requires effort is to enable efficient workflows scheduling in such complex environments, while preserving robustness of the results. Moreover, recent research trend coined under term "computing continuum" prescribes convergence of the multi-scale computational systems with complex spatio-temporal dynamics and diverse sets of the management policies. This paper contributes with the set of recommendations and brief analysis for the existing scheduling algorithms.}, doi = {10.54546/mlit.2021.29.45.001}, keywords = {scheduling, algorithms, brief review, workflows}, url = {http://ceur-ws.org/Vol-3041/} } @InProceedings{Kashansky2021a, author = {Vladislav Kashansky and Nishant Saurabh and Radu Prodan and Aso Validi and Cristina Olaverri-Monreal and Renate Burian and Gerhard Burian and Dimo Hirsch and Yisheng Lv and Fei-Yue Wang and Hai Zuhge}, booktitle = {Proceedings of the Conference on Information Technology for Social Good (GoodIT 2021)}, title = {{The ADAPT Project: Adaptive and Autonomous Data Performance Connectivity and Decentralized Transport Network}}, year = {2021}, month = {sep}, pages = {115--120}, publisher = {ACM}, abstract = {The ADAPT project started during the most critical phase of the COVID-19 outbreak in Europe when the demand for Personal Protective Equipment (PPE) from each country's healthcare system surpassed national stock amounts. Due to national shutdowns, reduced transport logistics, and containment measures on the federal and provincial levels, the authorities could not meet the rising demand from the health care system on the PPE equipment. Fortunately, the PPE production capacities in China have regained (and expanded) their available capacities through which Austria now can get the demand of PPE to protect its citizens. ADAPT develops an adaptive and autonomous decision-making network to support the involved stakeholders along the PPE supply chain to save and protect human lives. The ADAPT decentralized blockchain platform optimizes supply, demand, and transport capacities between China and Austria with transparent, real-time certification checks on equipment, production documentation, and intelligent decision-making capabilities at all levels of this multidimensional logistic problem.}, doi = {10.1145/3462203.3475880}, url = {https://dl.acm.org/doi/10.1145/3462203.3475880} } @InProceedings{Hellwagner2021, author = {Antonia Stornig and Aymen Fakhreddine and Hellwagner, Hermann and Petar Popovski and Christian Bettstetter}, booktitle = {2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring)}, title = {{Video Quality and Latency for UAV Teleoperation over {LTE}: A Study with ns3}}, year = {2021}, month = {apr}, pages = {1--7}, publisher = {IEEE}, abstract = {Teleoperation of an unmanned aerial vehicle (UAV) is a challenging mobile application with real-time control from a first-person view. It poses stringent latency requirements for both video and control traffic. This paper studies the video quality and latencies for UAV teleoperation over LTE using ns3 simulations. A key ingredient is the latency budget model. We observe that the latency of the video is higher and more sensitive to mobility than that of the control traffic. The latency is influenced by the traffic variation caused by the variable bit rate of the streaming application. High mobility tends to increase latency and lead to more outliers, being problematic in real-time control.}, doi = {10.1109/vtc2021-spring51267.2021.9448676}, keywords = {Drone, teleoperation, video streaming, ns3, simulation, QoS, QoE}, url = {https://ieeexplore.ieee.org/document/9448676} } @InProceedings{Ghamsarian2021, author = {Negin Ghamsarian and Mario Taschwer and Doris Putzgruber-Adamitsch and Stephanie Sarny and Klaus Schoeffmann}, booktitle = {2020 25th International Conference on Pattern Recognition (ICPR)}, title = {{Relevance Detection in Cataract Surgery Videos by Spatio- Temporal Action Localization}}, year = {2021}, month = {jan}, pages = {10720--10727}, publisher = {IEEE}, abstract = {In cataract surgery, the operation is performed with the help of a microscope. Since the microscope enables watching real-time surgery by up to two people only, a major part of surgical training is conducted using the recorded videos. To optimize the training procedure with the video content, the surgeons require an automatic relevance detection approach. In addition to relevance-based retrieval, these results can be further used for skill assessment and irregularity detection in cataract surgery videos. In this paper, a three-module framework is proposed to detect and classify the relevant phase segments in cataract videos. Taking advantage of an idle frame recognition network, the video is divided into idle and action segments. To boost the performance in relevance detection, the cornea where the relevant surgical actions are conducted is detected in all frames using Mask R-CNN. The spatiotemporally localized segments containing higher-resolution information about the pupil texture and actions, and complementary temporal information from the same phase are fed into the relevance detection module. This module consists of four parallel recurrent CNNs being responsible to detect four relevant phases that have been defined with medical experts. The results will then be integrated to classify the action phases as irrelevant or one of four relevant phases. Experimental results reveal that the proposed approach outperforms static CNNs and different configurations of feature-based and end-to-end recurrent networks.}, doi = {10.1109/icpr48806.2021.9412525}, url = {https://ieeexplore.ieee.org/document/9412525} } @InProceedings{Farahani2021b, author = {Reza Farahani}, booktitle = {Proceedings of the 12th ACM Multimedia Systems Conference}, title = {{CDN and SDN Support and Player Interaction for HTTP Adaptive Video Streaming}}, year = {2021}, month = {jun}, pages = {398--402}, publisher = {ACM}, abstract = {Video streaming has become one of the most prevailing, bandwidth-hungry, and latency-sensitive Internet applications. HTTP Adaptive Streaming (HAS) has become the dominant video delivery mechanism over the Internet. Lack of coordination among the clients and lack of awareness of the network in pure client-based adaptive video bitrate approaches have caused problems, such as sub-optimal data throughput from Content Delivery Network (CDN) or origin servers, high CDN costs, and non-satisfactory users' experience. Recent studies have shown that network-assisted HAS techniques by utilizing modern networking paradigms, e.g., Software Defined Networking (SDN), Network Function Virtualization(NFV), and edge computing can significantly improve HAS system performance. In this doctoral study, we leverage the aforementioned modern networking paradigms and design network-assistance for/by HAS clients to improve HAS systems performance and CDN/network utilization. We present four fundamental research questions to target different challenges in devising a network-assisted HAS system.}, doi = {10.1145/3458305.3478464}, url = {https://dl.acm.org/doi/abs/10.1145/3458305.3478464} } @InProceedings{Farahani2021a, author = {Reza Farahani and Farzad Tashtarian and Hadi Amirpour and Christian Timmerer and Mohammad Ghanbari and Hellwagner, Hermann}, booktitle = {2021 IEEE 46th Conference on Local Computer Networks (LCN)}, title = {{CSDN: CDN-Aware QoE Optimization in SDN-Assisted HTTP Adaptive Video Streaming}}, year = {2021}, month = {oct}, pages = {525--532}, publisher = {IEEE}, abstract = {Recent studies have revealed that network-assisted techniques, by providing a comprehensive view of the network, improve HTTP Adaptive Streaming (HAS) system performance significantly. This paper leverages the capability of Software-Defined Networking, Network Function Virtualization, and edge computing to introduce a CDN-Aware QoE Optimization in SDN-Assisted Adaptive Video Streaming (CSDN) framework. We employ virtualized edge entities to collect various information items and run an optimization model with a new server/segment selection approach in a time-slotted fashion to serve the clients’ requests by selecting optimal cache servers. In case of a cache miss, a client’s request is served by an optimal replacement quality from a cache server, by a quality transcoded from an optimal replacement quality at the edge, or by the originally requested quality from the origin server. Comprehensive experiments conducted on a large-scale testbed demonstrate that CSDN outperforms other approaches in terms of the users’ QoE and network utilization.}, doi = {10.1109/lcn52139.2021.9524970}, keywords = {Dynamic Adaptive Streaming over HTTP (DASH), Edge Computing, Network-Assisted Video Streaming, Quality of Experience (QoE), Software Defined Networking (SDN), Network Function Virtualization (NFV), Video Transcoding, Content Delivery Network (CDN)}, url = {https://ieeexplore.ieee.org/document/9524970} } @InProceedings{Farahani2021, author = {Reza Farahani and Farzad Tashtarian and Alireza Erfanian and Christian Timmerer and Mohammad Ghanbari and Hellwagner, Hermann}, booktitle = {Proceedings of the 31st ACM Workshop on Network and Operating Systems Support for Digital Audio and Video}, title = {{ES-HAS: an edge- and SDN-assisted framework for HTTP adaptive video streaming}}, year = {2021}, month = {jul}, pages = {50--57}, publisher = {ACM}, abstract = {Recently, HTTP Adaptive Streaming (HAS) has become the dominant video delivery technology over the Internet. In HAS, clients have full control over the media streaming and adaptation processes. Lack of coordination among the clients and lack of awareness of the network conditions may lead to sub-optimal user experience and resource utilization in a pure client-based HAS adaptation scheme. Software Defined Networking (SDN) has recently been considered to enhance the video streaming process. In this paper, we leverage the capability of SDN and Network Function Virtualization (NFV) to introduce an edge- and SDN-assisted video streaming framework called ES-HAS. We employ virtualized edge components to collect HAS clients' requests and retrieve networking information in a time-slotted manner. These components then perform an optimization model in a time-slotted manner to efficiently serve clients' requests by selecting an optimal cache server (with the shortest fetch time). In case of a cache miss, a client's request is served (i) by an optimal replacement quality (only better quality levels with minimum deviation) from a cache server, or (ii) by the original requested quality level from the origin server. This approach is validated through experiments on a large-scale testbed, and the performance of our framework is compared to pure client-based strategies and the SABR system [12]. Although SABR and ES-HAS show (almost) identical performance in the number of quality switches, ES-HAS outperforms SABR in terms of playback bitrate and the number of stalls by at least 70% and 40%, respectively.}, doi = {10.1145/3458306.3460997}, keywords = {Dynamic Adaptive Streaming over HTTP (DASH), Edge Computing, Network-Assisted Video Streaming, Quality of Experience (QoE), Software Defined Networking (SDN), Network Function Virtualization (NFV)}, url = {https://dl.acm.org/doi/10.1145/3458306.3460997} } @InProceedings{Erfanian2021c, author = {Alireza Erfanian}, booktitle = {Proceedings of the 12th ACM Multimedia Systems Conference}, title = {{Optimizing QoE and Latency of Live Video Streaming Using Edge Computing and In-Network Intelligence}}, year = {2021}, month = {jun}, pages = {373--377}, publisher = {ACM}, abstract = {Live video streaming traffic and related applications have experienced significant growth in recent years. More users have started generating and delivering live streams with high quality (e.g., 4K resolution) through popular online streaming platforms such as YouTube, Twitch, and Facebook. Typically, the video contents are generated by streamers and watched by many audiences, which are geographically distributed in various locations far away from the streamers' locations. The resource limitation in the network (e.g., bandwidth) is a challenging issue for network and video providers to meet the users' requested quality. In this thesis, we will investigate optimizing QoEand end-to-end (E2E) latency of live video streaming by leveraging edge computing capabilities and in-network intelligence. We present four main research questions aiming to address the various challenges in optimizing live streaming QoE and E2E latency by employing edge computing and in-network intelligence.}, doi = {10.1145/3458305.3478459}, url = {https://dl.acm.org/doi/10.1145/3458305.3478459} } @InProceedings{Erfanian2021b, author = {Alireza Erfanian and Hadi Amirpour and Farzad Tashtarian and Christian Timmerer and Hellwagner, Hermann}, booktitle = {Proceedings of the Workshop on Design, Deployment, and Evaluation of Network-assisted Video Streaming}, title = {{LwTE-Live: Light-weight Transcoding at the Edge for Live Streaming}}, year = {2021}, month = {dec}, pages = {22--28}, publisher = {ACM}, abstract = {Live video streaming is widely embraced in video services, and its applications have attracted much attention in recent years. The increased number of users demanding high quality (e.g., 4K resolution) live videos increases the bandwidth utilization in the backhaul network. To decrease bandwidth utilization in HTTP Adaptive Streaming (HAS), in on-the-fly transcoding approaches, only the highest bitrate representation is delivered to the edge, and other representations are generated by transcoding at the edge. However, this approach is inefficient due to the high transcoding cost. In this paper, we propose a light-weight transcoding at the edge method for live applications, LwTE-Live, to decrease the bandwidth utilization and the overall live streaming cost. During the encoding processes at the origin server, the optimal encoding decisions are saved as metadata and the metadata replaces the corresponding representation in the bitrate ladder. The significantly reduced size of the metadata compared to its corresponding representation decreases the bandwidth utilization. The extracted metadata is then utilized at the edge to decrease the transcoding time. We formulate the problem as a Mixed-Binary Linear Programming (MBLP) model to optimize the live streaming cost, including the bandwidth and computation costs. We compare the proposed model with state-of-the-art approaches, and the experimental results show that our proposed method saves the cost and backhaul bandwidth utilization up to 34% and 45%, respectively.}, doi = {10.1145/3488662.3493829}, url = {https://dl.acm.org/doi/10.1145/3488662.3493829} } @InProceedings{Cetinkaya2021b, author = {Ekrem Cetinkaya}, booktitle = {Proceedings of the 12th ACM Multimedia Systems Conference}, title = {{Machine Learning Based Video Coding Enhancements for HTTP Adaptive Streaming}}, year = {2021}, month = {jun}, pages = {418--422}, publisher = {ACM}, abstract = {Video traffic comprises the majority of today's Internet traffic, and HTTP Adaptive Streaming (HAS) is the preferred method to deliver video content over the Internet. Increasing demand for video and the improvements in the video display conditions over the years caused an increase in the video coding complexity. This increased complexity brought the need for more efficient video streaming and coding solutions. The latest standard video codecs can reduce the size of the videos by using more efficient tools with higher time-complexities. The plans for integrating machine learning into upcoming video codecs raised the interest in applied machine learning for video coding. In this doctoral study, we aim to propose applied machine learning methods to video coding, focusing on HTTP adaptive streaming. We present four primary research questions to target different challenges in video coding for HTTP adaptive streaming.}, doi = {10.1145/3458305.3478468}, url = {https://dl.acm.org/doi/10.1145/3458305.3478468} } @InProceedings{Barcis2021a, author = {Michal Barcis and Hellwagner, Hermann}, booktitle = {2021 Wireless Days (WD)}, title = {{Information Distribution in Multi-Robot Systems: Adapting to Varying Communication Conditions}}, year = {2021}, month = {jun}, pages = {1--8}, publisher = {IEEE}, abstract = {This work addresses the problem of application-layer congestion control in multi-robot systems (MRS). It is motivated by the fact that many MRS constrain the amount of transmitted data in order to avoid congestion in the network and ensure that critical messages get delivered. However, such constraints often need to be manually tuned and assume constant network capabilities. We introduce the adaptive goodput constraint, which smoothly adapts to varying communication conditions. It is suitable for long-term communication planning, where rapid changes are undesirable. We analyze the introduced method in a simulation-based study and show its practical applicability using mobile robots.}, doi = {10.1109/wd52248.2021.9508324}, keywords = {Wireless communication, Adaptation models, Adaptive systems, Limiting, Control systems, Data models, Planning}, url = {https://ieeexplore.ieee.org/document/9508324} } @InProceedings{Amirpourazarian2021a, author = {Hadi Amirpourazarian and Christian Timmerer and Mohammad Ghanbari}, booktitle = {2021 Data Compression Conference (DCC)}, title = {{SLFC: Scalable Light Field Coding}}, year = {2021}, month = {mar}, pages = {43-52}, publisher = {IEEE}, abstract = {Light field imaging enables some post-processing capabilities like refocusing, changing view perspective, and depth estimation. As light field images are represented by multiple views they contain a huge amount of data that makes compression inevitable. Although there are some proposals to efficiently compress light field images, their main focus is on encoding efficiency. However, some important functionalities such as viewpoint and quality scalabilities, random access, and uniform quality distribution have not been addressed adequately. In this paper, an efficient light field image compression method based on a deep neural network is proposed, which classifies multiple views into various layers. In each layer, the target view is synthesized from the available views of previously encoded/decoded layers using a deep neural network. This synthesized view is then used as a virtual reference for the target view inter-coding. In this way, random access to an arbitrary view is provided. Moreover, uniform quality distribution among multiple views is addressed. In higher bitrates where random access to an arbitrary view is more crucial, the required bitrate to access the requested view is minimized.}, doi = {10.1109/dcc50243.2021.00012}, keywords = {Light field, Compression, Scalable, Random Access}, url = {https://ieeexplore.ieee.org/document/9418753} } @InProceedings{Amirpourazarian2021, author = {Hadi Amirpourazarian and Christian Timmerer and Mohammad Ghanbari}, booktitle = {2021 IEEE International Conference on Multimedia and Expo (ICME)}, title = {{PSTR: Per-Title Encoding Using Spatio-Temporal Resolutions}}, year = {2021}, month = jun, pages = {1--6}, publisher = {IEEE}, abstract = {Current per-title encoding schemes encode the same video content (or snippets/subsets thereof) at various bitrates and spatial resolutions to find an optimal bitrate ladder for each video content. Compared to traditional approaches, in which a predefined, content-agnostic ("fit-to-all") encoding ladder is applied to all video contents, per-title encoding can result in (i) a significant decrease of storage and delivery costs and (ii) an increase in the Quality of Experience (QoE). In the current per-title encoding schemes, the bitrate ladder is optimized using only spatial resolutions, while we argue that with the emergence of high framerate videos, this principle can be extended to temporal resolutions as well. In this paper, we improve the per-title encoding for each content using spatio-temporal resolutions. Experimental results show that our proposed approach doubles the performance of bitrate saving by considering both temporal and spatial resolutions compared to considering only spatial resolutions.}, doi = {10.1109/icme51207.2021.9428247}, keywords = {Bitrate ladder, per-title encoding, framerate, spatial resolution}, url = {https://ieeexplore.ieee.org/document/9428247} } @InProceedings{Amirpour2021b, author = {Hadi Amirpour and Raimund Schatz and Christian Timmerer and Mohammad Ghanbari}, booktitle = {2021 International Conference on Visual Communications and Image Processing (VCIP)}, title = {{On the Impact of Viewing Distance on Perceived Video Quality}}, year = {2021}, month = {dec}, pages = {1--5}, publisher = {IEEE}, abstract = {Due to the growing importance of optimizing the quality and efficiency of video streaming delivery, accurate assessment of user-perceived video quality becomes increasingly important. However, due to the wide range of viewing distances encountered in real-world viewing settings, the perceived video quality can vary significantly in everyday viewing situations. In this paper, we investigate and quantify the influence of viewing distance on perceived video quality. A subjective experiment was conducted with full HD sequences at three different fixed viewing distances, with each video sequence being encoded at three different quality levels. Our study results confirm that the viewing distance has a significant influence on the quality assessment. In particular, they show that an increased viewing distance generally leads to increased perceived video quality, especially at low media encoding quality levels. In this context, we also provide an estimation of potential bitrate savings that knowledge of actual viewing distance would enable in practice. Since current objective video quality metrics do not systematically take into account viewing distance, we also analyze and quantify the influence of viewing distance on the correlation between objective and subjective metrics. Our results confirm the need for distance-aware objective metrics when the accurate prediction of perceived video quality in real-world environments is required.}, doi = {10.1109/vcip53242.2021.9675431}, keywords = {Measurement, Image coding, Visual communication, Video sequences, Estimation, Streaming media, Media, video streaming, QoE, viewing distance, subjective testing}, url = {https://ieeexplore.ieee.org/document/9675431} } @InProceedings{Amirpour2021a, author = {Hadi Amirpour and Hannaneh Barahouei Pasandi and Christian Timmerer and Mohammad Ghanbari}, booktitle = {2021 International Conference on Visual Communications and Image Processing (VCIP)}, title = {{Improving Per-title Encoding for HTTP Adaptive Streaming by Utilizing Video Super-resolution}}, year = {2021}, month = {dec}, pages = {1--5}, publisher = {IEEE}, abstract = {In per-title encoding, to optimize a bitrate ladder over spatial resolution, each video segment is downscaled to a set of spatial resolutions, and they are all encoded at a given set of bitrates. To find the highest quality resolution for each bitrate, the low-resolution encoded videos are upscaled to the original resolution, and a convex hull is formed based on the scaled qualities. Deep learning-based video super-resolution (VSR) approaches show a significant gain over traditional upscaling approaches, and they are becoming more and more efficient over time. This paper improves the per-title encoding over the upscaling methods by using deep neural network-based VSR algorithms. Utilizing a VSR algorithm by improving the quality of low-resolution encodings can improve the convex hull. As a result, it will lead to an improved bitrate ladder. To avoid bandwidth wastage at perceptually lossless bitrates, a maximum threshold for the quality is set, and encodings beyond it are eliminated from the bitrate ladder. Similarly, a minimum threshold is set to avoid low-quality video delivery. The encodings between the maximum and minimum thresholds are selected based on one Just Noticeable Difference. Our experimental results show that the proposed per-title encoding results in a 24% bitrate reduction and 53% storage reduction compared to the state-of-the-art method.}, doi = {10.1109/vcip53242.2021.9675403}, keywords = {Image coding, Visual communication, Bit rate, Superresolution, Bandwidth, Streaming media, Spatial resolution, HAS, per-title, deep learning, compression, bitrate ladder}, url = {https://ieeexplore.ieee.org/document/9675403} } @InProceedings{AguilarArmijo2021a, author = {Jesus Aguilar-Armijo}, booktitle = {Proceedings of the 12th ACM Multimedia Systems Conference}, title = {{Multi-access Edge Computing for Adaptive Bitrate Video Streaming}}, year = {2021}, month = {jun}, pages = {378--382}, publisher = {ACM}, abstract = {Video streaming is the most used service in mobile networks and its usage will continue growing in the upcoming years. Due to this increase, content delivery should be improved as a key aspect of video streaming service, supporting higher bandwidth demand while assuring high quality of experience (QoE) for all the users. Multi-access edge computing (MEC) is an emerging paradigm that brings computational power and storage closer to the user. It is seen in the industry as a key technology for 5G mobile networks, with the goals of reducing latency, ensuring highly efficient network operation, improving service delivery and offering an improved user experience, among others. In this doctoral study, we aim to leverage the possibilities of MEC to improve the content delivery of video streaming services. We present four main research questions to target the different challenges in content delivery for HTTP Adaptive Streaming.}, doi = {10.1145/3458305.3478460}, url = {https://dl.acm.org/doi/10.1145/3458305.3478460} } @InProceedings{AguilarArmijo2021, author = {Jesus Aguilar-Armijo and Christian Timmerer and Hellwagner, Hermann}, booktitle = {2021 IEEE 46th Conference on Local Computer Networks (LCN)}, title = {{EADAS: Edge Assisted Adaptation Scheme for HTTP Adaptive Streaming}}, year = {2021}, month = {oct}, pages = {487--494}, publisher = {IEEE}, abstract = {Mobile networks equipped with edge computing nodes enable access to information that can be leveraged to assist client-based adaptive bitrate (ABR) algorithms in making better adaptation decisions to improve both Quality of Experience (QoE) and fairness. For this purpose, we propose a novel on-the-fly edge mechanism, named EADAS (Edge Assisted Adaptation Scheme for HTTP Adaptive Streaming), located at the edge node that assists and improves the ABR decisions on-the-fly. EADAS proposes (i) an edge ABR algorithm to improve QoE and fairness for clients and (ii) a segment prefetching scheme. The results show a QoE increase of 4.6%, 23.5%, and 24.4% and a fairness increase of 11%, 3.4%, and 5.8% when using a buffer-based, a throughput-based, and a hybrid ABR algorithm, respectively, at the client compared with client-based algorithms without EADAS. Moreover, QoE and fairness among clients can be prioritized using parameters of the EADAS algorithm according to service providers’ requirements.}, doi = {10.1109/lcn52139.2021.9524883}, keywords = {Edge Computing, HTTP Adaptive Streaming, Network-assisted Video Streaming, Quality of Experience}, url = {https://ieeexplore.ieee.org/document/9524883} } @InProceedings{Zabrovskiy2020, author = {Anatoliy Zabrovskiy and Prateek Agrawal and Roland Matha and Christian Timmerer and Radu Prodan}, booktitle = {2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM)}, title = {{ComplexCTTP: Complexity Class Based Transcoding Time Prediction for Video Sequences Using Artificial Neural Network}}, year = {2020}, month = sep, pages = {316--325}, publisher = {{IEEE}}, abstract = {HTTP Adaptive Streaming of video content is becoming an integral part of the Internet and accounts for the majority of today’s traffic. Although Internet bandwidth is constantly increasing, video compression technology plays an important role and the major challenge is to select and set up multiple video codecs, each with hundreds of transcoding parameters. Additionally, the transcoding speed depends directly on the selected transcoding parameters and the infrastructure used. Predicting transcoding time for multiple transcoding parameters with different codecs and processing units is a challenging task, as it depends on many factors. This paper provides a novel and considerably fast method for transcoding time prediction using video content classification and neural network prediction. Our artificial neural network (ANN) model predicts the transcoding times of video segments for state of the art video codecs based on transcoding parameters and content complexity. We evaluated our method for two video codecs/implementations (AVC/x264 and HEVC/x265) as part of large-scale HTTP Adaptive Streaming services. The ANN model of our method is able to predict the transcoding time by minimizing the mean absolute error (MAE) to 1.37 and 2.67 for x264 and x265 codecs, respectively. For x264, this is an improvement of 22\% compared to the state of the art.}, doi = {10.1109/bigmm50055.2020.00056}, keywords = {Transcoding time prediction, adaptive streaming, video transcoding, neural networks, video encoding, video complexity class, HTTP adaptive streaming, MPEG-DASH}, url = {https://ieeexplore.ieee.org/document/9232616} } @InProceedings{VenkataPhaniKumar2020, author = {Venkata Phani Kumar Malladi and Christian Timmerer and Hellwagner, Hermann}, booktitle = {2020 IEEE International Conference on Multimedia and Expo (ICME)}, title = {{Mipso: Multi-Period Per-Scene Optimization For HTTP Adaptive Streaming}}, year = {2020}, month = {jul}, pages = {1--6}, publisher = {IEEE}, abstract = {Video delivery over the Internet has become more and more established in recent years due to the widespread use of Dynamic Adaptive Streaming over HTTP (DASH). The current DASH specification defines a hierarchical data model for Media Presentation Descriptions (MPDs) in terms of periods, adaptation sets, representations and segments. Although multi-period MPDs are widely used in live streaming scenarios, they are not fully utilized in Video-on-Demand (VoD) HTTP adaptive streaming (HAS) scenarios. In this paper, we introduce MiPSO, a framework for Multi–Period per-Scene Optimization, to examine multiple periods in VoD HAS scenarios. MiPSO provides different encoded representations of a video at either (i) maximum possible quality or (ii) minimum possible bitrate, beneficial to both service providers and subscribers. In each period, the proposed framework adjusts the video representations (resolution-bitrate pairs) by taking into account the complexities of the video content, with the aim of achieving streams at either higher qualities or lower bitrates. The experimental evaluation with a test video data set shows that the MiPSO reduces the average bitrate of streams with the same visual quality by approximately 10% or increases the visual quality of streams by at least 1 dB in terms of Peak Signal-to-Noise (PSNR) at the same bitrate compared to conventional approaches to video content delivery.}, doi = {10.1109/icme46284.2020.9102775}, keywords = {Adaptive Streaming, Video-on-Demand, Per-Scene Encoding, Media Presentation Description}, url = {https://ieeexplore.ieee.org/document/9102775} } @InProceedings{Timmerer2020, author = {Christian Timmerer and Hellwagner, Hermann}, booktitle = {Proceedings of the Brazilian Symposium on Multimedia and the Web}, title = {{HTTP Adaptive Streaming: Where Is It Heading?}}, year = {2020}, month = {nov}, pages = {349--350}, publisher = {ACM}, abstract = {In this contribution, we present selected novel approaches and results of our research work in the ATHENA Christian Doppler Laboratory (Adaptive Streaming over HTTP and Emerging Networked Multimedia Services), a major research project at our department jointly funded by public sources and industry. By putting this work also into the context of related ongoing research activities, we aim at working out where HTTP Adaptive Streaming is currently heading.}, doi = {10.1145/3428658.3434574}, keywords = {HTTP adaptive streaming, video coding, machine learning, edge computing, immersive media, quality of experience}, url = {https://dl.acm.org/doi/10.1145/3428658.3434574} } @InProceedings{Taraghi2020, author = {Babak Taraghi and Anatoliy Zabrovskiy and Christian Timmerer and Hellwagner, Hermann}, booktitle = {Proceedings of the 11th ACM Multimedia Systems Conference}, title = {{Cloud-based Adaptive Video Streaming Evaluation Framework for the Automated Testing of Media Players CAdViSE}}, year = {2020}, month = {may}, pages = {349--352}, publisher = {ACM}, abstract = {Attempting to cope with fluctuations of network conditions in terms of available bandwidth, latency and packet loss, and to deliver the highest quality of video (and audio) content to users, research on adaptive video streaming has attracted intense efforts from the research community and huge investments from technology giants. How successful these efforts and investments are, is a question that needs precise measurements of the results of those technological advancements. HTTP-based Adaptive Streaming (HAS) algorithms, which seek to improve video streaming over the Internet, introduce video bitrate adaptivity in a way that is scalable and efficient. However, how each HAS implementation takes into account the wide spectrum of variables and configuration options, brings a high complexity to the task of measuring the results and visualizing the statistics of the performance and quality of experience. In this paper, we introduce CAdViSE, our Cloud-based Adaptive Video Streaming Evaluation framework for the automated testing of adaptive media players. The paper aims to demonstrate a test environment which can be instantiated in a cloud infrastructure, examines multiple media players with different network attributes at defined points of the experiment time, and finally concludes the evaluation with visualized statistics and insights into the results.}, doi = {10.1145/3339825.3393581}, keywords = {HTTP Adaptive Streaming, Media Players, MPEG-DASH, Network Emulation, Automated Testing, Quality of Experience}, url = {https://dl.acm.org/doi/10.1145/3339825.3393581} } @InProceedings{Sokolova2020, author = {Natalia Sokolova and Mario Taschwer and Stephanie Sarny and Doris Putzgruber-Adamitsch and Klaus Schoeffmann}, booktitle = {2020 IEEE 17th International Symposium on Biomedical Imaging Workshops (ISBI Workshops)}, title = {{Pixel-Based Iris and Pupil Segmentation in Cataract Surgery Videos Using Mask R-CNN}}, year = {2020}, month = {apr}, publisher = {IEEE}, abstract = {Automatically detecting clinically relevant events in surgery video recordings is becoming increasingly important for documentary, educational, and scientific purposes in the medical domain. From a medical image analysis perspective, such events need to be treated individually and associated with specific visible objects or regions. In the field of cataract surgery (lens replacement in the human eye), pupil reaction (dilation or restriction) during surgery may lead to complications and hence represents a clinically relevant event. Its detection requires automatic segmentation and measurement of pupil and iris in recorded video frames. In this work, we contribute to research on pupil and iris segmentation methods by (1) providing a dataset of 82 annotated images for training and evaluating suitable machine learning algorithms, and (2) applying the Mask R-CNN algorithm to this problem, which – in contrast to existing techniques for pupil segmentation – predicts free-form pixel-accurate segmentation masks for iris and pupil. The proposed approach achieves consistent high segmentation accuracies on several metrics while delivering an acceptable prediction efficiency, establishing a promising basis for further segmentation and event detection approaches on eye surgery videos.}, doi = {10.1109/isbiworkshops50223.2020.9153367}, keywords = {object segmentation, cataract surgery videos, mask RCNN, deep learning}, url = {https://ieeexplore.ieee.org/document/9153367} } @InProceedings{Palanisamy2020, author = {Anandhakumar Palanisamy and Mirsat Sefidanoski and Spiros Koulouzis and Carlos Rubia and Nishant Saurabh and Radu Prodan}, booktitle = {2020 IEEE Symposium on Computers and Communications (ISCC)}, title = {{Decentralized Social Media Applications as a Service: a Car-Sharing Perspective}}, year = {2020}, month = {jul}, pages = {1--7}, publisher = {IEEE}, abstract = {Social media applications are essential for next generation connectivity. Today, social media are centralized platforms with a single proprietary organization controlling the network and posing critical trust and governance issues over the created and propagated content. The ARTICONF project funded by the European Union’s Horizon 2020 program researches a decentralized social media platform based on a novel set of trustworthy, resilient and globally sustainable tools to fulfil the privacy, robustness and autonomy-related promises that proprietary social media platforms have failed to deliver so far. This paper presents the ARTICONF approach to a car-sharing use case application, as a new collaborative peer-to-peer model providing an alternative solution to private car ownership. We describe a prototype implementation of the car-sharing social media application and illustrate through real snapshots how the different ARTICONF tools support it in a simulated scenario.}, doi = {10.1109/iscc50000.2020.9219617}, keywords = {Social media, car-sharing, decentralization, blockchain}, url = {https://ieeexplore.ieee.org/document/9219617} } @InProceedings{Nguyen2020a, author = {Minh Nguyen and Christian Timmerer and Hellwagner, Hermann}, booktitle = {Proceedings of the 25th ACM Workshop on Packet Video}, title = {{H2BR: An HTTP/2-based Retransmission Technique to Improve the QoE of Adaptive Video Streaming}}, year = {2020}, month = {jun}, pages = {1--7}, publisher = {ACM}, abstract = {HTTP-based Adaptive Streaming (HAS) plays a key role in over-the-top video streaming. It contributes towards reducing the rebuffering duration of video playout by adapting the video quality to the current network conditions. However, it incurs variations of video quality in a streaming session because of the throughput fluctuation, which impacts the user’s Quality of Experience (QoE). Besides, many adaptive bitrate (ABR) algorithms choose the lowest-quality segments at the beginning of the streaming session to ramp up the playout buffer as soon as possible. Although this strategy decreases the startup time, the users can be annoyed as they have to watch a low-quality video initially. In this paper, we propose an efficient retransmission technique, namely H2BR, to replace low-quality segments being stored in the playout buffer with higher-quality versions by using features of HTTP/2 including (i) stream priority, (ii) server push, and (iii) stream termination. The experimental results show that H2BR helps users avoid watching low video quality during video playback and improves the user’s QoE. H2BR can decrease by up to more than 70% the time when the users suffer the lowest-quality video as well as benefits the QoE by up to 13%.}, doi = {10.1145/3386292.3397117}, keywords = {HTTP adaptive streaming, DASH, ABR algorithms, QoE, HTTP/2}, url = {https://dl.acm.org/doi/abs/10.1145/3386292.3397117} } @InProceedings{Nguyen2020, author = {Minh Nguyen and Hadi Amirpour and Christian Timmerer and Hellwagner, Hermann}, booktitle = {Proceedings of the Workshop on the Evolution, Performance, and Interoperability of QUIC}, title = {{Scalable High Efficiency Video Coding based HTTP Adaptive Streaming over QUIC}}, year = {2020}, month = {aug}, pages = {28--34}, publisher = {ACM}, abstract = {HTTP/2 has been explored widely for adaptive video streaming, but still suffers from Head-of-Line blocking, and three-way handshake delay due to TCP. Meanwhile, QUIC running on top of UDP can tackle these issues. In addition, although many adaptive bitrate (ABR) algorithms have been proposed for scalable and non-scalable video streaming, the literature lacks an algorithm designed for both types of video streaming approaches. In this paper, we investigate the impact of QUIC and HTTP/2 on the performance of ABR algorithms. Moreover, we propose an efficient approach for utilizing scalable video coding formats for adaptive video streaming that combines a traditional video streaming approach (based on non-scalable video coding formats) and a retransmission technique. The experimental results show that QUIC benefits significantly from our proposed method in the context of packet loss and retransmission. Compared to HTTP/2, it improves the average video quality and provides a smoother adaptation behavior. Finally, we demonstrate that our proposed method originally designed for non-scalable video codecs also works efficiently for scalable videos such as Scalable High Efficiency Video Coding (SHVC).}, doi = {10.1145/3405796.3405829}, keywords = {QUIC, H2BR, HTTP adaptive streaming, Retransmission, SHVC}, url = {https://dl.acm.org/doi/10.1145/3405796.3405829} } @InProceedings{Moll2020, author = {Philipp Moll and Veit Frick and Natascha Rauscher and Mathias Lux}, booktitle = {Proceedings of the 12th ACM International Workshop on Immersive Mixed and Virtual Environment Systems}, title = {{How players play games}}, year = {2020}, month = {jun}, publisher = {ACM}, abstract = {The popularity of computer games is remarkably high and is still growingevery year. Despite this popularity and the economical importance of gaming,research in game design, or to be more precise, of game mechanics that can beused to improve the enjoyment of a game, is still scarce. In this paper, weanalyze Fortnite, one of the currently most successful games, and observe howplayers play the game. We investigate what makes playing the game enjoyable byanalyzing video streams of experienced players from game streaming platformsand by conducting a user study with players who are new to the game. Weformulate four hypotheses about how game mechanics influence the way playersinteract with the game and how it influences player enjoyment. We presentdifferences in player behavior between experienced players and beginners anddiscuss how game mechanics could be used to improve the enjoyment forbeginners. In addition, we describe our approach to analyze games withoutaccess to game-internal data by using a toolchain which automatically extractsgame information from video streams.}, doi = {10.1145/3386293.3397113}, keywords = {Online Games, Game Mechanics, Game Design, Video Analysis}, url = {https://dl.acm.org/doi/10.1145/3386293.3397113} } @InProceedings{Messous2020, author = {Mohamed Ayoub Messous and Hellwagner, Hermann and Sidi-Mohammed Senouci and Driton Emini and Dominik Schnieders}, booktitle = {ICC 2020 - 2020 IEEE International Conference on Communications (ICC)}, title = {{Edge Computing for Visual Navigation and Mapping in a UAV Network}}, year = {2020}, month = {jun}, pages = {1--6}, publisher = {IEEE}, abstract = {This research work presents conceptual considerations and quantitative evaluations into how integrating computation offloading to edge computing servers would offer a paradigm shift for an effective deployment of autonomous drones. The specific mission that has been considered is collaborative autonomous navigation and mapping in a 3D environment of a small drone network. Specifically, in order to achieve this mission, each drone is required to compute a low latency, highly compute intensive task in a timely manner. The proposed model decides for each task, while considering the impact on performance and mission requirements, whether to (i) compute locally, (ii) offload to the edge server, or (iii) to the ground station. Extensive simulation work was performed to assess the effectiveness of the proposed scheme compared to other models.}, doi = {10.1109/icc40277.2020.9149087}, keywords = {UAV Network, Edge Computing, Computation Offloading, Visual Navigation and Mapping}, url = {https://ieeexplore.ieee.org/document/9149087} } @InProceedings{Mazdin2020, author = {Petra Mazdin and Michal Barcis and Hellwagner, Hermann and Bernhard Rinner}, booktitle = {2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)}, title = {{Distributed Task Assignment in Multi-Robot Systems based on Information Utility}}, year = {2020}, month = {aug}, pages = {734--740}, publisher = {IEEE}, abstract = {Most multi-robot systems (MRS) require to coordinate the assignment of tasks to individual robots for efficient missions. Due to the dynamics, incomplete knowledge and changing requirements, the robots need to distribute their local state information within the MRS continuously during the mission. Since communication resources are limited and message transfers may be erroneous, the global state estimated by each robot may become inconsistent. This inconsistency may lead to degraded task assignment and mission performance. In this paper, we explore the effect and cost of communication and exploit information utility for online distributed task assignment. In particular, we model the usefulness of the transferred state information by its information utility and use it for controlling the distribution of local state information and for updating the global state. We compare our distributed, utility-based online task assignment with well-known centralized and auction-based methods and show how substantial reduction of communication effort still leads to successful mission completion. We demonstrate our approach in a wireless communication testbed using ROS2.}, doi = {10.1109/case48305.2020.9216982}, keywords = {Task analysis, Robot kinematics, Mathematical model, Multi-robot systems, Optimization, Heuristic algorithms}, url = {https://doi.org/10.1109/CASE48305.2020.9216982} } @InProceedings{Leibetseder2020a, author = {Andreas Leibetseder and Klaus Schoeffmann}, booktitle = {Proceedings of the 2020 International Conference on Multimedia Retrieval}, title = {{surgXplore: Interactive Video Exploration for Endoscopy}}, year = {2020}, month = {jun}, pages = {397--401}, publisher = {ACM}, abstract = {Accumulating recordings of daily conducted surgical interventions such as endoscopic procedures for the long term generates very large video archives that are both difficult to search and explore. Since physicians utilize this kind of media routinely for documentation, treatment planning or education and training, it can be considered a crucial task to make said archives manageable in regards to discovering or retrieving relevant content. We present an interactive tool including a multitude of modalities for browsing, searching and filtering medical content, demonstrating its usefulness on over 140 hours of pre-processed laparoscopic surgery videos.}, doi = {10.1145/3372278.3391930}, keywords = {medical video exploration, endoscopy, interactive video retrieval}, url = {https://dl.acm.org/doi/10.1145/3372278.3391930} } @InProceedings{Leibetseder2020, author = {Andreas Leibetseder and Klaus Schoeffmann}, booktitle = {Proceedings of the Third Annual Workshop on Lifelog Search Challenge}, title = {{lifeXplore at the Lifelog Search Challenge 2020}}, year = {2020}, month = {jun}, pages = {37--42}, publisher = {ACM}, abstract = {Since its first iteration in 2018, the Lifelog Search Challenge (LSC) -- an interactive competition for retrieving lifelogging moments -- is co-located at the annual ACM International Conference on Multimedia Retrieval (ICMR) and has drawn international attention. With the goal of making an ever growing public lifelogging dataset searchable, several teams develop systems for quickly solving time-limited queries during the challenge. Having participated in both previous LSC iterations, i.e. LSC2018 and LSC2019, we present our lifeXplore system -- a video exploration and retrieval tool combining feature map browsing, concept search and filtering as well as hand-drawn sketching. The system is improved by including additional deep concept YOLO9000, optical character recognition (OCR) as well as adding uniform sampling as an alternative to the system's traditional underlying shot segmentation.}, doi = {10.1145/3379172.3391721}, keywords = {lifelogging, evaluation campaign, interactive image retrieval, video browsing}, url = {https://dl.acm.org/doi/10.1145/3379172.3391721} } @InProceedings{Kimovski_2020, author = {Dragi Kimovski and Dijana C. Bogatinoska and Narges Mehran and Aleksandar Karadimce and Natasa Paunkoska and Radu Prodan and Ninoslav Marina}, booktitle = {2020 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (BDCloud)}, title = {{Cloud-Edge Offloading Model for Vehicular Traffic Analysis}}, year = {2020}, month = {dec}, pages = {746--753}, publisher = {IEEE}, abstract = {The proliferation of smart sensing and computing devices, capable of collecting a vast amount of data, has made the gathering of the necessary vehicular traffic data relatively easy. However, the analysis of these big data sets requires computational resources, which are currently provided by the Cloud Data Centers. Nevertheless, the Cloud Data Centers can have unacceptably high latency for vehicular analysis applications with strict time requirements. The recent introduction of the Edge computing paradigm, as an extension of the Cloud services, has partially moved the processing of big data closer to the data sources, thus addressing this issue. Unfortunately, this unlocked multiple challenges related to resources management. Therefore, we present a model for scheduling of vehicular traffic analysis applications with partial task offloading across the Cloud - Edge continuum. The approach represents the traffic applications as a set of interconnected tasks composed into a workflow that can be partially offloaded to the Edge. We evaluated the approach through a simulated Cloud - Edge environment that considers two representative vehicular traffic applications with a focus on video stream analysis. Our results show that the presented approach reduces the application response time up to eight times while improving energy efficiency by a factor of four.}, doi = {10.1109/ispa-bdcloud-socialcom-sustaincom51426.2020.00119}, keywords = {Edge offloading, Cloud-Edge continuum, Application Scheduling, Particle Swarm Optimization}, url = {https://ieeexplore.ieee.org/document/9443969} } @InProceedings{Kashansky2020, author = {Vladislav Kashansky and Dragi Kimovski and Radu Prodan and Prateek Agrawal and Fabrizio Marozzo and Gabriel Iuhasz and Marek Marozzo and Javier Garcia-Blas}, booktitle = {2020 28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)}, title = {{M3AT: Monitoring Agents Assignment Model for Data-Intensive Applications}}, year = {2020}, month = {mar}, pages = {72--79}, publisher = {IEEE}, abstract = {Nowadays, massive amounts of data are acquired, transferred, and analyzed nearly in real-time by utilizing a large number of computing and storage elements interconnected through high-speed communication networks. However, one issue that still requires research effort is to enable efficient monitoring of applications and infrastructures of such complex systems. In this paper, we introduce a Integer Linear Programming (ILP) model called M3AT for optimised assignment of monitoring agents and aggregators on large-scale computing systems. We identified a set of requirements from three representative data-intensive applications and exploited them to define the model’s input parameters. We evaluated the scalability of M3AT using the Constraint Integer Programing (SCIP) solver with default configuration based on synthetic data sets. Preliminary results show that the model provides optimal assignments for systems composed of up to 200 monitoring agents while keeping the number of aggregators constant and demonstrates variable sensitivity with respect to the scale of monitoring data aggregators and limitation policies imposed.}, doi = {10.1109/pdp50117.2020.00018}, keywords = {Monitoring systems, high performance computing, aggregation, systems control, data-intensive systems, generalized assignment problem, SCIP optimization suite}, url = {https://ieeexplore.ieee.org/document/9092397} } @InProceedings{Hooft2020, author = {Jeroen van der Hooft and Maria Torres Vega and Christian Timmerer and Ali C. Begen and Filip De Turck and Raimund Schatz}, booktitle = {2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX)}, title = {{Objective and Subjective QoE Evaluation for Adaptive Point Cloud Streaming}}, year = {2020}, month = {may}, publisher = {IEEE}, abstract = {Volumetric media has the potential to provide the six degrees of freedom (6DoF) required by truly immersive media. However, achieving 6DoF requires ultra-high bandwidth transmissions, which real-world wide area networks cannot provide economically. Therefore, recent efforts have started to target efficient delivery of volumetric media, using a combination of compression and adaptive streaming techniques. It remains, however, unclear how the effects of such techniques on the user perceived quality can be accurately evaluated. In this paper, we present the results of an extensive objective and subjective quality of experience (QoE) evaluation of volumetric 6DoF streaming. We use PCC-DASH, a standards-compliant means for HTTP adaptive streaming of scenes comprising multiple dynamic point cloud objects. By means of a thorough analysis we investigate the perceived quality impact of the available bandwidth, rate adaptation algorithm, viewport prediction strategy and user’s motion within the scene. We determine which of these aspects has more impact on the user’s QoE, and to what extent subjective and objective assessments are aligned.}, doi = {10.1109/qomex48832.2020.9123081}, keywords = {Volumetric Media, HTTP Adaptive Streaming, 6DoF, MPEG V-PCC, QoE Assessment, Objective Metrics}, url = {https://ieeexplore.ieee.org/document/9123081} } @InProceedings{Gurrin2020, author = {Cathal Gurrin and Tu-Khiem Le and Van-Tu Ninh and Duc-Tien Dang-Nguyen and Björn Thor Jonsson and Jakub Loko and Wolfgang Hürst and Minh-Triet Tran and Klaus Schöffmann}, booktitle = {Proceedings of the 2020 International Conference on Multimedia Retrieval}, title = {{Introduction to the Third Annual Lifelog Search Challenge (LSC' 20)}}, year = {2020}, month = {jun}, pages = {584--585}, publisher = {{ACM}}, abstract = {The Lifelog Search Challenge (LSC) is an annual comparative benchmarking activity for comparing approaches to interactive retrieval from multi-modal lifelogs. LSC'20, the third such challenge, attracts fourteen participants with their interactive lifelog retrieval systems. These systems are comparatively evaluated in front of a live-audience at the LSC workshop at ACM ICMR'20 in Dublin, Ireland. This overview motivates the challenge, presents the dataset and system configuration used in the challenge, and briefly presents the participating teams.}, doi = {10.1145/3372278.3388043}, keywords = {Lifelog, interactive retrieval systems, benchmarking}, url = {https://dl.acm.org/doi/abs/10.1145/3372278.3388043} } @InProceedings{Ghamsarian2020b, author = {Negin Ghamsarian and Mario Taschwer and Klaus Schoeffmann}, booktitle = {2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)}, title = {{Deblurring Cataract Surgery Videos Using a Multi-Scale Deconvolutional Neural Network}}, year = {2020}, month = {apr}, pages = {872--876}, publisher = {IEEE}, abstract = {A common quality impairment observed in surgery videos is blur, caused by object motion or a defocused camera. Degraded image quality hampers the progress of machine-learning-based approaches in learning and recognizing semantic information in surgical video frames like instruments, phases, and surgical actions. This problem can be mitigated by automatically deblurring video frames as a preprocessing method for any subsequent video analysis task. In this paper, we propose and evaluate a multi-scale deconvolutional neural network to deblur cataract surgery videos. Experimental results confirm the effectiveness of the proposed approach in terms of the visual quality of frames as well as PSNR improvement.}, doi = {10.1109/isbi45749.2020.9098318}, keywords = {Video Deblurring, Deconvolutional Neural Networks, Cataract Surgery Videos}, url = {https://ieeexplore.ieee.org/document/9098318} } @InProceedings{Ghamsarian2020a, author = {Negin Ghamsarian}, booktitle = {Proceedings of the 2020 International Conference on Multimedia Retrieval}, title = {{Enabling Relevance-Based Exploration of Cataract Videos}}, year = {2020}, month = {jun}, pages = {378--382}, publisher = {ACM}, abstract = {Training new surgeons as one of the major duties of experienced expert surgeons demands a considerable supervisory investment of them. To expedite the training process and subsequently reduce the extra workload on their tight schedule, surgeons are seeking a surgical video retrieval system. Automatic workflow analysis approaches can optimize the training procedure by indexing the surgical video segments to be used for online video exploration. The aim of the doctoral project described in this paper is to provide the basis for a cataract video exploration system, that is able to (i) automatically analyze and extract the relevant segments of videos from cataract surgery, and (ii) provide interactive exploration means for browsing archives of cataract surgery videos. In particular, we apply deep-learning-based classification and segmentation approaches to cataract surgery videos to enable automatic phase and action recognition and similarity detection.}, doi = {10.1145/3372278.3391937}, keywords = {Action recognition, Phase recognition, Deep learning, Cataract surgery}, url = {https://dl.acm.org/doi/10.1145/3372278.3391937} } @InProceedings{Ghamsarian2020, author = {Negin Ghamsarian and Hadi Amirpourazarian and Christian Timmerer and Mario Taschwer and Klaus Schöffmann}, booktitle = {Proceedings of the 28th ACM International Conference on Multimedia}, title = {{Relevance-Based Compression of Cataract Surgery Videos Using Convolutional Neural Networks}}, year = {2020}, month = {oct}, pages = {3577--3585}, publisher = {ACM}, abstract = {Recorded cataract surgery videos play a prominent role in training and investigating the surgery, and enhancing the surgical outcomes. Due to storage limitations in hospitals, however, the recorded cataract surgeries are deleted after a short time and this precious source of information cannot be fully utilized. Lowering the quality to reduce the required storage space is not advisable since the degraded visual quality results in the loss of relevant information that limits the usage of these videos. To address this problem, we propose a relevance-based compression technique consisting of two modules: (i) relevance detection, which uses neural networks for semantic segmentation and classification of the videos to detect relevant spatio-temporal information, and (ii) content-adaptive compression, which restricts the amount of distortion applied to the relevant content while allocating less bitrate to irrelevant content. The proposed relevance-based compression framework is implemented considering five scenarios based on the definition of relevant information from the target audience's perspective. Experimental results demonstrate the capability of the proposed approach in relevance detection. We further show that the proposed approach can achieve high compression efficiency by abstracting substantial redundant information while retaining the high quality of the relevant content.}, doi = {10.1145/3394171.3413658}, keywords = {Convolutional Neural Networks, ROI Detection, Video Coding, HEVC, Medical Multimedia}, url = {https://dl.acm.org/doi/10.1145/3394171.3413658} } @InProceedings{Fox2020, author = {Markus Fox and Mario Taschwer and Klaus Schoeffmann}, booktitle = {2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS)}, title = {{Pixel-Based Tool Segmentation in Cataract Surgery Videos with Mask R-CNN}}, year = {2020}, month = {jul}, pages = {565--568}, publisher = {IEEE}, abstract = {Automatically detecting surgical tools in recorded surgery videos is an important building block of further content-based video analysis. In ophthalmology, the results of such methods can support training and teaching of operation techniques and enable investigation of medical research questions on a dataset of recorded surgery videos. While previous methods used frame-based classification techniques to predict the presence of surgical tools — but did not localize them, we apply a recent deep-learning segmentation method (Mask R-CNN) to localize and segment surgical tools used in ophthalmic cataract surgery. We add ground-truth annotations for multi-class instance segmentation to two existing datasets of cataract surgery videos and make resulting datasets publicly available for research purposes. In the absence of comparable results from literature, we tune and evaluate the Mask R-CNN approach on these datasets for instrument segmentation/localization and achieve promising results (61\% mean average precision on 50\% intersection over union for instance segmentation, working even better for bounding box detection or binary segmentation), establishing a reasonable baseline for further research. Moreover, we experiment with common data augmentation techniques and analyze the achieved segmentation performance with respect to each class (instrument), providing evidence for future improvements of this approach.}, doi = {10.1109/cbms49503.2020.00112}, keywords = {cataract surgeries, instrument segmentation, tool annotation, deep neural networks, ophthalmology}, url = {https://ieeexplore.ieee.org/document/9183116} } @InProceedings{Fard2020a, author = {Hamid Mohammadi Fard and Radu Prodan and Felix Wolf}, booktitle = {2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing (UCC)}, title = {{Dynamic Multi-objective Scheduling of Microservices in the Cloud}}, year = {2020}, month = {dec}, pages = {386--393}, publisher = {IEEE}, abstract = {For many applications, a microservices architecture promises better performance and flexibility compared to a conventional monolithic architecture. In spite of the advantages of a microservices architecture, deploying microservices poses various challenges for service developers and providers alike. One of these challenges is the efficient placement of microservices on the cluster nodes. Improper allocation of microservices can quickly waste resource capacities and cause low system throughput. In the last few years, new technologies in orchestration frameworks, such as the possibility of multiple schedulers for pods in Kubernetes, have improved scheduling solutions of microservices but using these technologies needs to involve both the service developer and the service provider in the behavior analysis of workloads. Using memory and CPU requests specified in the service manifest, we propose a general microservices scheduling mechanism that can operate efficiently in private clusters or enterprise clouds. We model the scheduling problem as a complex variant of the knapsack problem and solve it using a multi-objective optimization approach. Our experiments show that the proposed mechanism is highly scalable and simultaneously increases utilization of both memory and CPU, which in turn leads to better throughput when compared to the state-of-the-art.}, doi = {10.1109/ucc48980.2020.00061}, keywords = {scheduling microservices, cloud computing, multi-objective optimization, knapsack problem, resource management}, url = {https://ieeexplore.ieee.org/document/9302823} } @InProceedings{Erfanian2020, author = {Alireza Erfanian and Farzad Tashtarian and Reza Farahani and Christian Timmerer and Hellwagner, Hermann}, booktitle = {2020 6th IEEE Conference on Network Softwarization (NetSoft)}, title = {{On Optimizing Resource Utilization in AVC-based Real-time Video Streaming}}, year = {2020}, month = {jun}, pages = {301--309}, publisher = {IEEE}, abstract = {Real-time video streaming traffic and related applications have witnessed significant growth in recent years. However, this has been accompanied by some challenging issues, predominantly resource utilization. IP multicasting, as a solution to this problem, suffers from many problems. Using scalable video coding could not gain wide adoption in the industry, due to reduced compression efficiency and additional computational complexity. The emerging software-defined networking (SDN)and network function virtualization (NFV) paradigms enable re-searchers to cope with IP multicasting issues in novel ways. In this paper, by leveraging the SDN and NFV concepts, we introduce a cost-aware approach to provide advanced video coding (AVC)-based real-time video streaming services in the network. In this study, we use two types of virtualized network functions (VNFs): virtual reverse proxy (VRP) and virtual transcoder (VTF)functions. At the edge of the network, VRPs are responsible for collecting clients’ requests and sending them to an SDN controller. Then, executing a mixed-integer linear program (MILP) determines an optimal multicast tree from an appropriate set of video source servers to the optimal group of transcoders. The desired video is sent over the multicast tree. The VTFs transcode the received video segments and stream to the requested VRPs over unicast paths. To mitigate the time complexity of the proposed MILPmodel, we propose a heuristic algorithm that determines a near-optimal solution in a reasonable amount of time. Using theMiniNet emulator, we evaluate the proposed approach and show it achieves better performance in terms of cost and resource utilization in comparison with traditional multicast and unicast approaches.}, doi = {10.1109/netsoft48620.2020.9165450}, keywords = {Dynamic Adaptive Streaming over HTTP (DASH), Real-time Video Streaming, Software Defined Networking (SDN), Video Transcoding, Network Function Virtualization (NFV)}, url = {https://ieeexplore.ieee.org/document/9165450} } @InProceedings{Cetinkaya2020, author = {Ekrem Cetinkaya and Hadi Amirpour and Christian Timmerer and Mohammad Ghanbari}, booktitle = {2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)}, title = {{FaME-ML: Fast Multirate Encoding for HTTP Adaptive Streaming Using Machine Learning}}, year = {2020}, month = {dec}, pages = {87--90}, publisher = {{IEEE}}, abstract = {HTTP Adaptive Streaming(HAS) is the most common approach for delivering video content over the Internet. The requirement to encode the same content at different quality levels (i.e., representations) in HAS is a challenging problem for content providers. Fast multirate encoding approaches try to accelerate this process by reusing information from previously encoded representations. In this paper, we propose to use convolutional neural networks (CNNs) to speed up the encoding of multiple representations with a specific focus on parallel encoding. In parallel encoding, the overall time-complexity is limited to the maximum time-complexity of one of the representations that are encoded in parallel. Therefore, instead of reducing the time-complexity for all representations, the highest time-complexities are reduced. Experimental results show that FaME-ML achieves significant time-complexity savings in parallel encoding scenarios(41%in average) with a slight increase in bitrate and quality degradation compared to the HEVC reference software.}, doi = {10.1109/vcip49819.2020.9301850}, keywords = {HEVC, Multirate Encoding, Machine Learning, DASH, HTTP Adaptive Streaming, HAS}, url = {https://ieeexplore.ieee.org/abstract/document/9301850} } @InProceedings{Amirpour_2020, author = {Hadi Amirpour and Ekrem Cetinkaya and Christian Timmerer and Mohammad Ghanbari}, booktitle = {2020 Data Compression Conference (DCC)}, title = {{Fast Multi-rate Encoding for Adaptive HTTP Streaming}}, year = {2020}, month = {mar}, publisher = {IEEE}, abstract = {Adaptive HTTP streaming is the preferred method to deliver multimedia content in the internet. It provides multiple representations of the same content in different qualities (i.e. bit-rates and resolutions) and allows the client to request segments from the available representations in a dynamic, adaptive way depending on its context. The growing number of representations in adaptive HTTP streaming makes encoding of one video segment at different representations a challenging task in terms of encoding time-complexity. In this paper, information of both highest and lowest quality representations are used to limit Rate Distortion Optimization (RDO) for each Coding Unit Tree (CTU) in High Efficiency Video Coding. Our proposed method first encodes the highest quality representation and consequently uses it to encode the lowest quality representation. In particular, the block structure and the selected reference frame of both highest and lowest quality representations are then used to predict and shorten the RDO process of each CTU for intermediate quality representations. Our proposed method introduces a delay of two CTUs thanks to employing parallel processing techniques. Experimental results show significant reduction in time-complexity over the reference software 38% and the state-of-the-art 10% while quality degradation is negligible.}, doi = {10.1109/dcc47342.2020.00080}, keywords = {HTTP adaptive streaming, Multi-rate encoding, HEVC, Fast block partitioning}, url = {https://ieeexplore.ieee.org/document/9105709} } @InProceedings{Amirpour2020, author = {Hadi Amirpour and Christian Timmerer and Mohammad Ghanbari}, booktitle = {2020 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)}, title = {{Towards View-Aware Adaptive Streaming of Holographic Content}}, year = {2020}, month = {jul}, publisher = {IEEE}, abstract = {Holography is able to reconstruct a three-dimensional structure of an object by recording full wave fields of light emitted from the object. This requires a huge amount of data to be encoded, stored, transmitted, and decoded for holographic content, making its practical usage challenging especially for bandwidth-constrained networks and memory-limited devices. In the delivery of holographic content via the internet, bandwidth wastage should be avoided to tackle high bandwidth demands of holography streaming. For real-time applications, encoding time-complexity is also a major problem. In this paper, the concept of dynamic adaptive streaming over HTTP (DASH) is extended to holography image streaming and view-aware adaptation techniques are studied. As each area of a hologram contains information of a specific view, instead of encoding and decoding the entire hologram, just the part required to render the selected view is encoded and transmitted via the network based on the users’ interactivity. Four different strategies, namely, monolithic, single view, adaptive view, and non-real time streaming strategies are explained and compared in terms of bandwidth requirements, encoding time-complexity, and bitrate overhead. Experimental results show that the view-aware methods reduce the required bandwidth for holography streaming at the cost of a bitrate increase.}, doi = {10.1109/icmew46912.2020.9106055}, keywords = {Holography, compression, bitrate adaption, dynamic adaptive streaming over HTTP, DASH}, url = {https://ieeexplore.ieee.org/document/9106055} } @InProceedings{AguilarArmijo2020, author = {Jesus Aguilar-Armijo and Babak Taraghi and Christian Timmerer and Hellwagner, Hermann}, booktitle = {2020 IEEE International Symposium on Multimedia (ISM)}, title = {{Dynamic Segment Repackaging at the Edge for {HTTP} Adaptive Streaming}}, year = {2020}, month = {dec}, pages = {17--24}, publisher = {IEEE}, abstract = {Adaptive video streaming systems typically support different media delivery formats, e.g., MPEG-DASH and HLS, replicating the same content multiple times into the network. Such a diversified system results in inefficient use of storage, caching, and bandwidth resources. The Common Media Application Format (CMAF) emerges to simplify HTTP Adaptive Streaming (HAS), providing a single encoding and packaging format of segmented media content and offering the opportunities of bandwidth savings, more cache hits and less storage needed. However, CMAF is not yet supported by most devices. To solve this issue, we present a solution where we maintain the main advantages of CMAF while supporting heterogeneous devices using different media delivery formats. For that purpose, we propose to dynamically convert the content from CMAF to the desired media delivery format at an edge node. We study the bandwidth savings with our proposed approach using an analytical model and simulation, resulting in bandwidth savings of up to 20% with different media delivery format distributions. We analyze the runtime impact of the required operations on the segmented content performed in two scenarios: the classic one, with four different media delivery formats, and the proposed scenario, using CMAF-only delivery through the network. We compare both scenarios with different edge compute power assumptions. Finally, we perform experiments in a real video streaming testbed delivering MPEG-DASH using CMAF content to serve a DASH and an HLS client, performing the media conversion for the latter one.}, doi = {10.1109/ism.2020.00009}, keywords = {CMAF, Edge Computing, HTTP Adaptive Streaming (HAS)} } @InProceedings{Zabrovskiy2019, author = {Midoglu, Cise and Zabrovskiy, Anatoliy and Alay, Ozgu and Hoelbling-Inzko, Daniel and Griwodz, Carsten and Timmerer, Christian}, booktitle = {Proceedings of the 27th ACM International Conference on Multimedia}, title = {{Docker-Based Evaluation Framework for Video Streaming QoE in Broadband Networks}}, year = {2019}, month = {Oktober}, pages = {2288--2291}, publisher = {ACM New York}, doi = {10.1145/3343031.3350538}, url = {https://dl.acm.org/citation.cfm?doid=3343031.3350538} } @InProceedings{Timmerer2019d, author = {Bentaleb, Abdelhak and Timmerer, Christian and Begen, Ali C. and Zimmermann, Roger}, booktitle = {Proceedings of the 29th ACM Workshop on Network and Operating Systems Support for Digital Audio and Video}, title = {{Bandwidth prediction on low-latency chunked streaming}}, year = {2019}, month = {Juni}, pages = {7--13}, publisher = {ACM New York}, doi = {10.1145/3304112.3325611}, url = {https://dl.acm.org/citation.cfm?doid=3304112.3325611} } @InProceedings{Timmerer2019c, author = {Timmerer, Christian and Begen, Ali C.}, booktitle = {Proceedings of the 27th ACM International Conference on Multimedia}, title = {{A Journey Towards Fully Immersive Media Access}}, year = {2019}, month = {Oktober}, pages = {2703--2705}, publisher = {ACM New York}, doi = {10.1145/3343031.3350543}, url = {https://dl.acm.org/citation.cfm?id=3350543} } @InProceedings{Timmerer2019b, author = {van der Hooft, Jeroen and Wauters, Tim and De Turck, Filip and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the 27th ACM International Conference on Multimedia}, title = {{Towards 6dof http adaptive streaming through point cloud compression}}, year = {2019}, month = {Oktober}, pages = {2405--2413}, publisher = {ACM New York}, doi = {10.1145/3343031.3350917}, url = {https://dl.acm.org/citation.cfm?id=3350917} } @InProceedings{Sokolova2019, author = {Sokolova, Natalia and Schöffmann, Klaus and Taschwer, Mario and Putzgruber-Adamitsch, Doris and El-Shabrawi, Yosuf}, booktitle = {Proceedings of the 26th International Conference in MultiMedia Modeling (MMM 2020) (Part II)}, title = {{Evaluating the Generalization Performance of Instrument Classification in Cataract Surgery Videos}}, year = {2019}, address = {Berlin}, editor = {Wen-Huang Cheng and Junmo Kim and Wei-Ta Chu and Peng Cui and Jung-Woo Choi and Min-Chun Hu and Wesley De Neve}, month = {Dezember}, pages = {626--636}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, volume = {11962}, doi = {10.1007/978-3-030-37734-2_51}, url = {https://www.researchgate.net/publication/338188982_Evaluating_the_Generalization_Performance_of_Instrument_Classification_in_Cataract_Surgery_Videos} } @InProceedings{Schoeffmann2019d, author = {Lokoc, Jakub and Schöffmann, Klaus and Bailer, Werner and Rossetto, Luca and Gurrin, Cathal}, booktitle = {Proceedings of the ACM International Conference on Multimedia Retrieval}, title = {{Interactive Video Retrieval in the Age of Deep Learning}}, year = {2019}, address = {New York, NY}, month = {Juni}, pages = {2--4}, publisher = {ACM - New York}, doi = {10.1145/3323873.3326588}, url = {https://dl.acm.org/doi/10.1145/3323873.3326588} } @InProceedings{Schoeffmann2019c, author = {Berns, Fabian and Rossetto, Luca and Schöffmann, Klaus and Beecks, Christian and Awad, George M.}, booktitle = {Proceedings of the ACM International Conference on Multimedia Retrieval}, title = {{V3C1 Dataset: An Evaluation of Content Characteristics }}, year = {2019}, address = {New York, NY}, month = {Juni}, pages = {334--338}, publisher = {ACM - New York}, doi = {10.1145/3323873.3325051}, url = {https://dl.acm.org/doi/10.1145/3323873.3325051} } @InProceedings{Schoeffmann2019b, author = {Peng, Cheng and Xu, Qing and Guo, Yuejun and Schöffmann, Klaus}, booktitle = {Proceedings of the 28th International Conference on Artificial Neural Networks}, title = {{Eye Movement-Based Analysis on Methodologies and Efficiency in the Process of Image Noise Evaluation}}, year = {2019}, address = {Berlin}, month = {September}, pages = {29--40}, publisher = {Springer}, doi = {10.1007/978-3-030-30508-6_3}, url = {https://www.researchgate.net/publication/335699630_Eye_Movement-Based_Analysis_on_Methodologies_and_Efficiency_in_the_Process_of_Image_Noise_Evaluation} } @InProceedings{Schoeffmann2019a, author = {Halvorsen, Pal and Riegler, Michael and Schöffmann, Klaus}, booktitle = {Proceedings of the 27th ACM International Conference on Multimedia}, title = {{Medical Multimedia Systems and Applications}}, year = {2019}, month = {Oktober}, pages = {2711--2713}, publisher = {ACM New York}, doi = {10.1145/3343031.3351319}, url = {https://dl.acm.org/doi/10.1145/3343031.3351319} } @InProceedings{Schoeffmann2019, author = {Schöffmann, Klaus}, booktitle = {Proceedings of the International Conference on Content-Based Multimedia Indexing (CBMI'19)}, title = {{Video Browser Showdown 2012-2019: A Review}}, year = {2019}, address = {Piscataway (NJ)}, month = {Oktober}, publisher = {IEEE}, doi = {10.1109/CBMI.2019.8877397}, url = {https://ieeexplore.ieee.org/document/8877397} } @InProceedings{Schatz2019, author = {Schatz, Raimund and Zabrovskiy, Anatoliy and Timmerer, Christian}, title = {Tile-based Streaming of 8K Omnidirectional Video: Subjective and Objective QoE Evaluation}, booktitle = {2019 Eleventh International Conference on Qualit of Multimedia Experience (QoMEX)}, year = {2019}, address = {New York, USA}, month = jun, publisher = {IEEE}, abstract = {Omnidirectional video (ODV) streaming applica- tions are becoming increasingly popular. They enable a highly immersive experience as the user can freely choose her/his field of view within the 360-degree environment. Current deployments are fairly simple but viewport-agnostic which inevitably results in high storage/bandwidth requirements and low Quality of Experience (QoE). A promising solution is referred to as tile- based streaming which allows to have higher quality within the user’s viewport while quality outside the user’s viewport could be lower. However, empirical QoE assessment studies in this domain are still rare. Thus, this paper investigates the impact of different tile-based streaming approaches and configurations on the QoE of ODV. We present the results of a lab-based subjective evaluation in which participants evaluated 8K omnidirectional video QoE as influenced by different (i) tile-based streaming approaches (full vs. partial delivery), (ii) content types (static vs. moving camera), and (iii) tile encoding quality levels determined by different quantization parameters. Our experimental setup is character- ized by high reproducibility since relevant media delivery aspects (including the user’s head movements and dynamic tile quality adaptation) are already rendered into the respective processed video sequences. Additionally, we performed a complementary objective evaluation of the different test sequences focusing on bandwidth efficiency and objective quality metrics. The results are presented in this paper and discussed in detail which confirm that tile-based streaming of ODV improves visual quality while reducing bandwidth requirements.}, keywords = {Omnidirectional Video, Tile-based Streaming, Subjective Testing, Objective Metrics, Quality of Experience} } @InProceedings{Saurabh2019, author = {Saurabh, Nishant and Remmers, Julian and Kimovski, Dragi and Prodan, Radu Aurel and Barbosa, jorge G.}, booktitle = {Proceedings of the 33rd IEEE International Parallel and Distributed Processing Symposium (IPDPS) 2019}, title = {{Semantics-Aware Virtual Machine Image Management in IaaS Clouds}}, year = {2019}, address = {Piscataway (NJ)}, month = {September}, pages = {418--427}, publisher = {IEEE}, doi = {10.1109/IPDPS.2019.00052}, url = {https://ieeexplore.ieee.org/document/8820973} } @InProceedings{ProdanIET2019a, author = {Oleksiak, Ariel and Lefevre, Laurent and Alonso, Pedro and Da Costa, Georges and De Maio, Vincenzo and Frasheri, Neki and Garcia, Victor M. and Guerrero, Joel and Lafond, Sebastien and Lastovetsky, Alexey L. and Manumachu, Ravi Reddy and Muite, Benson and Orgerie, Anne-Cecile and Piatek, Wojciech and Pierson, Jean-Marc and Prodan, Radu Aurel and Stolf, Patricia and Sheme, Enida and Varrette, Sebastien}, booktitle = {Ultrascale Computing Systems}, title = {{Energy aware ultrascale systems}}, year = {2019}, address = {Stevenage}, editor = {Jesus Carretero and Emmanuel Jeannot and Albert Y. Zomaya}, month = {Januar}, pages = {127--188}, publisher = {The Institution of Engineering and Technology (IET)}, abstract = {Energy consumption is one of the main limiting factors for the design of ultrascale infrastructures. Multi-level hardware and software optimizations must be designed and explored in order to reduce energy consumption for these largescale equipment. This chapter addresses the issue of energy efficiency of ultrascale systems in front of other quality metrics. The goal of this chapter is to explore the design of metrics, analysis, frameworks and tools for putting energy awareness and energy efficiency at the next stage. Significant emphasis will be placed on the idea of “energy complexity,” reflecting the synergies between energy efficiency and quality of service, resilience and performance, by studying computation power, communication/data sharing power, data access power, algorithm energy consumption, etc.}, doi = {10.1049/PBPC024E}, url = {https://digital-library.theiet.org/content/books/pc/pbpc024e} } @InProceedings{ProdanGLOBECOMWS, author = {Mudgill, Vipul and Aujla, Gagangeet Singh and Kumar, Neeraj and Obaidat, Mohammad S. and Prodan, Radu Aurel}, booktitle = {Proceedings of the 2018 IEEE Globecom Workshops}, title = {{DLopC: Data Locality Independency-Aware VM Clustering in Cloud Computing}}, year = {2019}, address = {Piscataway (NJ)}, month = {Februar}, pages = {1--6}, publisher = {IEEE}, doi = {10.1109/GLOCOMW.2018.8644081}, url = {https://ieeexplore.ieee.org/document/8644081} } @InProceedings{ProdanGLOBECOM, author = {Jindal, Anish and Aujla, Gagangeet Singh and Kumar, Neeraj and Prodan, Radu Aurel and Obaidat, Mohammad S.}, booktitle = {Proceedings of the 2018 IEEE Global Communications Conference (GLOBECOM)}, title = {{DRUMS: Demand Response Management in a Smart City Using Deep Learning and SVR}}, year = {2019}, address = {Piscataway (NJ)}, month = {Februar}, pages = {1--6}, publisher = {IEEE}, doi = {10.1109/GLOCOM.2018.8647926}, url = {https://ieeexplore.ieee.org/document/8647926} } @InProceedings{Prodan2019, author = {Radu Prodan and Ennio Torre and Juan J. Durillo and Gagangeet Singh Aujla and Neeraj Kummar and Hamid Mohammadi Fard and Shajulin Benedikt}, booktitle = {2019 45th Euromicro Conference on Software Engineering and Advanced Applications (SEAA)}, title = {{Dynamic Multi-objective Virtual Machine Placement in Cloud Data Centers}}, year = {2019}, month = {aug}, pages = {92--99}, publisher = {IEEE}, abstract = {Minimizing the resource wastage reduces the energy cost of operating a data center, but may also lead to a considerably high resource overcommitment affecting the Quality of Service (QoS) of the running applications. Determining the effective tradeoff between resource wastage and overcommitment is a challenging task in virtualized Cloud data centers and depends on how Virtual Machines (VMs) are allocated to physical resources. In this paper, we propose a multi-objective framework for dynamic placement of VMs exploiting live-migration mechanisms which simultaneously optimize the resource wastage, overcommitment ratio and migration cost. The optimization algorithm is based on a novel evolutionary meta-heuristic using an island population model underneath. We implemented and validated our method based on an enhanced version of a well-known simulator. The results demonstrate that our approach outperforms other related approaches by reducing up to 57% migrations energy consumption while achieving different energy and QoS goals.}, doi = {10.1109/seaa.2019.00023}, keywords = {Cloud computing, Energy efficiency, Multi objective optimization, Virtual machine placement}, url = {https://ieeexplore.ieee.org/document/8906523} } @InProceedings{Moll2019c, author = {Philipp Moll and Andreas Leibetseder and Sabrina Kletz and Mathias Lux and Bernd Muenzer}, booktitle = {Proceedings of the 10th {ACM} Multimedia Systems Conference}, title = {{Alternative inputs for games and AR/VR applications}}, year = {2019}, month = {jun}, pages = {320--323}, publisher = {ACM}, abstract = {In multimedia research, scientific progress is often slowed downby high demands on hard- and software. However, hardware con-tinuously improves and today’s hardware got powerful enoughto meet the performance demands of complex 3D and deep learn-ing applications. With this demo, we demonstrate that utilizingdeep learning and 3D modeling is not a major barrier anymorewhen building prototypes for showcasing research projects. Ourweb-based game, called “HeadbangZ”, showcases a novel gesture-based input methodology realized through deeply learned poseestimation and user interaction in a 3D environment. Since gesture-based inputs increase the immersion in virtual environments, weassume this input methodology to be especially useful for AR/VRapplications and games. Furthermore, we demonstrate that rapidprototyping of applications using novel technologies, such as deeplearning, is even possible within 48 hours by developing a workingdemo within this time frame. Finally, we provide insights into whatwe learned during the development of HeadbangZ to encourageother researchers to make use of novel technologies. In referenceto Stephen Harper’s quote “Having hit a wall, the next logical stepis not to bang our heads against it.”, we hope that the presentationof HeadbangZ encourages researchers to bang their heads rhythmi-cally to rock music instead of angrily against a virtual wall createdby hard- and software limitations.}, doi = {10.1145/3304109.3323832}, keywords = {Alternative Inputs, Deep Learning, Rhythm Games}, url = {https://dl.acm.org/citation.cfm?id=3323832} } @InProceedings{Moll2019a, author = {Moll, Philipp and Theuermann, Sebastian and Hellwagner, Hermann and Burke, Jeff}, booktitle = {2019 IEEE International Conference on Communications Workshops (ICC Workshops)}, title = {{Distributing the Game State of Online Games: Towards an NDN Version of Minecraft}}, year = {2019}, address = {Piscataway (NJ)}, editor = {Philipp Moll and Sebastian Theuermann and Hellwagner, Hermann and Jeff Burke}, month = {Juli}, publisher = {IEEE}, doi = {10.1109/ICCW.2019.8756979}, url = {https://ieeexplore.ieee.org/document/8756979} } @InProceedings{Moll2019, author = {Moll, Philipp and Theuermann, Sebastian and Rauscher, Natascha Jasmin and Hellwagner, Hermann and Burke, Jeff}, booktitle = {Proceedings of the 6th ACM Conference on Information-Centric Networking (ICN' 19)}, title = {{Inter-Server Game State Synchronization using Named Data Networking}}, year = {2019}, address = {New York, NY}, month = {September}, pages = {12--18}, publisher = {ACM Digital Library}, doi = {10.1145/3357150.3357399}, url = {https://dl.acm.org/citation.cfm?id=3357399} } @InProceedings{Mehran2019, author = {Mehran, Narges and Kimovski, Dragi and Prodan, Radu Aurel}, booktitle = {Proceedings of the 9th International Conference on the Internet of Things (IoT 2019)}, title = {{MAPO: A Multi-Objective Model for IoT Application Placement in a Fog Environment}}, year = {2019}, month = {Oktober}, pages = {1--8}, publisher = {Association for Computing Machinery (ACM)}, doi = {10.1145/3365871.3365892}, url = {https://dl.acm.org/doi/pdf/10.1145/3365871.3365892?download=true} } @InProceedings{Madaan2019, author = {Vishu Madaan and Rupinder Kaur and Prateek Agrawal}, booktitle = {2019 4th International Conference on Information Systems and Computer Networks (ISCON)}, title = {{Rheumatoid Arthritis anticipation using Adaptive Neuro Fuzzy Inference System}}, year = {2019}, month = nov, pages = {340--346}, publisher = {IEEE}, abstract = {A state of discomfort is known as a disease, also termed as illness or sickness. When the tiniest living things like virus enters our body, it reacts with the cells of the body and results an illness. The Arthritis is very problematic to early forecast. It nurtures with the age and related to the large and small joint pain. The Rheumatoid Arthritis (RA) is chronic disease, its long-term auto-immune and inflammatory disease which damages many joints tissues. It occurs when immune system can't distinguish the cells and tissues. The ANFIS model is used for the prediction of the RA in human mortals. A complete process is mentioned in this study, which helps to a technique for the diagnosis of the Rheumatoid Arthritis in human beings with accuracy 93.5%. This diagnosis is made on the bases of 12 symptoms of RA in human lives like age, stiffness, joint deformity, ESR, CRP, WBC, Uric Acid etc. This paper also compares the ANFIS with Naive Bayes, Bagging algorithm and KNN classifiers.}, doi = {10.1109/iscon47742.2019.9036297}, keywords = {Disease Diagnosis, Arthritis Symptoms, Arthritis Prediction, KNN Classifier, ANFIS, Naive Bayes Classification}, url = {https://ieeexplore.ieee.org/document/9036297} } @InProceedings{Lux2019e, author = {Dang-Nguyen, Duc-Tien and Piras, Luca and Riegler, Michael and Zhou, Liting and Lux, Mathias and Tran, Minh-Triet and Le, Tu-Khiem and Ninh, Van-Tu and Gurrin, Cathal}, booktitle = {Proceedings of the Conference and Labs of the Evaluation Forum (CLEF 2019)}, title = {{Overview of ImageCLEFlifelog 2019: Solve My Life Puzzle and Lifelog Moment Retrieval}}, year = {2019}, pages = {09--12}, publisher = {CEUR-Workshop Proceedings}, volume = {2380}, url = {https://www.semanticscholar.org/paper/Overview-of-ImageCLEFlifelog-2019%3A-Solve-My-Life-Dang-Nguyen-Piras/736f4783f29dd1ac0ec5fb0c020567e049cae5b1} } @InProceedings{Lux2019d, author = {Ionescu, Bogdan and Müller, Henning and Péteri, Renaud and Dang-Nguyen, Duc-Tien and Piras, Luca and Riegler, Michael and Tran, Minh-Triet and Lux, Mathias and Gurrin, Cathal and Dicente Cid, Yashin and Liauchuk, Vitali and Kovalev, Vassili and Abacha, Asma Ben and Hasan, Sadid A. and Datla, Vivek and Liu, Joey and Demner-Fushman, Dina and Pelka, Obioma and Friedrich, Christoph M. and Chamberlain, Jon and Clark, Adrian and Seco de Herrera, Alba Garcia and Garcia, Narciso and Kavallieratou, Ergina and del Blanco, Carlos Roberto and Cuevas Rodríguez, Carlos and Vasillopoulos, Nikos and Karampidis, Konstantinos}, booktitle = {Proceedings of the 41st European Conference on Information Retrieval (ECIR 2019)}, title = {{ImageCLEF 2019: Multimedia Retrieval in Lifelogging, Medical, Nature, and Security Applications}}, year = {2019}, address = {Berlin}, editor = {Leif Azzopardi and Benno Stein and Norbert Fuhr and Philipp Mayr and Claudia Hauff and Djoerd Hiemstra}, month = {April}, pages = {301--308}, publisher = {Springer}, doi = {10.1007/978-3-030-15719-7_40}, url = {https://link.springer.com/chapter/10.1007/978-3-030-15719-7_40} } @InProceedings{Lux2019c, author = {Lux, Mathias and Halvorsen, Pal and Dang-Nguyen, Duc-Tien and Stensland, Hakon and Kesavulu, Manoj and Potthast, Martin and Riegler, Michael}, booktitle = {Proceedings of the 11th ACM Workshop on Immersive Mixed and Virtual Environment Systems (MMVE 2019)}, title = {{Summarizing E-sports matches and tournaments: the example of counter-strike: global offensive}}, year = {2019}, address = {New York, NY}, month = {Juni}, pages = {13--18}, publisher = {ACM Digital Library}, doi = {10.1145/3304113.3326116}, url = {https://dl.acm.org/doi/10.1145/3304113.3326116} } @InProceedings{Lux2019b, author = {Ninh, Van-Tu and Le, Tu-Khiem and Zhou, Liting and Piras, Luca and Riegler, Michael and Lux, Mathias and Tran, Minh-Triet and Gurrin, Cathal and Dang-Nguyen, Duc-Tien}, booktitle = {Proceedings of the Conference and Labs of the Evaluation Forum (CLEF 2019)}, title = {{LIFER 2.0: Discovering Personal Lifelog Insights using an Interactive Lifelog Retrieval System}}, year = {2019}, month = {September}, publisher = {CEUR-Workshop Proceedings}, volume = {2380}, url = {https://pdfs.semanticscholar.org/c1d9/d2cbfebc7d275f9a4ca48d6c7953544d1e6b.pdf?_ga=2.244744845.962216161.1578471476-1581210800.1576149693} } @InProceedings{Lux2019a, author = {Hicks, Steven Alexander and Riegler, Michael and Smedsrud, Pia and Haugen, Trine B. and Ranheim Randel, Kristin and Pogorelov, Konstantin and Stensland, Hakon and Dang-Nguyen, Duc-Tien and Lux, Mathias and Petlund, Andreas and de Lange, Thomas and Schmidt, Peter T. and Halvorsen, Pal}, booktitle = {Proceedings of the 27th ACM International Conference on Multimedia}, title = {{ACM Multimedia BioMedia 2019 Grand Challenge Overview}}, year = {2019}, month = {Oktober}, pages = {2563--2567}, publisher = {ACM New York}, doi = {10.1145/3343031.3356058}, url = {https://dl.acm.org/doi/10.1145/3343031.3356058} } @InProceedings{Lux2019, author = {Lux, Mathias and Riegler, Michael and Halvorsen, Pal and Dang-Nguyen, Duc-Tien and Potthast, Martin}, booktitle = {Savegame}, title = {{Challenges for Multimedia Research in E-Sports Using Counter-Strike}}, year = {2019}, address = {Wiesbaden}, editor = {Wilfried Elmenreich and René Reinhold Schallegger and Felix Schniz and Sonja Gabriel and Gerhard Pölsterl and Wolfgang B. Ruge}, month = {November}, pages = {197--206}, publisher = {Springer VS}, abstract = {That video and computer games have reached the masses is a well-known fact. However, game streaming and, therefore, watching other people play videogames has also outgrown its humble beginnings by far. Game streams, be it live or recorded, are viewed by millions. Many of the streams are broadcasting competitive multiplayer games. This is called e-sports and it is very similar to sports broadcasting. E-sports is organized in leagues and tournaments in which players can compete in controlled environments and viewers can experience the matches, discuss and criticize just like in physical sports. In this paper, we look into the challenges for computer science in general and multimedia research in particular. The multimedia research community has done a lot of work on video streaming, broadcasting and analyzing the audience, but has missed the opportunity to investigate e-sports in detail. We focus on one particular game we deem representative for e-sports, Counter-Strike: Global Offensive, and investigate how the audience consumes game streams from competitive tournaments.}, doi = {10.1007/978-3-658-27395-8_13}, url = {https://link.springer.com/chapter/10.1007/978-3-658-27395-8_13} } @InProceedings{Leibetseder2019b, author = {Leibetseder, Andreas and Münzer, Bernd and Primus, Manfred Jürgen and Kletz, Sabrina and Schöffmann, Klaus and Berns, Fabian and Beecks, Christian}, booktitle = {Proceedings of the ACM Workshop on Lifelog Search Challenge (LSC 19)}, title = {{lifeXplore at the Lifelog Search Challenge 2019 }}, year = {2019}, address = {New York, NY}, month = {Juni}, pages = {13--17}, publisher = {ACM - New York}, doi = {10.1145/3326460.3329157}, url = {https://www.researchgate.net/publication/333690590_lifeXplore_at_the_Lifelog_Search_Challenge_2019} } @InProceedings{Leibetseder2019a, author = {Leibetseder, Andreas and Kletz, Sabrina and Schöffmann, Klaus and Keckstein, Simon and Keckstein, Jörg}, booktitle = {Proceedings of the 26th International Conference in MultiMedia Modeling (MMM 2020) (Part II)}, title = {{GLENDA: Gynecologic Laparoscopy Endometriosis Dataset}}, year = {2019}, address = {Berlin}, editor = {Wen-Huang Cheng and Junmo Kim and Wei-Ta Chu and Peng Cui and Jung-Woo Choi and Min-Chun Hu and Wesley De Neve}, month = {Dezember}, pages = {439--450}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, volume = {11962}, doi = {10.1007/978-3-030-37734-2_36}, url = {https://www.researchgate.net/publication/338189084_GLENDA_Gynecologic_Laparoscopy_Endometriosis_Dataset/link/5e1c30554585159aa4cb7378/download} } @InProceedings{Leibetseder2019, author = {Leibetseder, Andreas and Münzer, Bernd and Primus, Manfred Jürgen and Kletz, Sabrina and Schöffmann, Klaus}, booktitle = {Proceedings of the 26th International Conference in MultiMedia Modeling (MMM 2020) (Part II)}, title = {{diveXplore 4.0: The ITEC Deep Interactive Video Exploration System at Video Browser Showdown 2020}}, year = {2019}, address = {Berlin}, editor = {Wen-Huang Cheng and Junmo Kim and Wei-Ta Chu and Peng Cui and Jung-Woo Choi and Min-Chun Hu and Wesley De Neve}, month = {Dezember}, pages = {753--759}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, volume = {11962}, doi = {10.1007/978-3-030-37734-2_65}, url = {https://link.springer.com/chapter/10.1007%2F978-3-030-37734-2_65} } @InProceedings{Kletz_Leibetseder_Moll, author = {Errath, Daniela and Kletz, Sabrina and Leibetseder, Andreas and Moll, Philipp and Zraunig, Julia and Elmenreich, Wilfried}, booktitle = {Das Anthropozän.}, title = {{Digitalisierung und Anthropozän}}, year = {2019}, address = {München, Wien}, editor = {Heike Egner and Horst Peter Groß}, pages = {133--176}, publisher = {Profil Verlag}, abstract = {Das Anthropozän bezeichnet ein neues Erdzeitalter, in dem die Menschheit deutliche Spuren hinterlässt. Diese reichen von Gesteinsschichten mit radioaktiven Ablagerungen aus Atomtests über ausgerottete Tier- und Pflanzenarten bis hin zum allgegenwärtigen Klimawandel. Für manche dieser Spuren ist technologischer Fortschritt ein erheblicher Einflussfaktor. Während Mensch und Technik zusammen Spuren hinterlassen, beeinflusst auch die Technik den Menschen. Insbesondere die Digitalisierung könnte einen besonderen Einfluss auf das neue Erdzeitalter nehmen, in dem digitales Grundverständnis und Computational Thinking notwendige Kompetenzen auf dem Weg in die Zukunft darstellen. Wie diese aussieht, ist aufgrund der hohen Dynamik der gegenwärtigen Systeme ungewiss, insbesondere da durch die digitale Vernetzung eine hohe Produktivität einer großen Volatilität bei der Langzeitarchivierung gegenübersteht. In diesem Buchkapitel spannen wir einen Bogen vom Anthropozän über derzeitige Auswirkungen der menschlichen Intervention hin zur Entwicklung und Wirkung von Kommunikations- und Computertechnik in der heutigen Welt, zusammengefasst als digitale (R)evolution. In einem weiteren Schritt beschäftigen wir uns mit der gegenwärtig vorherrschenden und uns täglich umgebenden “digitalen Welt” und der Notwendigkeit zu digitalem Grundverständnis und Computational Thinking. Den Abschluss des Kapitels bildet ein Ausblick in die Zukunft und erläutert mögliche Zukunftsszenarien im digitalen Bereich.} } @InProceedings{Kletz2019b, author = {Sabrina Kletz and Andreas Leibetseder and Klaus Schoeffmann}, booktitle = {Proceedings of the 10th ACM Multimedia Systems Conference}, title = {{A comparative study of video annotation tools for scene understanding}}, year = {2019}, month = {jun}, pages = {133--144}, publisher = {ACM}, abstract = {Computers are powerful tools capable of solving a great variety of ever so complex problems, yet training them to interpret even the simplest video scenes can prove more challenging than one might imagine. Still being one of the major problems in computer vision, this issue recently is addressed by utilizing promising deep learning approaches in order to recognize objects and their semantics. For achieving this goal, huge artificial networks are fed with many human-created annotations using more or less sophisticated tools for speeding up the otherwise time-consuming task of manual annotation. Purposefully refraining from designing yet another of these annotation tools, in this work we strive for evaluating what makes existing ones great or not, i.e. we aim at determining effectiveness and efficiency of state-of-the-art object annotation tools when employed for annotating different kinds of video content. Our findings in a user study evaluating three comparable tools on three videos of distinct domains indicate a significant difference in annotation effort from a video perspective, yet no significance regarding utilized tools. Further, we determine a significant correlation between annotation time and accuracy.}, doi = {10.1145/3304109.3306223}, keywords = {Video Annotation Tools, User Study, Object Detection, Interpolation, Bounding Boxes, Machine Learning}, url = {https://dl.acm.org/citation.cfm?id=3306223} } @InProceedings{Kletz2019, author = {Kletz, Sabrina and Schöffmann, Klaus and Leibetseder, Andreas and Benois-Pineau, Jenny and Husslein, Heinrich}, booktitle = {Proceedings of the 26th International Conference in MultiMedia Modeling (MMM 2020) (Part II)}, title = {{Instrument Recognition in Laparoscopy for Technical Skill Assessment}}, year = {2019}, address = {Berlin}, editor = {Wen-Huang Cheng and Junmo Kim and Wei-Ta Chu and Peng Cui and Jung-Woo Choi and Min-Chun Hu and Wesley De Neve}, month = {Dezember}, pages = {589--600}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, volume = {11962}, doi = {10.1007/978-3-030-37734-2_48}, url = {https://link.springer.com/chapter/10.1007%2F978-3-030-37734-2_48} } @InProceedings{Hammer2019, author = {Hammer, Josef and Moll, Philipp and Hellwagner, Hermann}, booktitle = {2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)}, title = {{Transparent Access to 5G Edge Computing Services}}, year = {2019}, address = {Piscataway (NJ)}, month = {Juli}, pages = {895--898}, publisher = {IEEE}, doi = {10.1109/IPDPSW.2019.00147}, url = {https://ieeexplore.ieee.org/document/8778343} } @InProceedings{BarcisM2019, author = {Barcis, Agata and Barcis, Michal and Bettstetter, Christian}, booktitle = {International Symposium on Multi-Robot and Multi-Agent Systems (MRS)}, title = {{Robots that Sync and Swarm: A Proof of Concept in ROS 2}}, year = {2019}, address = {Piscataway (NJ)}, month = {November}, publisher = {IEEE}, doi = {10.1109/MRS.2019.8901095}, url = {https://ieeexplore.ieee.org/document/8901095} } @InProceedings{Barcis2019, author = {Barcis, Michal and Hellwagner, Hermann}, booktitle = {IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)}, title = {{An Evaluation Model for Information Distribution in Multi-Robot Systems}}, year = {2019}, month = {September}, pages = {824--829}, doi = {10.1109/INFCOMW.2019.8845299}, url = {https://ieeexplore.ieee.org/document/8845299} } @InProceedings{Agrawal2019b, author = {Kaur, Rupinder and Madaan, Vishu and Agrawal, Prateek}, booktitle = {Proceedings of the 3rd International Conference On Advanced Informatics For Computing Research}, title = {{Diagnosis of Arthritis Using K-Nearest Neighbor Approach}}, year = {2019}, editor = {Ashish Kumar Luhach and Dharm Singh Jat and Kamarul Bin Ghazali Hawari and Xiao-Zhi Gao and Pawan Lingras}, month = {September}, pages = {160--171}, publisher = {Springer Singapore}, series = {Communications in Computer and Information Science}, doi = {10.1007/978-981-15-0108-1_16}, url = {https://link.springer.com/chapter/10.1007/978-981-15-0108-1_16} } @InProceedings{Agrawal2019a, author = {Chaudhary, Deepak and Agrawal, Prateek and Madaan, Vishu}, booktitle = {Proceedings of the 3rd International Conference On Advanced Informatics For Computing Research}, title = {{Bank Cheque Validation Using Image Processing}}, year = {2019}, editor = {Ashish Kumar Luhach and Dharm Singh Jat and Kamarul Bin Ghazali Hawari and Xiao-Zhi Gao and Pawan Lingras}, month = {September}, pages = {148--159}, publisher = {Springer Singapore}, series = {Communications in Computer and Information Science}, doi = {10.1007/978-981-15-0108-1_15}, url = {https://link.springer.com/chapter/10.1007/978-981-15-0108-1_15} } @InProceedings{Agrawal2019, author = {Bhadwal, Neha and Agrawal, Prateek and Madaan, Vishu}, booktitle = {Proceedings of the 3rd International Conference On Advanced Informatics For Computing Research}, title = {{Bilingual Machine Translation System Between Hindi and Sanskrit Languages}}, year = {2019}, editor = {Ashish Kumar Luhach and Dharm Singh Jat and Kamarul Bin Ghazali Hawari and Xiao-Zhi Gao and Pawan Lingras}, month = {September}, pages = {312--321}, publisher = {Springer Singapore}, series = {Communications in Computer and Information Science}, doi = {10.1007/978-981-15-0108-1_29}, url = {https://link.springer.com/chapter/10.1007%2F978-981-15-0108-1_29} } @InProceedings{Zhou2018, author = {Zhou, Liting and Piras, Luca and Riegler, Michael and Lux, Mathias and Dang-Nguyen, Duc-Tien and Gurrin, Cathal}, title = {{An Interactive Lifelog Retrieval System for Activities of Daily Living Understanding}}, booktitle = {CLEF 2018 Working Notes}, year = {2018}, month = {September}, publisher = {CEUR-Workshop Proceedings}, abstract = {This paper describes the participation of the Organizer Teamin the ImageCLEFlifelog 2018 Daily Living Understanding and Lifelog MomentRetrieval. In this paper, we propose how to exploit LIFER, aninteractive lifelog search engine to solve the two tasks: Lifelog MomentRetrieval and Activities of Daily Living Understanding. We propose approachesfor both baseline, which aim to provide a reference system forother approaches, and human-in-the-loop, which advance the baselineresults.}, url = {http://ceur-ws.org/Vol-2125/} } @InProceedings{Zabrovskiy2018a, title = {{A Practical Evaluation of Video Codecs for Large-Scale HTTP Adaptive Streaming Services}}, author = {Zabrovskiy, Anatoliy and Feldmann, Christian and Timmerer, Christian}, booktitle = {2018 25th IEEE International Conference on Image Processing (ICIP)}, year = {2018}, address = {Piscataway (NJ)}, month = {Oktober}, pages = {998--1002}, publisher = {IEEE}, abstract = {The number of bandwidth-hungry applications and services is constantly growing. HTTP adaptive streaming of audiovisual content accounts for the majority of today's internet traffic. Although the internet bandwidth increases also constantly, audio-visual compression technology is inevitable and we are currently facing the challenge to be confronted with multiple video codecs. This paper provides a practical evaluation of state of the art video codecs (i. e., AV1, AVC/libx264, HEVC/libx265, VP9/Iibvpx-vp9) for large-scale HTTP adaptive streaming services. In anticipation of the results, AV I shows promising performance compared to established video codecs. Additionally, AV I is intended to be royalty free making it worthwhile to be considered for large scale HTTP adaptive streaming services.}, doi = {10.1109/ICIP.2018.8451017}, url = {https://ieeexplore.ieee.org/document/8451017} } @InProceedings{Zabrovskiy2018, title = {Multi-codec DASH dataset}, author = {Zabrovskiy, Anatoliy and Feldmann, Christian and Timmerer, Christian}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {438--443}, publisher = {ACM Press}, abstract = {The number of bandwidth-hungry applications and services is constantly growing. HTTP adaptive streaming of audio-visual content accounts for the majority of today's internet traffic. Although the internet bandwidth increases also constantly, audio-visual compression technology is inevitable and we are currently facing the challenge to be confronted with multiple video codecs.This paper proposes a multi-codec DASH dataset comprising AVC, HEVC, VP9, and AV1 in order to enable interoperability testing and streaming experiments for the efficient usage of these codecs under various conditions. We adopt state of the art encoding and packaging options and also provide basic quality metrics along with the DASH segments. Additionally, we briefly introduce a multi-codec DASH scheme and possible usage scenarios. Finally, we provide a preliminary evaluation of the encoding efficiency in the context of HTTP adaptive streaming services and applications.}, doi = {10.1145/3204949.3208140}, url = {https://dl.acm.org/citation.cfm?id=3208140} } @InProceedings{Trattnig2018, title = {Investigation of YouTube regarding Content Provisioning for HTTP Adaptive Streaming}, author = {Trattnig, Armin and Timmerer, Christian and Müller, Christopher}, booktitle = {PV '18 Proceedings of the 23rd Packet Video Workshop}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {60--65}, publisher = {ACM Press}, abstract = {About 300 hours of video are uploaded to YouTube every minute. The main technology to delivery YouTube content to various clients is HTTP adaptive streaming and the majority of today's internet traffic comprises streaming audio and video. In this paper, we investigate content provisioning for HTTP adaptive streaming under predefined aspects representing content features and upload characteristics as well and apply it to YouTube. Additionally, we compare the YouTube's content upload and processing functions with a commercially available video encoding service. The results reveal insights into YouTube's content upload and processing functions and the methodology can be applied to similar services. All experiments conducted within the paper allow for reproducibility thanks to the usage of open source tools, publicly available datasets, and scripts used to conduct the experiments on virtual machines.}, doi = {10.1145/3210424.3210431}, url = {https://dl.acm.org/citation.cfm?id=3210424.3210431} } @InProceedings{TimmererHVEI2018, title = {{A Framework for Adaptive Delivery of Omnidirectional Video}}, author = {Timmerer, Christian and Begen, Ali Cengiz}, booktitle = {IS\&T International Symposium on Electronic Imaging 2018, Human Vision and Electronic Imaging 2018 Conference}, year = {2018}, month = jan, issn = {2470-1173}, journal = {Electronic Imaging}, url = {https://doi.org/10.2352/ISSN.2470-1173.2018.14.HVEI-524} } @InProceedings{Timmerer2018c, author = {Timmerer, Christian and Zabrovskiy, Anatoliy and Begen, Ali C.}, title = {{Automated Objective and Subjective Evaluation of HTTP Adaptive Streaming Systems}}, booktitle = {2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)}, year = {2018}, address = {Piscataway (NJ)}, month = {April}, publisher = {IEEE}, abstract = {Streaming audio and video content currently accounts for the majority of the internet traffic and is typically deployed over the top of the existing infrastructure. We are facing the challenge of a plethora of media players and adaptation algorithms showing different behavior but lack a common framework for both objective and subjective evaluation of such systems. This paper aims to close this gap by (i) proposing such a framework, (ii) describing its architecture, (iii) providing an example evaluation, (iv) and discussing open issues.}, doi = {10.1109/MIPR.2018.00080}, url = {https://ieeexplore.ieee.org/document/8397036/} } @InProceedings{Timmerer2018_NAB, title = {Efficient Multi-Codec Support for OTT Services: HEVC/H.265 and/or AV1?}, author = {Timmerer, Christian and Smole, Martin and Mueller, Christopher}, booktitle = {2018 NAB BEIT Proceedings}, year = {2018}, address = {Washington DC, USA}, editor = {available, not}, month = apr, pages = {5}, publisher = {National Association of Broadcasters (NAB)} } @InProceedings{Timmerer2018_MIPR, title = {Automated Objective and Subjective Evaluation of HTTP Adaptive Streaming Systems}, author = {Timmerer, Christian and Zabrovskiy, Anatoliy and Begen, Ali Cengiz}, booktitle = {Proceedings of the 1st IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR)}, year = {2018}, editor = {available, not}, month = apr, pages = {6}, abstract = {Streaming audio and video content currently accounts for the majority of the internet traffic and is typically deployed over the top of the existing infrastructure. We are facing the challenge of a plethora of media players and adaptation algorithms showing different behavior but lack a common framework for both objective and subjective evaluation of such systems. This paper aims to close this gap by (i) proposing such a framework, (ii) describing its architecture, (iii) providing an example evaluation, (iv) and discussing open issues.}, doi = {10.1109/MIPR.2018.00080}, url = {https://ieeexplore.ieee.org/document/8397036/} } @InProceedings{Timmerer2018, author = {Timmerer, Christian}, title = {{MPEG column: 123rd MPEG meeting in Ljubljana, Slovenia}}, booktitle = {ACM SIGMultimedia Records}, year = {2018}, volume = {10}, address = {New York (NY)}, month = {September}, publisher = {ACM Press}, abstract = {The original blog post can be found at the Bitmovin Techblog and has been modified/updated here to focus on and highlight research aspects.}, doi = {10.1145/3300001.3300012}, url = {https://dl.acm.org/citation.cfm?id=3300012} } @InProceedings{Taschwer2018a, author = {Taschwer, Mario and Primus, Manfred J{\"u}rgen and Schoeffmann, Klaus and Marques, Oge}, booktitle = {Working Notes Proceedings of the MediaEval 2018 Workshop}, title = {Early and Late Fusion of Classifiers for the {MediaEval Medico} Task}, year = {2018}, editor = {M. Larson and P. Arora and C.H. Demarty and M. Riegler and B. Bischke and E. Dellandrea and M. Lux and A. Porter and G.J.F. Jones}, series = {CEUR Workshop Proceedings}, volume = {2283}, url = {http://ceur-ws.org/Vol-2283/MediaEval_18_paper_23.pdf} } @InProceedings{Schoeffmann2018d, author = {Schöffmann, Klaus and Münzer, Bernd and Primus, Manfred Jürgen and Kletz, Sabrina and Leibetseder, Andreas}, title = {{How Experts Search Different Than Novices – An Evaluation of the diveXplore Video Retrieval System at Video Browser Showdown 2018}}, booktitle = {2018 IEEE International Conference on Multimedia \& Expo Workshops (ICMEW)}, year = {2018}, address = {Piscataway (NJ)}, month = {Juli}, publisher = {IEEE}, abstract = {We present a modern interactive video retrieval tool, called diveXplore, that has been used for several iterations of the Video Browser Showdown (VBS) competition with great success – 2nd place for the last two years in a row. The tool provides novel video content search and interaction features (e.g., a semantic map-search & browsing feature with similarity arrangement and a highly efficient sketch-search, optimized for mobile touch-interaction) that make it perfectly suited for flexible video retrieval in large video collections. With the help of a user study we show that the diveXplore system can be used very efficiently by both type of users: novices and experts. Our evaluation results do also show that the interaction statistics of novices and experts differ in terms of used features. The details of our insights can be used to further optimize interfaces of video retrieval tools for non-experts.}, doi = {10.1109/ICMEW.2018.8551552}, url = {https://ieeexplore.ieee.org/document/8551552} } @InProceedings{Schoeffmann2018c, author = {Schöffmann, Klaus and Bailer, Werner and Gurrin, Cathal and Awad, George M. and Lokoč, Jakub}, title = {{Interactive Video Search: Where is the User in the Age of Deep Learning?}}, booktitle = {MM '18 Proceedings of the 26th ACM international conference on Multimedia}, year = {2018}, pages = {2101--2103}, address = {New York (NY)}, month = {Oktober}, publisher = {ACM Press}, abstract = {In this tutorial we discuss interactive video search tools and methods, review their need in the age of deep learning, and explore video and multimedia search challenges and their role as evaluation benchmarks in the field of multimedia information retrieval. We cover three different campaigns (TRECVID, Video Browser Showdown, and the Lifelog Search Challenge), discuss their goals and rules, and present their achieved findings over the last half-decade. Moreover, we talk about datasets, tasks, evaluation procedures, and examples of interactive video search tools, as well as how they evolved over the years. Participants of this tutorial will be able to gain collective insights from all three challenges and use them for focusing their research efforts on outstanding problems that still remain unsolved in this area.}, doi = {10.1145/3240508.3241473}, url = {https://dl.acm.org/citation.cfm?id=3241473} } @InProceedings{Schoeffmann2018, title = {Cataract-101: video dataset of 101 cataract surgeries}, author = {Klaus Schöffmann and Mario Taschwer and Stephanie Sarny and Bernd Münzer and Manfred Jürgen Primus and Doris Putzgruber-Adamitsch}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Mai}, pages = {421--425}, publisher = {ACM Press}, abstract = {Cataract surgery is one of the most frequently performed microscopic surgeries in the field of ophthalmology. The goal behind this kind of surgery is to replace the human eye lense with an artificial one, an intervention that is often required due to aging. The entire surgery is performed under microscopy, but co-mounted cameras allow to record and archive the procedure. Currently, the recorded videos are used in a postoperative manner for documentation and training. An additional benefit of recording cataract videos is that they enable video analytics (i.e., manual and/or automatic video content analysis) to investigate medically relevant research questions (e.g., the cause of complications). This, however, necessitates a medical multimedia information system trained and evaluated on existing data, which is currently not publicly available. In this work we provide a public video dataset of 101 cataract surgeries that were performed by four different surgeons over a period of 9 months. These surgeons are grouped into moderately experienced and highly experienced surgeons (assistant vs. senior physicians), providing the basis for experience-based video analytics. All videos have been annotated with quasi-standardized operation phases by a senior ophthalmic surgeon.}, doi = {http://dx.doi.org/10.1145/3204949.3208137}, url = {https://dl.acm.org/citation.cfm?id=3208137} } @InProceedings{Riegler2018, author = {Riegler, Michael and Halvorsen, Pal and Münzer, Bernd and Schöffmann, Klaus}, title = {{The Importance of Medical Multimedia}}, booktitle = {MM '18 Proceedings of the 26th ACM international conference on Multimedia}, year = {2018}, pages = {2016--2108}, address = {New York (NY)}, month = {Oktober}, publisher = {ACM Press}, abstract = {Multimedia research is becoming more and more important for the medical domain, where an increasing number of videos and images are integrated in the daily routine of surgical and diagnostic work. While the collection of medical multimedia data is not an issue, appropriate tools for efficient use of this data are missing. This includes management and inspection of the data, visual analytics, as well as learning relevant semantics and using recognition results for optimizing surgical and diagnostic processes. The characteristics and requirements in this interesting but challenging field are different than the ones in classic multimedia domains. Therefore, this tutorial gives a general introduction to the field, provides a broad overview of specific requirements and challenges, discusses existing work and open challenges, and elaborates in detail how machine learning approaches can help in multimedia-related fields to improve the performance of surgeons/clinicians.}, doi = {10.1145/3240508.3241475}, url = {https://dl.acm.org/citation.cfm?id=3241475} } @InProceedings{Rainer2018, author = {Rainer, Benjamin and Petscharnig, Stefan and Timmerer, Christian}, title = {{Merge and Forward: A Self-Organized Inter-Destination Media Synchronization Scheme for Adaptive Media Streaming over HTTP}}, booktitle = {MediaSync}, year = {2018}, pages = {593--627}, address = {Berlin}, month = {März}, publisher = {Springer}, abstract = {In this chapter, we present Merge and Forward, an IDMS scheme for adaptive HTTP streaming as a distributed control scheme and adopting the MPEG-DASH standard as representation format. We introduce so-called IDMS sessions and describe how an unstructured peer-to-peer overlay can be created using the session information using MPEG-DASH. We objectively assess the performance of Merge and Forward with respect to convergence time (time needed until all clients hold the same reference time stamp) and scalability. After the negotiation on a reference time stamp, the clients have to synchronize their multimedia playback to the agreed reference time stamp. In order to achieve this, we propose a new adaptive media playout approach minimizing the impact of playback synchronization on the QoE. The proposed adaptive media playout is assessed subjectively using crowd sourcing. We further propose a crowd sourcing methodology for conducting subjective quality assessments in the field of IDMS by utilizing GWAP. We validate the applicability of our methodology by investigating the lower asynchronism threshold for IDMS in scenarios like online quiz games.}, doi = {10.1007/978-3-319-65840-7_21}, url = {https://link.springer.com/chapter/10.1007/978-3-319-65840-7_21} } @InProceedings{Primus2018a, title = {The ITEC Collaborative Video Search System at the Video Browser Showdown 2018}, author = {Manfred Jürgen Primus and Bernd Münzer and Andreas Leibetseder and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 2)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Supavadee Aramvith and Noel E. O´Connor and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {438--443}, publisher = {Springer}, series = {LNCS}, volume = {10705}, abstract = {We present our video search system for the Video Browser Showdown (VBS) 2018 competition. It is based on the collaborative system used in 2017, which already performed well but also revealed high potential for improvement. Hence, based on our experience we introduce several major improvements, particularly (1) a strong optimization of similarity search, (2) various improvements for concept-based search, (3) a new flexible video inspector view, and (4) extended collaboration features, as well as numerous minor adjustments and enhancements, mainly concerning the user interface and means of user interaction. Moreover, we present a spectator view that visualizes the current activity of the team members to the audience to make the competition more attractive.}, doi = {10.1007/978-3-319-73600-6_47}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73600-6_47} } @InProceedings{Primus2018, title = {Frame-Based Classification of Operation Phases in Cataract Surgery Videos}, author = {Manfred Jürgen Primus and Doris Putzgruber-Adamitsch and Mario Taschwer and Bernd Münzer and Yosuf El-Shabrawi and Laszlo Böszörmenyi and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 1)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Noel E. O´Connor and Supavadee Aramvith and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {241--253}, publisher = {Springer}, series = {LNCS}, volume = {10704}, abstract = {Cataract surgeries are frequently performed to correct a lens opacification of the human eye, which usually appears in the course of aging. These surgeries are conducted with the help of a microscope and are typically recorded on video for later inspection and educational purposes. However, post-hoc visual analysis of video recordings is cumbersome and time-consuming for surgeons if there is no navigation support, such as bookmarks to specific operation phases. To prepare the way for an automatic detection of operation phases in cataract surgery videos, we investigate the effectiveness of a deep convolutional neural network (CNN) to automatically assign video frames to operation phases, which can be regarded as a single-label multi-class classification problem. In absence of public datasets of cataract surgery videos, we provide a dataset of 21 videos of standardized cataract surgeries and use it to train and evaluate our CNN classifier. Experimental results display a mean F1-score of about 68% for frame-based operation phase classification, which can be further improved to 75% when considering temporal information of video frames in the CNN architecture.}, doi = {10.1007/978-3-319-73603-7_20}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73603-7_20} } @InProceedings{Postoaca2018, title = {{h-Fair: Asymptotic Scheduling of Heavy Workloads in Heterogeneous Data Centers}}, author = {Postoaca, Andrei and Pop, Florin and Prodan, Radu}, booktitle = {2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)}, year = {2018}, address = {Piscataway (NJ)}, month = {Mai}, publisher = {IEEE}, abstract = {Large scale computing solutions are increasingly used in the context of Big Data platforms, where efficient scheduling algorithms play an important role in providing optimized cluster resource utilization, throughput and fairness. This paper deals with the problem of scheduling a set of jobs across a cluster of machines handling the specific use case of fair scheduling for jobs and machines with heterogeneous characteristics. Although job and cluster diversity is unprecedented, most schedulers do not provide implementations that handle multiple resource type fairness in a heterogeneous system. We propose in this paper a new scheduler called h-Fair that selects jobs for scheduling based on a global dominant resource fairness heterogeneous policy, and dispatches them on machines with similar characteristics to the resource demands using the cosine similarity. We implemented h-Fair in Apache Hadoop YARN and we compare it with the existing Fair Scheduler that uses the dominant resource fairness policy based on the Google workload trace. We show that our implementation provides better cluster resource utilization and allocates more containers when jobs and machines have heterogeneous characteristics.}, doi = {10.1109/CCGRID.2018.00058}, url = {https://ieeexplore.ieee.org/document/8411047/authors#authors} } @InProceedings{Pogorelov2018a, author = {Pogorelov, Konstantin and Riegler, Michael and Halvorsen, Pal and Hicks, Steven Alexander and Ranheim Randel, Kristin and Dang-Nguyen, Duc-Tien and Lux, Mathias and Ostroukhova, Olga and de Lange, Thomas}, title = {{Medico Multimedia Task at MediaEval 2018}}, booktitle = {Working Notes Proceedings of the MediaEval 2018 Workshop}, year = {2018}, address = {Aachen}, month = {Oktober}, publisher = {CEUR Workshop Proceedings (CEUR-WS.org)}, abstract = {The Medico: Multimedia for Medicine Task, running for the secondtime as part of MediaEval 2018, focuses on detecting abnormalities,diseases, anatomical landmarks and other findings in imagescaptured by medical devices in the gastrointestinal tract. The taskis described, including the use case and its challenges, the datasetwith ground truth, the required participant runs and the evaluationmetrics.}, url = {http://ceur-ws.org/Vol-2283/} } @InProceedings{Pogorelov2018, title = {Opensea: open search based classification tool}, author = {Konstantin Pogorelov and Zeno Albisser and Olga Ostroukhova and Mathias Lux and Dag Johansen and Pal Halvorsen and Michael Riegler}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {363--368}, publisher = {ACM Press}, abstract = {This paper presents an open-source classification tool for image and video frame classification. The classification takes a search-based approach and relies on global and local image features. It has been shown to work with images as well as videos, and is able to perform the classification of video frames in real-time so that the output can be used while the video is recorded, playing, or streamed. OpenSea has been proven to perform comparable to state-of-the-art methods such as deep learning, at the same time performing much faster in terms of processing speed, and can be therefore seen as an easy to get and hard to beat baseline. We present a detailed description of the software, its installation and use. As a use case, we demonstrate the classification of polyps in colonoscopy videos based on a publicly available dataset. We conduct leave-one-out-cross-validation to show the potential of the software in terms of classification time and accuracy.}, doi = {10.1145/3204949.3208128}, url = {https://dl.acm.org/citation.cfm?id=3208128} } @InProceedings{PetscharnigMMM18Demo, author = {Petscharnig, Stefan and Schöffmann, Klaus}, booktitle = {International Conference on Multimedia Modeling}, title = {ActionVis: An Explorative Tool to Visualize Surgical Actions in Gynecologic Laparoscopy}, year = {2018}, address = {Cham, Switzerland}, editor = {not available, yet}, month = {feb}, pages = {1-5}, publisher = {Springer}, abstract = {Appropriate visualization of endoscopic surgery recordings has a huge potential to benefit surgical work life. For example, it enables surgeons to quickly browse medical interventions for purposes of documentation, medical research, discussion with colleagues, and training of young surgeons. Current literature on automatic action recognition for endoscopic surgery covers domains where surgeries follow a standardized pattern, such as cholecystectomy. However, there is a lack of support in domains where such standardization is not possible, such as gynecologic laparoscopy. We provide ActionVis, an interactive tool enabling surgeons to quickly browse endoscopic recordings. Our tool analyses the results of a post-processing of the recorded surgery. Information on individual frames are aggregated temporally into a set of scenes representing frequent surgical actions in gynecologic laparoscopy, which help surgeons to navigate within endoscopic recordings in this domain.}, doi = {10.1007/978-3-319-73600-6_30}, language = {EN}, location = {Bangkok, Thailand}, talkdate = {2018.02.05}, talktype = {poster}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73600-6_30} } @InProceedings{Muenzer2018a, author = {Münzer, Bernd and Leibetseder, Andreas and Kletz, Sabrina and Primus, Manfred Jürgen and Schöffmann, Klaus}, title = {{lifeXplore at the Lifelog Search Challenge 2018}}, booktitle = {LSC '18 Proceedings of the 2018 ACM Workshop on The Lifelog Search Challenge}, year = {2018}, address = {New York, NY}, month = {Juni}, publisher = {ACM Digital Library}, abstract = {With the growing hype for wearable devices recording biometric data comes the readiness to capture and combine even more personal information as a form of digital diary - lifelogging today is practiced ever more and can be categorized anywhere between an informative hobby and a life-changing experience. From an information processing point of view, analyzing the entirety of such multi-source data is immensely challenging, which is why the first Lifelog Search Challenge 2018 competition is brought into being, as to encourage the development of efficient interactive data retrieval systems. Answering this call, we present a retrieval system based on our video search system diveXplore, which has successfully been used in the Video Browser Showdown 2017 and 2018. Due to the different task definition and available data corpus, the base system was adapted and extended to this new challenge. The resulting lifeXplore system is a flexible retrieval and exploration tool that offers various easy-to-use, yet still powerful search and browsing features that have been optimized for lifelog data and for usage by novice users. Besides efficient presentation and summarization of lifelog data, it includes searchable feature maps, concept and metadata filters, similarity search and sketch search.}, doi = {10.1145/3210539.3210541}, url = {https://dl.acm.org/citation.cfm?id=3210541} } @InProceedings{Muenzer2018, title = {Video Browsing on a Circular Timeline}, author = {Bernd Münzer and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 2)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Supavadee Aramvith and Noel E. O´Connor and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {395--399}, publisher = {Springer}, series = {LNCS}, volume = {10705}, abstract = {The emerging ubiquity of videos in all aspects of society demands for innovative and efficient browsing and navigation mechanisms. We propose a novel visualization and interaction paradigm that replaces the traditional linear timeline with a circular timeline. The main advantages of this new concept are (1) significantly increased and dynamic navigation granularity, (2) minimized spacial distances between arbitrary points on the timeline, as well as (3) the possibility to efficiently utilize the screen space for bookmarks or other supplemental information associated with points of interest. The demonstrated prototype implementation proves the expedience of this new concept and includes additional navigation and visualization mechanisms, which altogether create a powerful video browser.}, doi = {10.1007/978-3-319-73600-6_40}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73600-6_40} } @InProceedings{Moll2018d, author = {Moll, Philipp and Lux, Mathias and Theuermann, Sebastian and Hellwagner, Hermann}, title = {{A Network Traffic and Player Movement Model to Improve Networking for Competitive Online Games}}, booktitle = {Proceedings of the 16th Annual Workshop on Network and Systems Support for Games (NetGames 2018)}, year = {2018}, pages = {1--6}, month = {Juni}, abstract = {}, doi = {}, url = {https://dl.acm.org/citation.cfm?id=3307315}, pdf = {https://www.itec.aau.at/bib/files/a1-moll.pdf} } @InProceedings{Moll2018c, author = {Moll, Philipp and Lux, Mathias and Theuermann, Sebastian and Hellwagner, Hermann}, title = {{A Network Traffic and Player Movement Model to Improve Networking for Competitive Online Games}}, booktitle = {Proceedings of the OAGM Workshop 2018}, year = {2018}, pages = {89--89}, month = {Mai}, abstract = {The popularity of computer games and e-sports is enormously high and still growing every year. Despite the popularity computer games often rely on old technologies, especially in the field of networking. Research in networking for games is challenging due to the low availability of up-todate datasets and network traces. In order to achieve a high user satisfaction while keeping the network activity as low as possible, modern networking solutions of computer games take players’ activities as well as closeness of players in the game world into account. In this paper, we analyze the Battle Royale game mode of the online multiplayer game Fortnite, where 100 players challenge each other in a king-of-the-hill like game within a constantly contracting game world, as an example for a popular online game with demanding technical requirements. We extrapolate player movement patterns by finding player positions automatically from videos, uploaded by Fortnite players on popular streaming platforms and show, how they influence network traffic from the client to the server and vice versa. This extended abstract features the highlights of [1], which has been accepted at the NetGames 2018 event.}, doi = {10.3217/978-3-85125-603-1-17}, url = {http://diglib.tugraz.at/proceedings-of-the-oagm-workshop-2018-2018} } @InProceedings{Moll2018b, author = {Moll, Philipp and Theuermann, Sebastian and Hellwagner, Hermann}, title = {{Wireless Network Emulation for Research on Information-Centric Networking}}, booktitle = {WiNTECH '18 Proceedings of the 12th International Workshop on Wireless Network Testbeds, Experimental Evaluation \& Characterization}, year = {2018}, pages = {46--55}, address = {New York (NY)}, month = {Oktober}, publisher = {ACM Press}, abstract = {When developing new approaches in networking research, one of the most important requirements is to evaluate the degree of improvement of a new approach both realistically and cost-effectively. Wireless networks and their adequate emulation play an important role in evaluation, but emulation of wireless links and networks is still difficult to handle. In this paper, we present a low-cost, fixed-network testbed able to emulate the dynamically changing conditions of wireless links caused by client mobility and physical phenomena. We extend the existing fixed-network testbed for the purpose of wireless network emulation using the Linux tools tc, iptables, and NetEm in sophisticated ways. Convenient function blocks are provided to configure wireless network topologies as well as dynamic link and mobility conditions to be emulated with modest efforts. We utilize the testbed's capabilities to investigate the influence of different mobility models on streaming SVC-encoded videos in Named Data Networking (NDN), a novel Information-Centric Networking architecture. Furthermore, we evaluate the benefits of using early loss detection mechanisms for streaming in NDN, by implementing Wireless Loss Detection and Recovery (WLDR). Our results show that the extended fixed-network testbed can precisely emulate wireless network conditions and usage. For instance, the emulation revealed that both the choice of the mobility model and the use of WLDR have a substantial influence on the resulting SVC video streaming performance.}, doi = {10.1145/3267204.3267211}, url = {https://dl.acm.org/citation.cfm?id=3267211}, pdf = {https://www.itec.aau.at/bib/files/p46-moll.pdf} } @InProceedings{Moll2018a, title = {{Persistent Interests in Named Data Networking}}, author = {Moll, Philipp and Theuermann, Sebastian and Hellwagner, Hermann}, booktitle = {2018 IEEE 87th Vehicular Technology Conference (VTC Spring)}, year = {2018}, address = {Piscataway (NJ)}, month = {Juni}, publisher = {IEEE}, abstract = {Recent research in the field of Information-Centric Networking (ICN) shows the need for push-based data transfer, which is not supported in current pull-based ICN architectures, such as Named Data Networking (NDN). IoT deployments as well as emergency notifications and real-time multimedia communication are well suited to be realized using the ICN principles, but experience challenges in pull-based environments. Persistent Interests (PIs) are a promising approach to introduce pushlike traffic in Interest-based ICN architectures such as NDN. In this paper, we explore the characteristics of PIs and discuss advantages and disadvantages of using them. We provide an efficient solution for preventing so-called Data loops, which are introduced by giving up NDN’s one-request-per-packet principle. Furthermore, we investigate the performance of PIs compared to classical Interests in terms of the computational complexity of forwarding and discuss possible applications of PIs.}, doi = {10.1109/VTCSpring.2018.8417861}, url = {https://ieeexplore.ieee.org/document/8417861/}, pdf = {https://www.itec.aau.at/bib/files/08417861.pdf} } @InProceedings{Lux2018b, author = {Lux, Mathias and Brown, John N. A.}, title = {{Playing Captain Kirk: Designing a Video Game Based on Star Trek}}, booktitle = {Set Phasers to Teach!}, year = {2018}, pages = {125--135}, address = {Berlin}, month = {Juli}, publisher = {Springer}, doi = {10.1007/978-3-319-73776-8}, url = {https://www.springer.com/gp/book/9783319737751} } @Inproceedingsn{Lux2018a, author = {Lux, Mathias and Riegler, Michael and Dang-Nguyen, Duc-Tien and Larson, Marcus and Potthast, Martin and Halvorsen, Pal}, title = {{GameStory Task at MediaEval 2018}}, month = {Oktober}, year = {2018}, abstract = {That video games have reached the masses is well known. Moreover,game streaming and watching other people play video games is aphenomenon that has outgrown its small beginnings. Game videostreams, be it live or recorded, are viewed by millions. E-sports is theresult of organized leagues and tournaments in which players cancompete in controlled environments and viewers can experiencethe matches, discuss and criticize, just like in physical sports. In theGameStory task, taking place the first time in 2018, we approachthe game streaming and e-sports phenomena from a multimediaresearch side. We focus on the task of summarizing matches usinga specific relevant game, Counter-Strike: Global Offensive, as a casestudy. With the help of ZNIPE.tv, we provide a data set of highquality data and meta data from competitive tournaments and aimto foster research in the area of e-sports and game streaming.}, address = {Aachen}, booktitle = {Working Notes Proceedings of the MediaEval 2018 Workshop}, publisher = {CEUR Workshop Proceedings (CEUR-WS.org)}, url = {http://ceur-ws.org/Vol-2283/} } @InProceedings{Lokoc2018a, author = {Lokoč, Jakub and Bailer, Werner and Schöffmann, Klaus}, title = {{What is the Role of Similarity for Known-Item Search at Video Browser Showdown? }}, booktitle = {SISAP 2018: Similarity Search and Applications}, year = {2018}, pages = {96--104}, address = {Berlin}, month = {Oktober}, publisher = {Springer}, abstract = {Across many domains, machine learning approaches start to compete with human experts in tasks originally considered as very difficult for automation. However, effective retrieval of general video shots still represents an issue due to their variability, complexity and insufficiency of training sets. In addition, users can face problems trying to formulate their search intents in a given query interface. Hence, many systems still rely also on interactive human-machine cooperation to boost effectiveness of the retrieval process. In this paper, we present our experience with known-item search tasks in the Video Browser Showdown competition, where participating interactive video retrieval systems mostly rely on various similarity models. We discuss the observed difficulty of known-item search tasks, categorize employed interaction components (relying on similarity models) and inspect successful interactive known-item searches from the recent iteration of the competition. Finally, open similarity search challenges for known-item search in video are presented.}, doi = {10.1007/978-3-030-02224-2_8}, url = {https://link.springer.com/chapter/10.1007%2F978-3-030-02224-2_8} } @InProceedings{Leibetseder2018c, author = {Leibetseder, Andreas and Schöffmann, Klaus}, title = {{Extracting and Using Medical Expert Knowledge to Advance in Video Processing for Gynecologic Endoscopy}}, booktitle = {ICMR '18 Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval}, year = {2018}, address = {New York, NY}, month = {Juni}, publisher = {ACM Digital Library}, abstract = {Modern day endoscopic technology enables medical staff to conveniently document surgeries via recording raw treatment footage, which can be utilized for planning further proceedings, future case revisitations or even educational purposes. However, the prospect of manually perusing recorded media files constitutes a tedious additional workload on physicians' already packed timetables and therefore ultimately represents a burden rather than a benefit. The aim of this PhD project is to improve upon this situation by closely collaborating with medical experts in order to devise datasets and systems to facilitate semi-automatic post-surgical media processing.}, doi = {10.1145/3206025.3206082}, url = {https://dl.acm.org/citation.cfm?doid=3206025.3206082} } @InProceedings{Leibetseder2018b, title = {Lapgyn4: a dataset for 4 automatic content analysis problems in the domain of laparoscopic gynecology}, author = {Andreas Leibetseder and Stefan Petscharnig and Manfred Jürgen Primus and Sabrina Kletz and Bernd Münzer and Klaus Schöffmann and Jörg Keckstein}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {357--362}, publisher = {ACM Press}, abstract = {Modern imaging technology enables medical practitioners to perform minimally invasive surgery (MIS), i.e. a variety of medical interventions inflicting minimal trauma upon patients, hence, greatly improving their recoveries. Not only patients but also surgeons can benefit from this technology, as recorded media can be utilized for speeding-up tedious and time-consuming tasks such as treatment planning or case documentation. In order to improve the predominantly manually conducted process of analyzing said media, with this work we publish four datasets extracted from gynecologic, laparoscopic interventions with the intend on encouraging research in the field of post-surgical automatic media analysis. These datasets are designed with the following use cases in mind: medical image retrieval based on a query image, detection of instrument counts, surgical actions and anatomical structures, as well as distinguishing on which anatomical structure a certain action is performed. Furthermore, we provide suggestions for evaluation metrics and first baseline experiments.}, doi = {10.1145/3204949.3208127}, url = {https://dl.acm.org/citation.cfm?id=3208127} } @InProceedings{Leibetseder2018a, title = {Sketch-Based Similarity Search for Collaborative Feature Maps}, author = {Andreas Leibetseder and Sabrina Kletz and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 2)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Supavadee Aramvith and Noel E. O´Connor and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {425--430}, publisher = {Springer}, series = {LNCS}, volume = {10705}, abstract = {Past editions of the annual Video Browser Showdown (VBS) event have brought forward many tools targeting a diverse amount of techniques for interactive video search, among which sketch-based search showed promising results. Aiming at exploring this direction further, we present a custom approach for tackling the problem of finding similarities in the TRECVID IACC.3 dataset via hand-drawn pictures using color compositions together with contour matching. The proposed methodology is integrated into the established Collaborative Feature Maps (CFM) system, which has first been utilized in the VBS 2017 challenge.}, doi = {10.1007/978-3-319-73600-6_45}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73600-6_45} } @InProceedings{Leibetseder2018, title = {Automatic Smoke Classification in Endoscopic Video}, author = {Andreas Leibetseder and Manfred Jürgen Primus and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 2)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Supavadee Aramvith and Noel E. O´Connor and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {362--366}, publisher = {Springer}, series = {LNCS}, volume = {10705}, abstract = {Medical smoke evacuation systems enable proper, filtered removal of toxic fumes during surgery, while stabilizing internal pressure during endoscopic interventions. Typically activated manually, they, however, are prone to inefficient utilization: tardy activation enables smoke to interfere with ongoing surgeries and late deactivation wastes precious resources. In order to address such issues, in this work we demonstrate a vision-based tool indicating endoscopic smoke – a first step towards automatic activation of said systems and avoiding human misconduct. In the back-end we employ a pre-trained convolutional neural network (CNN) model for distinguishing images containing smoke from others.}, doi = {10.1007/978-3-319-73600-6_33}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73600-6_33} } @InProceedings{Kletz2018, title = {Evaluation of Visual Content Descriptors for Supporting Ad-Hoc Video Search Tasks at the Video Browser Showdown}, author = {Sabrina Kletz and Andreas Leibetseder and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 1)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Noel E. O´Connor and Supavadee Aramvith and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {203--215}, publisher = {Springer}, series = {LNCS}, volume = {10704}, abstract = {Since 2017 the Video Browser Showdown (VBS) collaborates with TRECVID and interactively evaluates Ad-Hoc Video Search (AVS) tasks, in addition to Known-Item Search (KIS) tasks. In this video search competition the participants have to find relevant target scenes to a given textual query within a specific time limit, in a large dataset consisting of 600 h of video content. Since usually the number of relevant scenes for such an AVS query is rather high, the teams at the VBS 2017 could find only a small portion of them. One way to support them at the interactive search would be to automatically retrieve other similar instances of an already found target scene. However, it is unclear which content descriptors should be used for such an automatic video content search, using a query-by-example approach. Therefore, in this paper we investigate several different visual content descriptors (CNN Features, CEDD, COMO, HOG, Feature Signatures and HOF) for the purpose of similarity search in the TRECVID IACC.3 dataset, used for the VBS. Our evaluation shows that there is no single descriptor that works best for every AVS query, however, when considering the total performance over all 30 AVS tasks of TRECVID 2016, CNN features provide the best performance.}, doi = {10.1007/978-3-319-73603-7_17}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73603-7_17} } @InProceedings{Kimovski2018, author = {Kimovski, Dragi and Ijaz, Humaira and Saurabh, Nishant and Prodan, Radu}, title = {An Adaptive Nature-inspired Fog Architecture}, booktitle = {2018 IEEE 2nd International Conference on Fog and Edge Computing (ICFEC 2018)}, year = {2018}, address = {Piscataway (NJ)}, month = {Mai}, publisher = {IEEE}, abstract = {During the last decade, Cloud computing has efficiently exploited the economyof scale by providing low cost computational and storage resources over theInternet, eventually leading to consolidation of computing resources into largedata centers. However, the nascent of the highly decentralized Internet ofThings (IoT) technologies that cannot effectively utilize the centralized Cloudinfrastructures pushes computing towards resource dispersion. Fog computingextends the Cloud paradigm by enabling dispersion of the computational andstorage resources at the edge of the network in a close proximity to where thedata is generated. In its essence, Fog computing facilitates the operation ofthe limited compute, storage and networking resources physically located closeto the edge devices. However, the shared complexity of the Fog and theinfluence of the recent IoT trends moving towards deploying and interconnectingextremely large sets of pervasive devices and sensors, requires exploration ofadaptive Fog architectural approaches capable of adapting and scaling inresponse to the unpredictable load patterns of the distributed IoTapplications. In this paper we introduce a promising new nature-inspired Fogarchitecture, named SmartFog, capable of providing low decision making latencyand adaptive resource management. By utilizing novel algorithms and techniquesfrom the fields of multi-criteria decision making, graph theory and machinelearning we model the Fog as a distributed intelligent processing system,therefore emulating the function of the human brain.}, doi = {10.1109/CFEC.2018.8358723}, url = {https://ieeexplore.ieee.org/document/8358723/} } @InProceedings{Ionescu2018, author = {Ionescu, Bogdan and Müller, Henning and Villegas, Mauricio and de Herrera, Aöna Garcoa Secp and Eickhoff, Carsten and Andrearczyk, Vincent and Dicente Cid, Yashin and Liauchuk, Vitali and Kovalev, Vassili and Hasan, Sadid H. and Ling, Yuan and Farri, Oladimeji and Liu, Joey and Lungren, Matthew and Dang-Nguyen, Duc-Tien and Piras, Luca and Riegler, Michael and Zhou, Liting and Lux, Mathias and Gurrin, Cathal}, title = {{Overview of ImageCLEF 2018: Challenges, Datasets and Evaluation}}, booktitle = {Experimental IR Meets Multilinguality, Multimodality, and Interaction}, year = {2018}, volume = {11018}, series = {LNCS}, address = {Berlin}, month = {August}, publisher = {Springer}, abstract = {This paper presents an overview of the ImageCLEF 2018 evaluation campaign, an event that was organized as part of the CLEF (Conference and Labs of the Evaluation Forum) Labs 2018. ImageCLEF is an ongoing initiative (it started in 2003) that promotes the evaluation of technologies for annotation, indexing and retrieval with the aim of providing information access to collections of images in various usage scenarios and domains. In 2018, the 16th edition of ImageCLEF ran three main tasks and a pilot task: (1) a caption prediction task that aims at predicting the caption of a figure from the biomedical literature based only on the figure image; (2) a tuberculosis task that aims at detecting the tuberculosis type, severity and drug resistance from CT (Computed Tomography) volumes of the lung; (3) a LifeLog task (videos, images and other sources) about daily activities understanding and moment retrieval, and (4) a pilot task on visual question answering where systems are tasked with answering medical questions. The strong participation, with over 100 research groups registering and 31 submitting results for the tasks, shows an increasing interest in this benchmarking campaign.}, doi = {10.1007/978-3-319-98932-7_28}, url = {https://link.springer.com/chapter/10.1007/978-3-319-98932-7_28} } @InProceedings{Hossfeld2018, author = {Hossfeld, Tobias and Timmerer, Christian}, title = {{Quality of experience column: an introduction}}, booktitle = {ACM SIGMultimedia Records}, year = {2018}, volume = {10}, address = {New York (NY)}, month = {September}, publisher = {ACM Press}, abstract = {Research on Quality of Experience (QoE) has advanced significantly in recent years and attracts attention from various stakeholders. Different facets have been addressed by the research community like subjective user studies to identify QoE influence factors for particular applications like video streaming, QoE models to capture the effects of those influence factors on concrete applications, QoE monitoring approaches at the end user site but also within the network to assess QoE during service consumption and to provide means for QoE management for improved QoE. However, in order to progress in the area of QoE, new research directions have to be taken. The application of QoE in practice needs to consider the entire QoE eco-system and the stakeholders along the service delivery chain to the end user.}, doi = {10.1145/3300001.3300011}, url = {https://dl.acm.org/citation.cfm?id=3300011} } @InProceedings{Hosseini2018, title = {Dynamic Adaptive Point Cloud Streaming}, author = {Hosseini, Mohammad and Timmerer, Christian}, booktitle = {PV '18 Proceedings of the 23rd Packet Video Workshop}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {25--30}, publisher = {ACM Press}, abstract = {High-quality point clouds have recently gained interest as an emerging form of representing immersive 3D graphics. Unfortunately, these 3D media are bulky and severely bandwidth intensive, which makes it difficult for streaming to resource-limited and mobile devices. This has called researchers to propose efficient and adaptive approaches for streaming of high-quality point clouds.In this paper, we run a pilot study towards dynamic adaptive point cloud streaming, and extend the concept of dynamic adaptive streaming over HTTP (DASH) towards DASH-PC, a dynamic adaptive bandwidth-efficient and view-aware point cloud streaming system. DASH-PC can tackle the huge bandwidth demands of dense point cloud streaming while at the same time can semantically link to human visual acuity to maintain high visual quality when needed. In order to describe the various quality representations, we propose multiple thinning approaches to spatially sub-sample point clouds in the 3D space, and design a DASH Media Presentation Description manifest speci.c for point cloud streaming. Our initial evaluations show that we can achieve signi.cant bandwidth and performance improvement on dense point cloud streaming with minor negative quality impacts compared to the baseline scenario when no adaptations is applied.}, doi = {10.1145/3210424.3210429}, url = {https://dl.acm.org/citation.cfm?id=3210429} } @InProceedings{Hicks2018a, title = {Comprehensible reasoning and automated reporting of medical examinations based on deep learning analysis}, author = {Steven Alexander Hicks and Konstantin Pogorelov and Thomas de Lange and Mathias Lux and Mattis Jeppsson and Kristin Ranheim Randel and Sigrun L. Eskeland and Pal Halvorsen and Michael Riegler}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {490--493}, publisher = {ACM Press}, abstract = {In the future, medical doctors will to an increasing degree be assisted by deep learning neural networks for disease detection during examinations of patients. In order to make qualified decisions, the black box of deep learning must be opened to increase the understanding of the reasoning behind the decision of the machine learning system. Furthermore, preparing reports after the examinations is a significant part of a doctors work-day, but if we already have a system dissecting the neural network for understanding, the same tool can be used for automatic report generation. In this demo, we describe a system that analyses medical videos from the gastrointestinal tract. Our system dissects the Tensorflow-based neural network to provide insights into the analysis and uses the resulting classification and rationale behind the classification to automatically generate an examination report for the patient's medical journal.}, doi = {10.1145/3204949.3208113}, url = {https://dl.acm.org/citation.cfm?id=3208113} } @InProceedings{Hicks2018, title = {Mimir: an automatic reporting and reasoning system for deep learning based analysis in the medical domain}, author = {Steven Alexander Hicks and Sigrun L. Eskeland and Mathias Lux and Thomas de Lange and Kristin Ranheim Randel and Mattis Jeppsson and Konstantin Pogorelov and Pal Halvorsen and Michael Riegler}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {369--374}, publisher = {ACM Press}, abstract = {Automatic detection of diseases is a growing field of interest, and machine learning in form of deep learning neural networks are frequently explored as a potential tool for the medical video analysis. To both improve the "black box"-understanding and assist in the administrative duties of writing an examination report, we release an automated multimedia reporting software dissecting the neural network to learn the intermediate analysis steps, i.e., we are adding a new level of understanding and explainability by looking into the deep learning algorithms decision processes. The presented open-source software can be used for easy retrieval and reuse of data for automatic report generation, comparisons, teaching and research. As an example, we use live colonoscopy as a use case which is the gold standard examination of the large bowel, commonly performed for clinical and screening purposes. The added information has potentially a large value, and reuse of the data for the automatic reporting may potentially save the doctors large amounts of time.}, doi = {10.1145/3204949.3208129}, url = {https://dl.acm.org/citation.cfm?id=3208129} } @InProceedings{Dang-Nguyen2018a, author = {Dang-Nguyen, Duc-Tien and Schöffmann, Klaus and Hürst, Wolfgang}, title = {{LSE2018 Panel - Challenges of Lifelog Search and Access}}, booktitle = {LSC '18 Proceedings of the 2018 ACM Workshop on The Lifelog Search Challenge}, year = {2018}, address = {New York, NY}, month = {Juni}, publisher = {ACM Digital Library}, abstract = {Lifelogging is becoming an increasingly important topic of research and this paper highlights the thoughts of the three panelists at the LSC - Lifelog Search Challenge at ICMR 2018 in Yokohama, Japan on June 11, 2018. The thoughts cover important topics such as the need for challenges in multimedia access, the need for a better user interface and the challenges in building datasets and organising benchmarking activities such as the LSC.}, doi = {10.1145/3210539.3210540}, url = {https://dl.acm.org/citation.cfm?id=3210540} } @InProceedings{Dang-Nguyen2018, author = {Dang-Nguyen, Duc-Tien and Piras, Luca and Riegler, Michael and Zhou, Liting and Lux, Mathias and Gurrin, Cathal}, title = {{Overview of ImageCLEFlifelog 2018: Daily Living Understanding andL ifelog Moment Retrieval}}, booktitle = {CLEF 2018 Working Notes}, year = {2018}, volume = {2125}, month = {September}, publisher = {CEUR-Workshop Proceedings}, abstract = {Benchmarking in Multimedia and Retrieval related researchelds has a long tradition and important position within the community.Benchmarks such as the MediaEval Multimedia Benchmark or CLEFare well established and also served by the community. One major goalof these competitions beside of comparing dierent methods and approachesis also to create or promote new interesting research directionswithin multimedia. For example the Medico task at MediaEval with thegoal of medical related multimedia analysis. Although lifelogging createsa lot of attention in the community which is shown by several workshopsand special session hosted about the topic. Despite of that there exist alsosome lifelogging related benchmarks. For example the previous editionof the lifelogging task at ImageCLEF. The last years ImageCLEFlifelogtask was well received but had some barriers that made it dicult forsome researchers to participate (data size, multi modal features, etc.) TheImageCLEFlifelog 2018 tries to overcome these problems and make thetask accessible for an even broader audience (e.g., pre-extracted featuresare provided). Furthermore, the task is divided into two subtasks (challenges).The two challenges are lifelog moment retrieval (LMRT) and theActivities of Daily Living understanding (ADLT). All in all seven teamsparticipated with a total number of 41 runs which was an signicantincrease compared to the previous year.}, url = {http://ceur-ws.org/Vol-2125/} } @InProceedings{mluxmartina2017, author = {Pogorelov, Konstantin and Riegler, Michael and Halvorsen, Pal and Griwodz, Carsten and de Lange, Thomas and Randel, Kristin and Eskeland, Sigrun and Dang-Ngyuen, Duc-Tien and Ostroukhova, Olga and Lux, Mathias and Spampinato, Concetto}, booktitle = {Working Notes Proceedings of the MediaEval 2017 Workshop}, title = {A Comparison of Deep Learning with Global Features for Gastrointestinal Disease Detection}, year = {2017}, address = {Dublin, Ireland}, editor = {Gravier, Guillaume and Bischke, Benjamin and Demarty, Claire-Hélène and Zaharieva, Maia and Riegler, Michael and Dellandrea, Emmanuel and Bogdanov, Dmitry and Sutcliffe, Richard and Jones, Gareth and Larson, Martha}, month = {sep}, pages = {3}, publisher = {CEUR Workshop Proceedings}, abstract = {This paper presents our approach for the 2017 Multimedia for Medicine Medico Task of the MediaEval 2017 Benchmark. We propose a system based on global features and deep neural networks, and preliminary results comparing the approaches are presented.}, language = {EN}, location = {Dublin, Ireland}, talkdate = {2017.09.14}, talktype = {registered}, url = {http://ceur-ws.org/Vol-1984/} } @InProceedings{mlux2017, author = {Riegler, Michael and Pogorelov, Konstantin and Halvorsen, Pal and Randel, Kristin and Eskeland, Sigrun and Dang-Nguyen, Duc-Tien and Lux, Mathias and Griwodz, Carsten and Spampinato, Concetto and de Lange, Thomas}, booktitle = {Working Notes Proceedings of the MediaEval 2017 Workshop}, title = {Multimedia for Medicine: The Medico Task at MediaEval 2017}, year = {2017}, address = {Dublin, Ireland}, editor = {Gravier, Guillaume and Bischke, Benjamin and Demarty, Claire-Hélène and Zaharieva, Maia and Riegler, Michael and Dellandrea, Emmanuel and Bogdanov, Dmitry and Sutcliffe, Richard and Jones, Gareth and Larson, Martha}, month = {jan}, pages = {3}, publisher = {CEUR Workshop Proceedings}, abstract = {The Multimedia for Medicine Medico Task, running for the first time as part of MediaEval 2017, focuses on detecting abnormalities, diseases and anatomical landmarks in images captured by medical devices in the gastrointestinal tract. The task characteristics are described, including the use case and its challenges, the dataset with ground truth, the required participant runs and the evaluation metrics.}, language = {EN}, location = {Dublin, Ireland}, talkdate = {2017.09.14}, talktype = {registered} } @InProceedings{martinadez2017, author = {Beck, Harald and Bierbaumer, Bruno and Dao-Tran, Minh and Eiter, Thomas and Hellwagner, Hermann and Schekotihin, Konstantin}, booktitle = {Communications (ICC), 2017 IEEE International Conference on}, title = {Stream Reasoning-Based Control of Caching Strategies in CCN Routers}, year = {2017}, address = {Paris, France}, editor = {Beylat, Jean Luc and Sari, Hikmet}, month = {may}, pages = {6}, publisher = {IEEE}, abstract = {Routers in Content-Centric Networking (CCN) may locally cache frequently requested content in order to speed up delivery to end users. Thus, the issue of caching strategies arises, i.e., which content shall be stored and when it should be replaced. In this work, we employ, and study the feasibility of, novel techniques towards intelligent control of CCN routers that autonomously switch between existing caching strategies in response to changing content request patterns. In particular, we present a router architecture for CCN networks that is controlled by rule-based stream reasoning, following the recent formal framework LARS which extends Answer Set Programming for streams. The obtained possibility for flexible router configuration at runtime allows for versatile network control schemes and may help advance the further development of CCN. Moreover, the empirical evaluation of our feasibility study shows that the resulting caching agent may give significant performance gains.}, doi = {10.1109/ICC.2017.7996762}, isbn10 = {978-1-4673-8999-0}, issn = {1938-1883}, keywords = {Cognition, Internet, Switches, Next generation networking, Programming, Computer architecture, Robots}, language = {EN}, location = {Paris}, talkdate = {2017.05.23}, talktype = {registered} } @InProceedings{martina2017, author = {Lux, Mathias and Riegler, Michael and Macstravic, Glenn}, booktitle = {ICMR '17 Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval}, title = {LireSolr: A Visual Information Retrieval Server}, year = {2017}, address = {New Yor New York, USA}, editor = {Sebe, Nicu and Ionescu, Bogdan}, month = {jun}, pages = {3}, publisher = {ACM}, abstract = {In this paper, we present LireSolr, an open source image retrieval server, build on top of the LIRE library and the Apache Solr search server. With LireSolr, visual information retrieval can be run on a server, which allows better distribution of workloads and simplifies applications in several areas including mobile and web. Furthermore, we showcase several example scenarios how LireSolr can be used to point out the broad range of possibilities and applications. The system is easy to install and setup, and the large number of retrieval tools either provided by LIRE or by other Apache Solr is made easily available on the search server. Moreover, our tool demonstrates how predictions from CNNs can easily be used to extend the visual information retrieval functionality.}, doi = {10.1145/3078971.3079014}, isbn10 = {978-1-4503-4701-3}, language = {EN}, location = {Bukarest, Rumänien}, talkdate = {2017.06.08}, talktype = {poster}, url = {https://dl.acm.org/citation.cfm?id=3079014} } @InProceedings{Zabrovskiy2017, author = {Zabrovskiy, Anatoliy and Kuzmin, Evgeny and Petrov, Evgeny and Timmerer, Christian and Mueller, Christopher}, booktitle = {Proceedings of the 8th ACM on Multimedia Systems Conference (MMSys'17)}, title = {AdViSE: Adaptive Video Streaming Evaluation Framework for the Automated Testing of Media Players}, year = {2017}, address = {New York, NY, USA}, editor = {Chen, Kuan-Ta}, month = {jun}, pages = {4}, publisher = {ACM}, abstract = {Today we can observe a plethora of adaptive video stream- ing services and media players which support interoperable formats like DASH and HLS. Most of the players and their rate adaptation algorithms work as a black box. We have de- veloped a system for easy and rapid testing of media players under various network scenarios. In this paper, we introduce AdViSE, the Adaptive Video Streaming Evaluation frame- work for the automated testing of adaptive media players. The presented framework is used for the comparison and testing of media players in the context of adaptive video streaming over HTTP in web/HTML5 environments. The demonstration showcases a series of experiments with different media players under given context conditions (e.g., network shaping, delivery format). We will also demonstrate the real-time capabilities of the framework and offline anal- ysis including several QoE metrics with respect to a newly introduced bandwidth index.}, doi = {10.1145/3083187.3083221}, isbn10 = {978-1-4503-5002-0}, language = {EN}, location = {Taipei, Taiwan}, pdf = {https://www.itec.aau.at/bib/files/Demo_Paper_Camera_Ready.pdf}, talkdate = {2017.06.21}, talktype = {poster} } @InProceedings{Timmerer2017b, author = {Timmerer, Christian and Zabrovskiy, Anatoliy and Kuzmin, Evgeny and Petrov, Evgeny}, booktitle = {2017 21st Conference of Open Innovations Association (FRUCT)}, title = {Quality of experience of commercially deployed adaptive media players}, year = {2017}, address = {N.N.}, editor = {Balandin, Sergey}, month = {nov}, pages = {330-335}, publisher = {N.N.}, abstract = {In the past decade we observed the transition from push-based, fully managed media streaming to pull-based, unmanaged adaptive HTTP streaming thanks to enhancements in media compression, network capacity, and client capabilities. Adaptive media players, specifically their algorithms, have been subject to research for a long time and lead to various approaches documented in the literature. In the past years we witnessed more and more commercial deployments taking into account findings presented in scientific papers but a quantitative evaluation and assessments of its performance is missing. In this paper, we propose means for the automated performance evaluation of commercially deployed adaptive media players with respect to i) objective, well-known metrics, such as bitrate, stalls, startup delay and ii) derived/calculated metrics (instability, inefficiency, average bitrate) previously proposed in the literature. Additionally, we propose a new metric (Bandwidth index) to measure the effectiveness of bandwidth utilization and together with existing QoE models for adaptive HTTP streaming (focusing on stalls, startup delay) we demonstrate its usefulness in this domain.}, doi = {10.23919/FRUCT.2017.8250200}, issn = {ISSN 2305-7254}, language = {EN}, location = {Helsinki, Finland}, pdf = {https://www.itec.aau.at/bib/files/08250200.pdf}, talkdate = {2017.11.10}, talktype = {registered} } @InProceedings{Timmerer2017_nab, author = {Timmerer, Christian and Graf, Mario and Mueller, Christopher}, booktitle = {2018 NAB Broadcast Engineering and IT Conference (BEITC)}, title = {Adaptive Streaming of VR/360-degree Immersive Media Services with high QoE}, year = {2017}, address = {Washington DC, USA}, editor = {available, not}, month = {apr}, pages = {5}, publisher = {National Association of Broadcasters (NAB)}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/TimmererC012317.pdf}, talktype = {none} } @InProceedings{SchoeffmannTutorialACMMM2017, author = {Schoeffmann,Klaus and Münzer,Bernd and Riegler,Michael and Halvorsen,Paal}, booktitle = {MM ’17 Proceedings of the 2017 ACM on Multimedia Conference}, title = {Medical Multimedia Information Systems (MMIS)}, year = {2017}, address = {New York, NY, USA}, editor = {Liu, Qiong and Lienhart, Rainer and Wang, Haohong}, month = {oct}, pages = {1957-1958}, publisher = {ACM}, abstract = {In hospitals all around the world, medical multimedia information systems have gained high importance over the last few years. One of the reasons is that an increasing number of interventions are performed in a minimally invasive way. These endoscopic inspections and surgeries are performed with a tiny camera -- the endoscope -- which produces a video signal that is used to control the intervention. Apart from the viewing purpose, the video signal is also used for automatic content analysis during the intervention as well as for post-surgical usage, such as communicating operation techniques, planning future interventions, and medical forensics. Another reason is video documentation, which is even enforced by law in some countries. The problem, however, is the sheer amount of unstructured medical videos that are added to the multimedia archive on a daily basis. Without proper management and a multimedia information system, the medical videos cannot be used efficiently for post-surgical scenarios. It is therefore already foreseeable that medical multimedia information systems will gain even more attraction in the next few years. In this tutorial we will introduce the audience to this challenging new field, describe the domain-specific characteristics and challenges of medical multimedia data, introduce related use cases, and talk about existing works -- contributed by the medical imaging and robotics community, but also already partly from the multimedia community -- as well as the many open issues and challenges that bear high research potential.}, doi = {10.1145/3123266.3130142}, isbn10 = {978-1-4503-4906-2}, keywords = {endoscopic video, medical image processing, medical multimedia}, language = {EN}, location = {Mountain View, CA}, talkdate = {2017.10.27}, talktype = {registered}, url = {https://dl.acm.org/citation.cfm?id=3130142} } @InProceedings{Schoeffmann2017MMM, author = {Schoeffmann, Klaus and Primus, Manfred Jürgen and Muenzer, Bernd and Petscharnig, Stefan and Karisch, Christoph and Xu, Qing and Huerst, Wolfgang}, booktitle = {MultiMedia Modeling: 23rd International Conference, MMM 2017, Reykjavik, Iceland, January 4-6, 2017, Proceedings, Part II}, title = {Collaborative Feature Maps for Interactive Video Search}, year = {2017}, address = {Cham}, editor = {Amsaleg, Laurent and Guðmundsson, Gylfi Þór and Gurrin, Cathal and Jónsson, Björn Þór and Satoh, Shin’ichi}, month = {jan}, pages = {457-462}, publisher = {Springer International Publishing}, abstract = {This extended demo paper summarizes our interface used for the Video Browser Showdown (VBS) 2017 competition, where visual and textual known-item search (KIS) tasks, as well as ad-hoc video search (AVS) tasks in a 600-h video archive need to be solved interactively. To this end, we propose a very flexible distributed video search system that combines many ideas of related work in a novel and collaborative way, such that several users can work together and explore the video archive in a complementary manner. The main interface is a perspective Feature Map, which shows keyframes of shots arranged according to a selected content similarity feature (e.g., color, motion, semantic concepts, etc.). This Feature Map is accompanied by additional views, which allow users to search and filter according to a particular content feature. For collaboration of several users we provide a cooperative heatmap that shows a synchronized view of inspection actions of all users. Moreover, we use collaborative re-ranking of shots (in specific views) based on retrieved results of other users.}, doi = {10.1007/978-3-319-51814-5_41}, language = {EN}, location = {Reykjavik, Iceland}, talkdate = {2017.01.04}, talktype = {registered}, url = {https://link.springer.com/chapter/10.1007/978-3-319-51814-5_41#copyrightInformation} } @InProceedings{Schoeffmann2017CHIIR, author = {Hopfgartner,Frank and Schoeffmann,Klaus}, booktitle = {Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval (CHIIR'17)}, title = {Interactive Search in Video \& Lifelogging Repositories}, year = {2017}, address = {New York, NY, USA}, editor = {Nordlie, ragnar and Pharo, Nils}, month = {mar}, pages = {421-423}, publisher = {ACM}, abstract = {Due to increasing possibilities to create digital video, we are facing the emergence of large video archives that are made accessible either online or offline. Though a lot of research has been spent on video retrieval tools and methods, which allow for automatic search in videos, still the performance of automatic video retrieval is far from optimal. At the same time, the organization of personal data is receiving increasing research attention due to the challenges that are faced in gathering, enriching, searching and visualizing this data. Given the increasing quantities of personal data being gathered by individuals, the concept of a heterogeneous personal digital libraries of rich multimedia and sensory content for every individual is becoming a reality. Despite the differences between video archives and personal lifelogging libraries, we are facing very similar challenges when accessing these multimedia repositories. For example, users will struggle to find the information they are looking for in either collection if they are not able to formulate their search needs through a query. In this tutorial we discussed (i) proposed solutions for improved video & lifelog content navigation, (ii) typical interaction of content-based querying features, and (iii) advanced content visualization methods. Moreover, we discussed and demonstrate interactive video & lifelog search systems and ways to evaluate their performance.}, doi = {10.1145/3020165.3022161}, isbn10 = {978-1-4503-4677-1}, language = {EN}, location = {Oslo}, talkdate = {2017.03.07}, talktype = {registered}, url = {https://dl.acm.org/citation.cfm?id=3022161} } @InProceedings{Schatz2017, author = {Schatz, Raimund and Sackl, Andreas and Timmerer, Christian and Gardlo, Bruno}, booktitle = {2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX)}, title = {Towards Subjective Quality of Experience Assessment for Omnidirectional Video Streaming}, year = {2017}, address = {New York, USA}, editor = {Raake, Alexander}, month = {jun}, pages = {6}, publisher = {IEEE}, abstract = {Currently, we witness dramatically increasing interest in immersive media technologies like Virtual Reality (VR), particularly in omnidirectional video (OV) streaming. Omnidirectional (also called 360-degree) videos are panoramic spherical videos in which the user can look around during playback and which therefore can be understood as hybrids between traditional movie streaming and interactive VR worlds. Unfortunately, streaming this kind of content is extremely bandwidth intensive (compared to traditional 2D video) and therefore, Quality of Experience (QoE) tends to deteriorate significantly in absence of continuous optimal bandwidth conditions. In this paper, we present a first approach towards subjective QoE assessment for omnidirectional video (OV) streaming. We present the results of a lab study on the QoE impact of stalling in the context of OV streaming using head-mounted displays (HMDs). Our findings show that subjective testing for immersive media like OV is not trivial, with even simple cases like stalling leading to unexpected results. After a discussion of characteristic pitfalls and lessons learned, we provide a a set of recommendations for upcoming OV assessment studies.}, doi = {10.1109/QoMEX.2017.7965657}, isbn10 = {978-1-5386-4024-1}, issn = {2472-7814}, language = {EN}, location = {Erfurt, Germany}, pdf = {https://www.itec.aau.at/bib/files/QoMEX_2017_paper_44.pdf}, talkdate = {2017.06.01}, talktype = {registered} } @InProceedings{PrimusTrecVID2017, author = {Primus, Manfred Jürgen and Münzer, Bernd and Schoeffmann, Klaus}, booktitle = {Proceedings of TRECVID 2017}, title = {ITEC-UNIKLU Ad-Hoc Video Search Submission 2017}, year = {2017}, address = {NIST, Gaithersburg, MD, USA}, editor = {Awad,George and Butt,Asad and Fiscus,Jonathan and Joy,David and Delgado,Andrew and Michel,Martial and Smeaton,Alan and Graham,Yvette and Kraaij,Wessel and Quénot,Georges and Eskevich,Maria and Ordelman,Roeland and Jones,Gareth and Huet,Benoit}, month = {nov}, pages = {10}, publisher = {NIST, USA}, abstract = {This paper describes our approach used for the fully automatic and manually assisted Ad-hoc Video Search (AVS) task for TRECVID 2017. We focus on the combination of different convolutional neural network models and query optimization. Each of this model focus on a specific query part, which could be, e.g., location, objects, or the wide-ranging ImageNet classes. All classification results are collected in different combinations in Lucene indixes. For the manually assisted run we use a junk filter and different query optimization methods.}, language = {EN}, location = {Gaithersburg, MD, USA}, talkdate = {2017.11.13}, talktype = {poster} } @InProceedings{Petscharnig_2017_DS, title = {Semi-Automatic Retrieval of Relevant Segments from Laparoscopic Surgery Videos}, author = {Petscharnig, Stefan}, booktitle = {Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval}, year = {2017}, address = {New York, NY, USA}, editor = {Ionescu, Bogdan and Sebe, Nicu}, month = {jun}, pages = {484--488}, publisher = {ACM}, series = {ICMR '17}, abstract = {Over the last decades, progress in medical technology and imaging technology enabled the technique of minimally invasive surgery. In addition, multimedia technologies allow for retrospective analyses of surgeries. The accumulated videos and images allow for a speed-up in documentation, easier medical case assessment across surgeons, training young surgeons, as well as they find the usage in medical research. Considering a surgery lasting for hours of routine work, surgeons only need to see short video segments of interest to assess a case. Surgeons do not have the time to manually extract video sequences of their surgeries from their big multimedia databases as they do not have the resources for this time-consuming task. The thesis deals with the questions of how to semantically classify video frames using Convolutional Neural Networks into different semantic concepts of surgical actions and anatomical structures. In order to achieve this goal, the capabilities of predefined CNN architectures and transfer learning in the laparoscopic video domain are investigated. The results are expected to improve by domain-specific adaptation of the CNN input layers, i.e. by fusion of the image with motion and relevance information. Finally, the thesis investigates to what extent surgeons' needs are covered with the proposed extraction of relevant scenes.}, doi = {10.1145/3078971.3079008}, keywords = {endoscopic image classification, endoscopic video retrieval}, language = {EN}, location = {Bucharest, Romania}, talkdate = {2017.06.08}, talktype = {registered}, url = {http://doi.acm.org/10.1145/3078971.3079008} } @InProceedings{PetscharnigSparDa2017, author = {Petscharnig, Stefan and Lux, Mathias and Chatzichristofis, Savvas}, booktitle = {15th International Workshop on Content-Based Multimedia Indexing}, title = {Dimensionality Reduction for Image Features using Deep Learning and Autoencoders}, year = {2017}, address = {New York, USA}, editor = {Bertini, Marco}, month = {jun}, pages = {.}, publisher = {ACM}, abstract = {The field of similarity based image retrieval has experienced a game changer lately. Hand crafted image features have been vastly outperformed by machine learning based approaches. Deep learning methods are very good at finding optimal features for a domain, given enough data is available to learn from. However, hand crafted features are still means to an end in domains, where the data either is not freely available, i.e. because it violates privacy, where there are commercial concerns, or where it cannot be transmitted, i.e. due to bandwidth limitations. Moreover, we have to rely on hand crafted methods whenever neural networks cannot be trained effectively, e.g. if there is not enough training data. In this paper, we investigate a particular approach to combine hand crafted features and deep learning to (i) achieve early fusion of off the shelf handcrafted global image features and (ii) reduce the overall number of dimensions to combine both worlds. This method allows for fast image retrieval in domains, where training data is sparse.}, doi = {10.1145/3095713.3095737}, isbn10 = {978-1-4503-5333-5}, language = {EN}, location = {Firenze, Italy}, talkdate = {2017.06.21}, talktype = {registered}, url = {https://dl.acm.org/citation.cfm?id=3095737} } @InProceedings{PetscharnigMMM17, author = {Petscharnig, Stefan and Schoeffmann, Klaus}, booktitle = {International Conference on Multimedia Modeling}, title = {Deep Learning of Shot Classification in Gynecologic Surgery Videos}, year = {2017}, address = {Cham}, editor = {Amsaleg, Laurent and Guðmundsson, Gylfi Þór and Gurrin, Cathal and Jónsson, Björn Þór and Satoh, Shin’ichi}, month = {jan}, pages = {702-713}, publisher = {Springer}, abstract = {In the last decade, advances in endoscopic surgery resulted in vast amounts of video data which is used for documentation, analysis, and education purposes. In order to find video scenes relevant for aforementioned purposes, physicians manually search and annotate hours of endoscopic surgery videos. This process is tedious and time-consuming, thus motivating the (semi-)automatic annotation of such surgery videos. In this work, we want to investigate whether the single-frame model for semantic surgery shot classification is feasible and useful in practice. We approach this problem by further training of AlexNet, an already pre-trained CNN architecture. Thus, we are able to transfer knowledge gathered from the Imagenet database to the medical use case of shot classification in endoscopic surgery videos. We annotate hours of endoscopic surgery videos for training and testing data. Our results imply that the CNN-based single-frame classification approach is able to provide useful suggestions to medical experts while annotating video scenes. Hence, the annotation process is consequently improved. Future work shall consider the evaluation of more sophisticated classification methods incorporating the temporal video dimension, which is expected to improve on the baseline evaluation done in this work.}, edition = {LNCS 10132}, keywords = {Multimedia content analysis, Convolutional neural networks, Deep learning, Medical shot classification}, language = {EN}, location = {Klagenfurt, Austria}, talkdate = {2017.01.05}, talktype = {registered}, url = {https://link.springer.com/chapter/10.1007/978-3-319-51811-4_57} } @InProceedings{PetscharnigME17, author = {Petscharnig, Stefan and Schoeffmann, Klaus and Lux, Mathias}, booktitle = {Working Notes Proceedings of the MediaEval 2017 Workshop}, title = {An Inception-like CNN Architecture for GI Disease and Anatomical Landmark Classification}, year = {2017}, address = {Vol-1984}, editor = {Gravier, Guillaume and Bischke, Benjamin and Demarty, Claire-Hélène and Zaharieva, Maia and Riegler, Michael and Dellandrea, Emmanuel and Bogdanov, Dmitry and Sutcliffe, Richard and Jones, Gareth and Larson, Martha}, month = {oct}, pages = {1--3}, publisher = {CEUR-WS}, abstract = {In this working note, we describe our approach to gastrointestinal disease and anatomical landmark classification for the Medico task at MediaEval 2017. We propose an inception-like CNN architecture and a fixed-crop data augmentation scheme for training and testing. The architecture is based on GoogLeNet and designed to keep the number of trainable parameters and its computational overhead small. Preliminary experiments show that the architecture is able to learn the classification problem from scratch using a tiny fraction of the provided training data only.}, language = {EN}, location = {Dublin, Ireland}, talkdate = {2017.09.15}, talktype = {registered}, url = {http://slim-sig.irisa.fr/me17/} } @InProceedings{Muenzer2017c, author = {Münzer, Bernd and Primus, Manfred Jürgen and Kletz, Sabrina and Petscharnig, Stefan and Schoeffmann, Klaus}, booktitle = {IEEE International Symposium on Multimedia (ISM2017)}, title = {Static vs. Dynamic Content Descriptors for Video Retrieval in Laparoscopy}, year = {2017}, address = {Taichung, Taiwan}, editor = {Chang, Kang-Ming and Chang, Wen-Thong}, month = {dec}, pages = {8}, publisher = {IEEE}, abstract = {The domain of minimally invasive surgery has recently attracted attention from the Multimedia community due to the fact that systematic video documentation is on the rise in this medical field. The vastly growing volumes of video archives demand for effective and efficient techniques to retrieve specific information from large video collections with visually very homogeneous content. One specific challenge in this context is to retrieve scenes showing similar surgical actions, i.e., similarity search. Although this task has a high and constantly growing relevance for surgeons and other health professionals, it has rarely been investigated in the literature so far for this particular domain. In this paper, we propose and evaluate a number of both static and dynamic content descriptors for this purpose. The former only take into account individual images, while the latter consider the motion within a scene. Our experimental results show that although static descriptors achieve the highest overall performance, dynamic descriptors are much more discriminative for certain classes of surgical actions. We conclude that the two approaches have complementary strengths and further research should investigate methods to combine them.}, language = {EN}, location = {Taichung, Taiwan}, talkdate = {2017.12.12}, talktype = {registered} } @InProceedings{Muenzer2017b, author = {Münzer, Bernd and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {IEEE International Symposium on Multimedia (ISM2017)}, title = {EndoXplore: A Web-based Video Explorer for Endoscopic Videos}, year = {2017}, address = {Taichung, Taiwan}, editor = {Chang, Kang-Ming and Chang, Wen-Thong}, month = {dec}, pages = {2}, publisher = {IEEE}, abstract = {The rapidly increasing volume of videos recorded in the course of endoscopic screenings and surgeries poses demanding challenges to video retrieval and browsing systems. Surgeons typically have to use standard video players to retrospectively review their procedures, which is an extremely cumbersome and time-consuming process. We present an HTML5-based video explorer that is specially tailored to this purpose and enables a time-efficient post-operative review of procedures. It incorporates various interactive browsing mechanisms as well as domain-specific content-based features based on previous research results. Preliminary interviews with surgeons indicate that this tool can considerably improve retrieval and browsing efficiency for users in the medical domain and allows surgeons to more easily and quickly revisit specific moments in recordings of their endoscopic surgeries.}, language = {EN}, location = {Taichung, Taiwan}, talkdate = {2017.12.11}, talktype = {poster} } @InProceedings{Muenzer2017a, author = {Münzer, Bernd and Primus, Manfred Jürgen and Hudelist, Marco and Beecks, Christian and Hürst, Wolfgang and Schoeffmann, Klaus}, booktitle = {2017 IEEE International Conference on Multimedia \& Expo Workshops (ICMEW)}, title = {When content-based video retrieval and human computation unite: Towards effective collaborative video search}, year = {2017}, address = {Hongkong, China}, editor = {Chan, Yui-Lam and Rahardja, Susanto}, month = {jul}, pages = {214-219}, publisher = {IEEE}, abstract = {Although content-based retrieval methods achieved very good results for large-scale video collections in recent years, they still suffer from various deficiencies. On the other hand, plain human perception is a very powerful ability that still outperforms automatic methods in appropriate settings, but is very limited when it comes to large-scale data collections. In this paper, we propose to take the best from both worlds by combining an advanced content-based retrieval system featuring various query modalities with a straightforward mobile tool that is optimized for fast human perception in a sequential manner. In this collaborative system with multiple users, both subsystems benefit from each other: The results of issued queries are used to re-rank the video list on the tablet tool, which in turn notifies the retrieval tool about parts of the dataset that have already been inspected in detail and can be omitted in subsequent queries. The preliminary experiments show promising results in terms of search performance.}, doi = {10.1109/ICMEW.2017.8026262}, language = {EN}, location = {Hongkong}, talkdate = {2017.07.10}, talktype = {registered} } @InProceedings{Moll2017a, author = {Moll, Philipp and Posch, Daniel and Hellwagner, Hermann}, booktitle = {Proceedings of the IEEE International Conference on Multimedia and Expo Workshops (ICMEW) 2017}, title = {Investigation of push-based traffic for conversational services in Named Data Networking}, year = {2017}, address = {Hong Kong}, editor = {Pesquet-Popescu,Beatrice and Ngo,Chong-Wah}, month = {jul}, pages = {315-320}, publisher = {IEEE}, abstract = {Conversational services (e.g., Internet telephony) exhibit hard Quality of Service (QoS) requirements, such as low delay and jitter. Current IP-based solutions for conversational services use push-based data transfer only, since pull-based communication as envisaged in Named Data Networking (NDN) suffers from the two-way delay. Unfortunately, IP's addressing scheme requires additional services for contacting communication partners. NDN provides an inherent solution for this issue by using a location-independent naming scheme. Nevertheless, it currently does not provide a mechanism for push-based data transfer. In this paper, we investigate Persistent Interests as a solution for push-based communication. We improve and implement the idea of Persistent Interests, and study their applicability for conversational services in NDN. This is done by comparing different push- and pull-based approaches for Internet telephony.}, doi = {10.1109/ICMEW.2017.8026212}, isbn13 = {978-1-5386-0560-8}, language = {EN}, location = {Hong Kong}, pdf = {https://www.itec.aau.at/bib/files/MuSIC_2017.pdf}, talkdate = {2017.07.10}, talktype = {registered}, url = {http://ieeexplore.ieee.org/document/8026212/} } @InProceedings{Moll2017, author = {Moll, Philipp and Janda, Julian and Hellwagner, Hermann}, booktitle = {Proceedings of the 4th ACM Conference on Information-Centric Networking}, title = {Adaptive Forwarding of Persistent Interests in Named Data Networking}, year = {2017}, address = {New York, NY, USA}, editor = {Schmidt, Thomas C and Seedorf, Jan}, month = {sep}, pages = {180-181}, publisher = {ACM}, abstract = {Persistent Interests (PIs) are a promising approach to introduce push-type traffic in Named Data Networking (NDN), in particular for conversational services such as voice and video calls. Forwarding decisions for PIs are crucial in NDN because they establish a long-lived path for the data flowing back toward the PI issuer. In the course of studying the use of PIs in NDN, we investigate adaptive PI forwarding and present a strategy combining regular NDN forwarding information and results from probing potential alternative paths through the network. Simulation results indicate that our adaptive PI forwarding approach is superior to the PI-adapted Best Route strategy when network conditions change due to link failures.}, doi = {10.1145/3125719.3132091}, isbn13 = {978-1-4503-5122-5}, language = {EN}, location = {Berlin, Germany}, pdf = {https://www.itec.aau.at/bib/files/ACM-ICN-2017_Poster.pdf}, talkdate = {2017.09.27}, talktype = {registered}, url = {http://dl.acm.org/citation.cfm?id=3132091} } @InProceedings{Leibetseder2017c, author = {Leibetseder, Andreas and Münzer, Bernd and Schoeffmann, Klaus}, booktitle = {IEEE International Symposium on Multimedia (ISM2017)}, title = {A Tool for Endometriosis Annotation in Endoscopic Videos}, year = {2017}, address = {Taichung, Taiwan}, editor = {Chang, Kang-Ming and Chang, Wen-Thong}, month = {dec}, pages = {2}, publisher = {IEEE}, abstract = {When regarding physicians’ tremendously packed timetables, it comes as no surprise that they start managing even critical situations hastily in order to cope with the high demands laid out for them. Apart from treating patients’ conditions they as well are required to perform time-consuming administrative tasks, including post-surgery video analyses. Concerning documentation of minimally invasive surgeries (MIS), specifically endoscopy, such processes usually involve repeatedly perusing through lengthy, in the worst case uncut recordings – a redundant task that nowadays can be optimized by using readily available technology: we present a tool for annotating endoscopic video frames targeting a specific use case – endometriosis, i.e. the dislocation of uterine-like tissue.}, language = {EN}, location = {Taichung, Taiwan}, talkdate = {2017.12.11}, talktype = {poster} } @InProceedings{Leibetseder2017b, author = {Leibetseder, Andreas and Primus, Manfred Jürgen and Petscharnig, Stefan and Schoeffmann, Klaus}, booktitle = {Proceedings of the on Thematic Workshops of ACM Multimedia 2017}, title = {Real-Time Image-based Smoke Detection in Endoscopic Videos}, year = {2017}, address = {New York, NY, USA}, editor = {Wu, Wanmin and Yag, Jiancho and Tian, Qi and Zimmermann, Roger}, month = {jan}, pages = {296--304}, publisher = {ACM}, series = {Thematic Workshops '17}, abstract = {The nature of endoscopy as a type of minimally invasive surgery (MIS) requires surgeons to perform complex operations by merely inspecting a live camera feed. Inherently, a successful intervention depends upon ensuring proper working conditions, such as skillful camera handling, adequate lighting and removal of confounding factors, such as fluids or smoke. The latter is an undesirable byproduct of cauterizing tissue and not only constitutes a health hazard for the medical staff as well as the treated patients, it can also considerably obstruct the operating physician's field of view. Therefore, as a standard procedure the gaseous matter is evacuated by using specialized smoke suction systems that typically are activated manually whenever considered appropriate. We argue that image-based smoke detection can be employed to undertake such a decision, while as well being a useful indicator for relevant scenes in post-procedure analyses. This work represents a continued effort to previously conducted studies utilizing pre-trained convolutional neural networks (CNNs) and threshold-based saturation analysis. Specifically, we explore further methodologies for comparison and provide as well as evaluate a public dataset comprising over 100K smoke/non-smoke images extracted from the Cholec80 dataset, which is composed of 80 different cholecystectomy procedures. Having applied deep learning to merely 20K images of a custom dataset, we achieve Receiver Operating Characteristic (ROC) curves enclosing areas of over 0.98 for custom datasets and over 0.77 for the public dataset. Surprisingly, a fixed threshold for saturation-based histogram analysis still yields areas of over 0.78 and 0.75.}, doi = {10.1145/3126686.3126690}, isbn10 = {978-1-4503-5416-5}, keywords = {cnn classification, deep learning, endoscopic surgery, image processing, smoke detection}, language = {EN}, location = {Mountain View, California, USA}, talkdate = {2017.10.27}, talktype = {registered}, url = {http://doi.acm.org/10.1145/3126686.3126690} } @InProceedings{Leibetseder2017, author = {Leibetseder, Andreas and Primus, Manfred Jürgen and Petscharnig, Stefan and Schoeffmann, Klaus}, booktitle = {Computer Assisted and Robotic Endoscopy and Clinical Image-Based Procedures: 4th International Workshop, CARE 2017, and 6th International Workshop, CLIP 2017, Held in Conjunction with MICCAI 2017, Qu{\'e}bec City, QC, Canada, September 14, 2017, Proceedings}, title = {Image-Based Smoke Detection in Laparoscopic Videos}, year = {2017}, address = {Cham, Schweiz}, editor = {Cardoso, M Jorge and Arbel, Tal and Luo, Xiongbiao and Wesarg, Stefan and Reichl, Tobias and Gonzalez Ballester, Miguel Angel and McLeod, Jonathan and Drechsler, Klaus and Peters, Terry and Erdt, Marius and Mori, Kensaku and Linguraru, Marius George and Uhl, Andreas and Oyarzun Laura, Cristina and Shekhar, Raj}, month = {jan}, pages = {70--87}, publisher = {Springer International Publishing}, abstract = {The development and improper removal of smoke during minimally invasive surgery (MIS) can considerably impede a patient's treatment, while additionally entailing serious deleterious health effects. Hence, state-of-the-art surgical procedures employ smoke evacuation systems, which often still are activated manually by the medical staff or less commonly operate automatically utilizing industrial, highly-specialized and operating room (OR) approved sensors. As an alternate approach, video analysis can be used to take on said detection process -- a topic not yet much researched in aforementioned context. In order to advance in this sector, we propose utilizing an image-based smoke classification task on a pre-trained convolutional neural network (CNN). We provide a custom data set of over 30 000 laparoscopic smoke/non-smoke images, part of which served as training data for GoogLeNet-based [41] CNN models. To be able to compare our research for evaluation, we separately developed a non-CNN classifier based on observing the saturation channel of a sample picture in the HSV color space. While the deep learning approaches yield excellent results with Receiver Operating Characteristic (ROC) curves enclosing areas of over 0.98, the computationally much less costly analysis of an image's saturation histogram under certain circumstances can, surprisingly, as well be a good indicator for smoke with areas under the curves (AUCs) of around 0.92--0.97.}, doi = {10.1007/978-3-319-67543-5_7}, edition = {LNCS}, language = {EN}, location = {Québec City, Kanada}, talkdate = {2017.09.14}, talktype = {registered}, url = {https://doi.org/10.1007/978-3-319-67543-5_7} } @InProceedings{Kletz2017, author = {Kletz, Sabrina and Schoeffmann, Klaus and Münzer, Bernd and Primus, Manfred J and Husslein, Heinrich}, booktitle = {Proceedings of the First ACM Workshop on Educational and Knowledge Technologies (MultiEdTech 2017)}, title = {Surgical Action Retrieval for Assisting Video Review of Laparoscopic Skills}, year = {2017}, address = {Mountain View, California, USA}, editor = {Li, Qiong and Lienhart, Rainer and Wang, Hao Hong}, month = {oct}, pages = {9}, publisher = {ACM}, series = {MultiEdTech '17}, abstract = {An increasing number of surgeons promote video review of laparoscopic surgeries for detection of technical errors at an early stage as well as for training purposes. The reason behind is the fact that laparoscopic surgeries require specific psychomotor skills, which are difficult to learn and teach. The manual inspection of surgery video recordings is extremely cumbersome and time-consuming. Hence, there is a strong demand for automated video content analysis methods. In this work, we focus on retrieving surgical actions from video collections of gynecologic surgeries. We propose two novel dynamic content descriptors for similarity search and investigate a query-by-example approach to evaluate the descriptors on a manually annotated dataset consisting of 18 hours of video content. We compare several content descriptors including dynamic information of the segments as well as descriptors containing only spatial information of keyframes of the segments. The evaluation shows that our proposed dynamic content descriptors considering motion and spatial information from the segment achieve a better retrieval performance than static content descriptors ignoring temporal information of the segment at all. The proposed content descriptors in this work enable content-based video search for similar laparoscopic actions, which can be used to assist surgeons in evaluating laparoscopic surgical skills.}, doi = {10.1145/3132390.3132395}, keywords = {feature signatures, laparoscopic video, medical endoscopy, motion analysis, similarity search, video retrieval}, language = {EN}, location = {Mountain View, California, USA}, talkdate = {2017.10.27}, talktype = {registered}, url = {http://doi.acm.org/10.1145/3132390.3132395} } @InProceedings{Janetschek2017a, author = {Janetschek, Matthias and Prodan, Radu and Benedict, Shajulin}, title = {A Compiler Transformation-based Approach to Scientific Workflow Enactment}, booktitle = {Proceedings of the 12th Workshop on Workflows in Support of Large-Scale Science}, year = {2017}, pages = {1-12}, publisher = {ACM}, doi = {10.1145/3150994.3150999}, url = {https://dl.acm.org/citation.cfm?doid=3150994.3150999} } @InProceedings{Hurst2017, author = {Hürst, Wolfgang and Ip Vai Ching, Algernon and Schoeffmann, Klaus and Primus, Manfred Juergen}, booktitle = {MultiMedia Modeling: 23rd International Conference, MMM 2017, Reykjavik, Iceland, January 4-6, 2017, Proceedings, Part II}, title = {Storyboard-Based Video Browsing Using Color and Concept Indices}, year = {2017}, address = {Cham}, editor = {Amsaleg, Laurent and Guðmundsson, Gylfi Þór and Gurrin, Cathal and Jónsson, Björn Þór and Satoh, Shin’ichi}, month = {jan}, pages = {480-485}, publisher = {Springer International Publishing}, abstract = {We present an interface for interactive video browsing where users visually skim storyboard representations of the files in search for known items (known-item search tasks) and textually described subjects, objects, or events (ad-hoc search tasks). Individual segments of the video are represented as a color-sorted storyboard that can be addressed via a color-index. Our storyboard representation is optimized for quick visual inspections considering results from our ongoing research. In addition, a concept based-search is used to filter out parts of the storyboard containing the related concept(s), thus complementing the human-based visual inspection with a semantic, content-based annotation.}, language = {EN}, location = {Reykjavik, Iceland}, talkdate = {2017.01.04}, talktype = {registered} } @InProceedings{Hudelist2017Thumb, author = {Hudelist, Marco and Schoeffmann, Klaus}, booktitle = {International Conference on Multimedia Modeling}, title = {An Evaluation of Video Browsing on Tablets with the ThumbBrowser}, year = {2017}, address = {Cham}, editor = {Amsaleg, Laurent and Guðmundsson, Gylfi Þór and Gurrin, Cathal and Jónsson, Björn Þór and Satoh, Shin’ichi}, month = {jan}, pages = {89-100}, publisher = {Springer}, abstract = {We present an extension and evaluation of a novel interaction concept for video browsing on tablets. It can be argued that the best user experience for watching video on tablets can be achieved when the device is held in landscape orientation. Most mobile video players ignore this fact and make the interaction unnecessarily hard when the tablet is held with both hands. Naturally, in this hand posture only the thumbs are available for interaction. Our ThumbBrowser-interface takes this into account and combines it in its latest iteration with content analysis information as well as two different interaction methods. The interface was already introduced in a basic form in earlier work. In this paper we report on extensions that we applied and show first evaluation results in comparison to standard video players. We are able to show that our video browser is superior in terms of search accuracy and user satisfaction.}, doi = {10.1007/978-3-319-51814-5_8}, isbn10 = {978-3-319-51813-8}, language = {EN}, location = {Klagenfurt, Austria}, talkdate = {2017.01.05}, talktype = {registered} } @InProceedings{Hudelist2017, author = {Hudelist, Marco A and Husslein, Heinrich and Münzer, Bernd and Schoeffmann, Klaus}, booktitle = {Proceedings of the Third IEEE International Conference on Multimedia Big Data (BigMM 2017)}, title = {A Tool to Support Surgical Quality Assessment}, year = {2017}, address = {Laguna Hills, California, USA}, editor = {Chen, Shu-Ching and Sheu, Philip Chen-Yu}, month = {apr}, pages = {2}, publisher = {IEEE}, series = {BigMM'17}, abstract = {In the domain of medical endoscopy an increasing number of surgeons nowadays store video recordings of their interventions in a huge video archive. Among some other purposes, the videos are used for post-hoc surgical quality assessment, since objective assessment of surgical procedures has been identified as essential component for improvement of surgical quality. Currently, such assessment is performed manually and for selected procedures only, since the amount of data and cumbersome interaction is very time-consuming. In the future, quality assessment should be carried out comprehensively and systematically by means of automated assessment algorithms. In this demo paper, we present a tool that supports human assessors in collecting manual annotations and therefore should help them to deal with the huge amount of visual data more efficiently. These annotations will be analyzed and used as training data in the future.}, doi = {10.1109/BigMM.2017.45}, keywords = {data handling, endoscopes, medical image processing, surgery, video signal processing, automated assessment algorithms, human assessor support tool, intervention video recordings, manual annotation collection, medical endoscopy, post-hoc surgical quality assessment, surgical procedure assessment, surgical quality assessment support tool, video archive, visual data, Minimally invasive surgery, Navigation, Quality assessment, Tools, User interfaces, Video recording, generric error rating tool, medical multimedia, surgical quality assessment}, language = {EN}, location = {Laguna Hills, California, USA}, talkdate = {2017.04.21}, talktype = {poster}, url = {http://ieeexplore.ieee.org/document/7966750/} } @InProceedings{Graf2017, author = {Graf, Mario and Timmerer, Christian and Mueller, Christopher}, booktitle = {Proceedings of the 8th ACM on Multimedia Systems Conference (MMSys'17)}, title = {Towards Bandwidth Efficient Adaptive Streaming of Omnidirectional Video over HTTP: Design, Implementation, and Evaluation}, year = {2017}, address = {New York, NY, USA}, editor = {Chen, Kuan-Ta}, month = {jun}, pages = {11}, publisher = {ACM}, abstract = {Real-time entertainment services such as streaming audio- visual content deployed over the open, unmanaged Internet account now for more than 70% during peak periods. More and more such bandwidth hungry applications and services are proposed like immersive media services such as virtual reality and, specifically omnidirectional/360-degree videos. The adaptive streaming of omnidirectional video over HTTP imposes an important challenge on today’s video delivery infrastructures which calls for dedicated, thoroughly designed techniques for content generation, delivery, and consumption. This paper describes the usage of tiles — as specified within modern video codecs such HEVC/H.265 and VP9 — enabling bandwidth efficient adaptive streaming of omnidirectional video over HTTP and we define various streaming strategies. Therefore, the parameters and characteristics of a dataset for omnidirectional video are proposed and exemplary instanti- ated to evaluate various aspects of such an ecosystem, namely bitrate overhead, bandwidth requirements, and quality as- pects in terms of viewport PSNR. The results indicate bitrate savings from 40% (in a realistic scenario with recorded head movements from real users) up to 65% (in an ideal scenario with a centered/fixed viewport) and serve as a baseline and guidelines for advanced techniques including the outline of a research roadmap for the near future.}, language = {EN}, location = {Taipei, Taiwan}, pdf = {https://www.itec.aau.at/bib/files/Special_Session_Camera_Ready.pdf}, talkdate = {2016.06.20}, talktype = {registered} } @InProceedings{Darragh2017, author = {Egan, Darragh and Keighrey, Conor and Barrett, John and Qiao, Yuansong and Brennan, Sean and Timmerer, Christian and Murray, Niall}, booktitle = {Proceedings of the 2nd International Workshop on Multimedia Alternate Realities}, title = {Subjective Evaluation of an Olfaction Enhanced Immersive Virtual Reality Environment}, year = {2017}, address = {New York, NY, USA}, editor = {Chambel, Teresa and Kaiser, Rene and Niamur, Omar Aziz and Ooi, Wei Tsang}, month = {oct}, pages = {15--18}, publisher = {ACM}, series = {AltMM '17}, abstract = {Recent research efforts have reported findings on user Quality of Experience (QoE) of immersive virtual reality (VR) experiences. Truly immersive multimedia experiences also include multisensory components such as factional, tactile etc., in addition to audiovisual stimuli. In this context, this paper reports the results of a user QoE study of an olfaction-enhanced immersive VR environment. The results presented compare the user QoE between two groups (VR vs VR + Olfaction) and consider how the addition of olfaction affected user QoE levels (considering sense of enjoyment, immersion and discomfort). Self-reported measures via post-test questionnaire (10 questions) only revealed one statistically significant difference between the groups; in terms of how users felt with respect to their senses being stimulated. The presence of olfaction in the VR environment did not have a statistically significant effect in terms of user levels of enjoyment, immersion and discomfort.}, doi = {10.1145/3132361.3132363}, isbn13 = {978-1-4503-5507-0}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/p15-egan.pdf}, talktype = {none}, url = {http://doi.acm.org/10.1145/3132361.3132363} } @InProceedings{Borodulin2017, author = {Borodulin, Kirill and Radchenko, Gleb and Shestakov, Aleksandr and Sokolinsky, Leonid and Tchernykh, Andrey and Prodan, Radu}, title = {Towards Digital Twins Cloud Platform: Microservices and Computational Workflows to Rule a Smart Factory}, booktitle = {2017 IEEE/ACM $10^{\mathit{th}}$ International Conference on Utility and Cloud Computing}, year = {2017}, pages = {209-210}, month = {December}, publisher = {ACM} } @InProceedings{Beecks2017, author = {Beecks, Christian and Kletz, Sabrina and Schoeffmann, Klaus}, booktitle = {Proceedings of the Third IEEE International Conference on Multimedia Big Data (BigMM 2017)}, title = {Large-Scale Endoscopic Image and Video Linking with Gradient-Based Signatures}, year = {2017}, address = {Laguna Hills, California, USA}, editor = {Chen, Shu-Ching and Sheu, Philip Chen-Yu}, month = {apr}, pages = {5}, publisher = {IEEE}, series = {BigMM}, abstract = {Given a large-scale video archive of surgical interventions and a medical image showing a specific moment of an operation, how to find the most image-related videos efficiently without the utilization of additional semantic characteristics? In this paper, we investigate a novel content-based approach of linking medical images with relevant video segments arising from endoscopic procedures. We propose to approximate the video segments' content-based features by gradient-based signatures and to index these signatures with the Minkowski distance in order to determine the most query-like video segments efficiently. We benchmark our approach on a large endoscopic image and video archive and show that our approach achieves a significant improvement in efficiency in comparison to the state-of-the-art while maintaining high accuracy.}, doi = {10.1109/BigMM.2017.44}, keywords = {feature signatures, laparoscopic video, medical endoscopy, motion analysis, similarity search, video retrieval}, language = {EN}, location = {Laguna Hills, California, USA}, talkdate = {2017.04.19}, talktype = {registered}, url = {http://ieeexplore.ieee.org/document/7966709/} } @InProceedings{0f4de0c76764d43901677cf74a330af9, title = {{Nerthus: A Bowel Preparation Quality Video Dataset}}, author = {Pogorelov, Konstantin and Ranheim Randel, Kristin and de Lange, Thomas and Eskeland, Sigrun L. and Griwodz, Carsten and Spampinato, Concetto and Taschwer, Mario and Lux, Mathias and Schmidt, Peter T. and Riegler, Michael and Halvorsen, Pal}, booktitle = {Proceedings of the 8th ACM on Multimedia Systems Conference (MMSys 2017)}, year = {2017}, editor = {Kuan-Ta Chen and Pablo Cesar and Cheng-Hsin Hsu}, month = {Juni}, pages = {170--174}, publisher = {Association for Computing Machinery (ACM)}, abstract = {Bowel preparation (cleansing) is considered to be a key precondition for successful colonoscopy (endoscopic examination of the bowel). The degree of bowel cleansing directly affects the possibility to detect diseases and may influence decisions on screening and follow-up examination intervals. An accurate assessment of bowel preparation quality is therefore important. Despite the use of reliable and validated bowel preparation scales, the grading may vary from one doctor to another. An objective and automated assessment of bowel cleansing would contribute to reduce such inequalities and optimize use of medical resources. This would also be a valuable feature for automatic endoscopy reporting in the future. In this paper, we present Nerthus, a dataset containing videos from inside the gastrointestinal (GI) tract, showing different degrees of bowel cleansing. By providing this dataset, we invite multimedia researchers to contribute in the medical field by making systems automatically evaluate the quality of bowel cleansing for colonoscopy. Such innovations would probably contribute to improve the medical field of GI endoscopy.}, doi = {10.1145/3083187.3083216}, url = {https://dl.acm.org/citation.cfm?id=3083216} } @InProceedings{timmerer2016_NAB, author = {Timmerer, Christian and Weinberger, Daniel and Smole, Martin and Grandl, Reinhard and Mueller, Christopher and Lederer, Stefan}, booktitle = {2016 NAB Broadcast Engineering Conference Proceedings \& CD}, title = {Live Transcoding and Streaming-as-a-Service with Low Delay and High QoE}, year = {2016}, address = {Washington DC, USA}, editor = {available, not}, month = {apr}, pages = {4}, publisher = {National Association of Broadcasters (NAB)}, language = {EN}, location = {Las Vegas, NV, USA}, pdf = {https://www.itec.aau.at/bib/files/TimmererC012716.pdf}, talkdate = {2016.04.20}, talktype = {registered} } @InProceedings{hudelist2016collaborative, title = {Collaborative Video Search Combining Video Retrieval with Human-Based Visual Inspection}, author = {Hudelist, Marco A and Cob{\^a}rzan, Claudiu and Beecks, Christian and van de Werken, Rob and Kletz, Sabrina and H{\"u}rst, Wolfgang and Schoeffmann, Klaus}, booktitle = {International Conference on Multimedia Modeling}, year = {2016}, address = {Cham, Switzerland}, editor = {Tian, Qi and Sebe, Nicu and Qi, Guo-Jun and Huet, Benoit and Hong, Richang and Liu, Xueliang}, month = {jan}, organization = {Springer}, pages = {400--405}, publisher = {Springer International Publishing}, language = {EN}, location = {Miami, FL, USA}, talkdate = {2016.01.05}, talktype = {registered} } @InProceedings{Timmerer2016, author = {Timmerer, Christian and Weinberger, Daniel and Smole, Martin and Grandl, Reinhard and Mueller, Christopher and Lederer, Stefan}, booktitle = {Proceedings of the 7th International Conference on Multimedia Systems}, title = {Transcoding and Streaming-as-a-Service for improved Video Quality on the Web}, year = {2016}, address = {New York}, editor = {Timmerer, Christian and Begen, Ali}, month = {may}, pages = {37:1--37:3}, publisher = {ACM}, language = {EN}, location = {Klagenfurt, Austria}, pdf = {https://www.itec.aau.at/bib/files/MMSys2016-paper.pdf}, talkdate = {2016.05.11}, talktype = {poster} } @InProceedings{Taschwer2016, author = {Taschwer, Mario and Marques, Oge}, booktitle = {MultiMedia Modeling}, title = {Compound Figure Separation Combining Edge and Band Separator Detection}, year = {2016}, address = {Cham, Switzerland}, editor = {Tian, Qi and Sebe, Nicu and Qi, Guo-Jun and Huet, Benoit and Hong, Richang and Liu, Xueliang}, month = {jan}, pages = {162--173}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, volume = {9516}, abstract = {We propose an image processing algorithm to automatically separate compound figures appearing in scientific articles. We classify compound images into two classes and apply different algorithms for detecting vertical and horizontal separators to each class: the edge-based algorithm aims at detecting visible edges between subfigures, whereas the band-based algorithm tries to detect whitespace separating subfigures (separator bands). The proposed algorithm has been evaluated on two datasets for compound figure separation (CFS) in the biomedical domain and compares well to semi-automatic or more comprehensive state-of-the-art approaches. Additional experiments investigate CFS effectiveness and classification accuracy of various classifier implementations.}, doi = {10.1007/978-3-319-27671-7_14}, isbn13 = {978-3-319-27671-7}, language = {EN}, location = {Miami, FL, USA}, pdf = {https://www.itec.aau.at/bib/files/fig-separation-mmm.pdf}, slides = {https://www.itec.aau.at/bib/files/MMM-2016-Taschwer.pdf}, subtitle = {22nd International Conference, MMM 2016, Miami, FL, USA, January 4-6, 2016}, talkdate = {2016.01.05}, talktype = {registered}, url = {http://link.springer.com/chapter/10.1007/978-3-319-27671-7_14} } @InProceedings{Steinbacher2016, author = {Leibetseder, Andreas and Lux, Mathias}, booktitle = {Proceedings of the Third International Workshop on Gamification for Information Retrieval - co-located with 39th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2016)}, title = {Gamifying Fitness or Fitnessifying Games: a Comparative Study}, year = {2016}, address = {Pisa, Italy}, editor = {Hopfgartner, F and Kazai, G and Kruschwitz, U and Meder, M}, month = {jul}, pages = {37-44}, publisher = {CEUR Workshop Proceedings}, volume = {1642}, abstract = {Fitness- or exergames are ubiquitously available, but often lack the main ingredient of successfully gamified systems: fun. This can be attributed to the typical way of designing such games -- highly focusing on specific physical activities, thus, gamifying fitness. Instead, we propose a novel alternate approach to improve motivation for exergaming, which we call fitnessification: integrating physical exercise into very popular games that have been developed keeping fun in mind and frequently are played for long periods of time -- so-called AAA games. In order to evaluate this concept, we have conducted a comparative study examining voluntary participants' reactions to testing an ergometer controlled casual game as well as a modified AAA game. Results indicate strong tendencies of players preferring the newly introduced AAA approach over the casual fitness game.}, issn = {1613-0073}, journal = {International Workshop on Gamification for Information Retrievalic}, language = {EN}, location = {Pisa, Italy}, pdf = {https://www.itec.aau.at/bib/files/__GAMIFIR__Research_Fitnessification.pdf}, talkdate = {2016.07.21}, talktype = {registered}, url = {http://ceur-ws.org/Vol-1642/} } @InProceedings{SchoeffmannSPIE2016, author = {Schoeffmann, Klaus and Beecks, Christian and Lux, Mathias and Uysal, Merih Seran and Seidl, Thomas}, booktitle = {Proceedings of SPIE 9786, Medical Imaging 2016: Image-Guided Procedures, Robotic Interventions, and Modeling}, title = {Content-based Retrieval in Videos from Laparoscopic Surgery}, year = {2016}, address = {Bellingham, WA, USA}, editor = {Webster, Robert and Yaniv, Ziv}, month = {feb}, pages = {97861V-97861V10}, publisher = {SPIE}, language = {EN}, location = {San Diego, CA, USA}, talkdate = {2016.02.27}, talktype = {registered} } @InProceedings{PrimusTrecVID2016, author = {Primus, Manfred Jürgen and Münzer, Bernd and Petscharnig, Stefan and Schoeffmann, Klaus}, booktitle = {Proceedings of TRECVID 2016}, title = {ITEC-UNIKLU Ad-Hoc Video Search Submission 2016}, year = {2016}, address = {NIST, Gaithersburg, MD, USA}, editor = {Awad, George and Fiscus, Jonathan and Michel, Martial and Joy, David and Kraaij, Wessel and Smeaton, Alan F and Quénot, Georges and Eskevich, Maria and Aly, Robin and Jones, Gareth J F and Ordelman, Roeland and Huet, Benoit and Larson, Martha}, month = {nov}, pages = {10}, publisher = {NIST, USA}, abstract = {In this report we describe our approach to the fully automatic Ad-hoc video search task for TRECVID 2016. We describe how we obtain training data from the web, create according CNN models for the provided queries and use them to classify keyframes from a custom sub-shot detection method. The resulting classifications are fed into a Lucene index in order to obtain the shots that match the query. We also discuss our results and point out potentials for further improvements.}, language = {EN}, location = {Gaithersburg, MD, USA}, talkdate = {2016.11.15}, talktype = {poster} } @InProceedings{Primus2015, author = {Primus, Manfred Jürgen and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 14th International Workshop on Content-Based Multimedia Indexing (CBMI 2016)}, title = {Temporal Segmentation of Laparoscopic Videos into Surgical Phases}, year = {2016}, address = {Los Alamitos, CA, USA}, editor = {Ionescu, Bogdan and Müller, Henning and Kompatsiaris, Yiannis and Gravier, Guillaume}, month = {jun}, pages = {1-6}, publisher = {IEEE}, language = {EN}, location = {Bucharest}, talkdate = {2016.06.15}, talktype = {registered} } @InProceedings{Posch2016, author = {Posch, Daniel and Rainer, Benjamin and Theuermann, Sebastian and Leibetseder, Andreas and Hellwagner, Hermann}, booktitle = {Proceedings of the 7th International Conference on Multimedia Systems}, title = {Emulating NDN-based Multimedia Delivery}, year = {2016}, address = {New York}, editor = {Timmerer, Christian and Begen, Ali}, month = {may}, pages = {4}, publisher = {ACM Digital Library}, series = {MMSys '16}, abstract = {Today, the global share and increase of Internet traffic is largely caused by multimedia delivery, mainly encompassing video, audio and image sharing on social, news, and entertainment platforms. This fact is well known to the Internet research community, which tries to counteract by increasing the content delivery efficiency. So-called Information-Centric Networks (ICN) are of considerable interest, advertised as enablers for intelligent networks, where effective delivery is to be provided as an inherent network feature. Most research proposals in this area are evaluated in simulated environments, using simulation frameworks such as OMNeT++ or ns-3. However, simulations always have shortcomings and cannot substitute measurements in physical networks. In this demonstration, we show how to readily set up an ICN-based testbed using low-budget single-board computers to conduct comprehensive emulations. We choose the scenario of pull-based adaptive video delivery as a showcase and evaluate the performance of different client-based adaptation mechanisms at the application level and different content forwarding strategies at the network level. All of the presented tools and visualization features are provided as open source contributions to the community.}, doi = {10.1145/2910017.2910626}, isbn13 = {978-1-4503-4297-1}, keywords = {Named Data Networking, Information-Centric Networking, Network Emulation, Adaptive Multimedia Delivery, Testbed}, language = {EN}, location = {Klagenfurt, Austria}, pdf = {https://www.itec.aau.at/bib/files/pi-demo.pdf}, talkdate = {2016.05.11}, talktype = {poster}, url = {http://doi.acm.org/10.1145/2910017.2910626} } @InProceedings{Muenzer2016, author = {Münzer, Bernd and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {29th International Symposium on Computer-Based Medical Systems (CBMS'16)}, title = {Domain-Specific Video Compression for Long-term Archiving of Endoscopic Surgery Videos}, year = {2016}, address = {Dublin, Ireland}, editor = {Kane, B and Marshall, A and Soda, P}, month = {jun}, pages = {312-317}, publisher = {IEEE}, doi = {10.1109/CBMS.2016.28}, language = {EN}, location = {Dublin}, talkdate = {2016.06.23}, talktype = {registered} } @InProceedings{Martina_HH_Jan18, author = {Beck, Harald and Bierbaumer, Bruno and Dao-Tran, Minh and Eiter, Thomas and Hellwagner, Hermann and Shekotihin, Konstantin}, booktitle = {Proceedings of 15th European Conference on Logics in Artificial Intelligence (JELIA) 2016}, title = {Rule-based Stream Reasoning for Intelligent Administration of Content-Centric Networks}, year = {2016}, address = {Cyprus}, editor = {Michael, Loizos and C Kakas, Antonis}, month = {nov}, pages = {522-528}, publisher = {Springer}, abstract = {Content-Centric Networking (CCN) research addresses the mismatch between the modern usage of the Internet and its outdated architecture. Importantly, CCN routers use various caching strategies to locally cache content frequently requested by end users. However, it is unclear which content shall be stored and when it should be replaced. In this work, we employ novel techniques towards intelligent administration of CCN routers. Our approach allows for autonomous switching between existing strategies in response to changing content request patterns using rule-based stream reasoning framework LARS which extends Answer Set Programming for streams. The obtained possibility for flexible router configuration at runtime allows for faster experimentation and may result in significant performance gains, as shown in our evaluation.}, doi = {10.1007/978-3-319-48758-8_34}, language = {EN}, location = {Cyprus}, talkdate = {2016.11.10}, talktype = {registered} } @InProceedings{Kreuzberger2016a, author = {Kreuzberger, Christian and Rainer, Benjamin and Hellwagner, Hermann and Toni, Laura and Frossard, Pascal}, booktitle = {Proceedings of the 26th International Workshop on Network and Operating Systems Support for Digital Audio and Video}, title = {A Comparative Study of DASH Representation Sets Using Real User Characteristics}, year = {2016}, address = {New York, NY, USA}, editor = {ACM,}, month = {may}, pages = {4:1--4:6}, publisher = {ACM}, isbn10 = {978-1-4503-4356-5}, language = {EN}, location = {Klagenfurt, Austria}, talkdate = {2016.05.13}, talktype = {registered} } @InProceedings{Hurst:2016:NTC:2964284.2973824, title = {A New Tool for Collaborative Video Search via Content-based Retrieval and Visual Inspection}, author = {Hürst, Wolfgang and Ip Vai Ching, Algernon and Hudelist, Marco and Primus, Manfred and Schoeffmann, Klaus and Beecks, Christian}, booktitle = {Proceedings of the 2016 ACM on Multimedia Conference}, year = {2016}, address = {New York, NY, USA}, editor = {Hanjalic, Alan and Snoek, Cees and Worring, Marcel}, month = {jan}, pages = {731--732}, publisher = {ACM}, series = {MM '16}, doi = {10.1145/2964284.2973824}, keywords = {collaborative search, feature signatures, human-computer interaction, video retrieval}, language = {EN}, location = {Amsterdam, The Netherlands}, talkdate = {2016.10.16}, talktype = {registered}, url = {http://doi.acm.org/10.1145/2964284.2973824} } @InProceedings{HudelistMMM2016, author = {Hudelist, Marco Andrea and Cob\^{a}rzan, Claudiu and Beecks, Christian and van de Werken, Rob and Kletz, Sabrina and H\"{u}rst, Wolfgang and Schoeffmann, Klaus}, booktitle = {Multimedia Modeling}, title = {Collaborative Video Search Combining Video Retrieval with Human-Based Visual Inspection}, year = {2016}, address = {Cham, Switzerland}, editor = {Tian, Qi and Sebe, Nicu and Qi, Guo-Jun and Huet, Benoit and Hong, Richang and Liu, Xueliang}, month = {jan}, pages = {400-405}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, abstract = {We propose a novel video browsing approach that aims at optimally integrating traditional, machine-based retrieval methods with an interface design optimized for human browsing performance. Advanced video retrieval and filtering (e.g., via color and motion signatures, and visual concepts) on a desktop is combined with a storyboard-based interface design on a tablet optimized for quick, brute-force visual inspection. Both modules run independently but exchange information to significantly minimize the data for visual inspection and compensate mistakes made by the search algorithms.}, isbn13 = {978-3-319-27673-1}, language = {EN}, location = {Miami, Florida, USA}, subtitle = {22nd International Conference, MMM 2016, Miami, FL, USA, January 4-6, 2016, Proceedings, Part II}, talkdate = {2016.01.05}, talktype = {poster}, url = {http://link.springer.com/chapter/10.1007/978-3-319-27674-8_40} } @InProceedings{Hudelist:2016:TAT:2964284.2973822, title = {A Tablet Annotation Tool for Endoscopic Videos}, author = {Hudelist, Marco and Kletz, Sabrina and Schoeffmann, Klaus}, booktitle = {Proceedings of the 2016 ACM on Multimedia Conference}, year = {2016}, address = {New York, NY, USA}, editor = {Hanjalic, Alan and Snoek, Cees and Worring, Marcel}, month = {jan}, pages = {725--727}, publisher = {ACM}, series = {MM '16}, doi = {10.1145/2964284.2973822}, keywords = {endoscopic videos, mobile, user interface, video browsing}, language = {EN}, location = {Amsterdam, The Netherlands}, talkdate = {2016.10.16}, talktype = {registered}, url = {http://doi.acm.org/10.1145/2964284.2973822} } @InProceedings{Hudelist:2016:MBE:2964284.2973821, title = {A Multi-Video Browser for Endoscopic Videos on Tablets}, author = {Hudelist, Marco and Kletz, Sabrina and Schoeffmann, Klaus}, booktitle = {Proceedings of the 2016 ACM on Multimedia Conference}, year = {2016}, address = {New York, NY, USA}, editor = {Hanjalic, Alan and Snoek, Cees and Worring, Marcel}, month = {oct}, pages = {722--724}, publisher = {ACM}, series = {MM '16}, doi = {10.1145/2964284.2973821}, keywords = {endoscopic videos, mobile, user interface, video browsing}, language = {EN}, location = {Amsterdam, The Netherlands}, talkdate = {2016.10.16}, talktype = {registered}, url = {http://doi.acm.org/10.1145/2964284.2973821} } @InProceedings{Hermann2016, author = {Yanmaz, Evsen and Quaritsch, Markus and Yahyanejad, Saeed and Rinner, Bernhard and Hellwagner, Hermann and Bettstetter, Christian}, booktitle = {Proceedings of the EAI International Conference on Ad Hoc Networks (ADHOCNETS)}, title = {Communication and Coordination for Drone Networks}, year = {2016}, address = {Ottawa, Canada}, editor = {Yifeng, Zhou and Thomas, Kunz}, month = {sep}, pages = {79-91}, publisher = {Springer Verlag}, abstract = {Small drones are being utilized in monitoring, delivery of goods, public safety, and disaster management among other civil applications. Due to their sizes, capabilities, payload limitations, and limited flight time, it is not far-fetched to expect multiple networked and coordinated drones incorporated into the air traffic. In this paper, we describe a high-level architecture for the design of a collaborative aerial system that consists of drones with on-board sensors and embedded processing, sensing, coordination, and communication&networking capabilities. We present a multi-drone system consisting of quadrotors and demonstrate its potential in a disaster assistance scenario. Furthermore, we illustrate the challenges in the design of drone networks and present potential solutions based on the lessons we have learned so far.}, doi = {10.1007/978-3-319-51204-4_7}, isbn13 = {978-3-319-51203-7}, keywords = {drones, unmanned aerial vehicle networks, wireless sensor networks, vehicular communications, cooperative aerial imaging}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Yanmaz_ADHOCNETS2016.pdf}, talktype = {none}, url = {http://link.springer.com/chapter/10.1007/978-3-319-51204-4_7} } @InProceedings{Egan2016, author = {Egan, Darragh and Brennan, Sean and Barret, John and Qiao, Yuansong and Timmerer, Christian and Murray, Niall}, booktitle = {2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX)}, title = {An evaluation of Heart Rate and ElectroDermal Activity as an objective QoE evaluation method for immersive virtual reality environments}, year = {2016}, address = {Lisboa, Portugal}, editor = {Pereira, Fernando and Diepold, Klaus and Queluz, Paula and Reiter, Ulrich}, month = {jun}, pages = {1-6}, publisher = {IEEE Signal Processing Society}, language = {EN}, location = {Lisboa, Portugal}, pdf = {https://www.itec.aau.at/bib/files/QoMEX2016-paper.pdf}, talkdate = {2016.06.07}, talktype = {poster} } @InProceedings{martina4HH, author = {Scherer, Jürgen and Yahyanejad, Saeed and Hayat, Samira and Yanmaz, Evsen and Andre, Torsten and Khan, Asif and Vukadinovic, Vladimir and Bettstetter, Christian and Hellwagner, Hermann and Rinner, Bernhard}, booktitle = {Proceedings of the First Workshop on Micro Aerial Vehicle Networks, Systems, and Applications for Civilian Use}, title = {An Autonomous Multi-UAV System for Search and Rescue}, year = {2015}, address = {New York, USA}, editor = {Chen, Kuan-Ta and Gerla, Mario and Hummel, Karin Anna and Palazzi, Claudio and Pollin, Sofie and Sterbenz, James JP}, month = {may}, pages = {33-38}, publisher = {ACM}, abstract = {This paper proposes and evaluates a modular architecture of an autonomous unmanned aerial vehicle (UAV) system for search and rescue missions. Multiple multicopters are coordinated using a distributed control system. The system is implemented in the Robot Operating System (ROS) and is capable of providing a real-time video stream from a UAV to one or more base stations using a wireless communications infrastructure. The system supports a heterogeneous set of UAVs and camera sensors. If necessary, an operator can interfere and reduce the autonomy. The system has been tested in an outdoor mission serving as a proof of concept. Some insights from these tests are described in the paper.}, doi = {10.1145/2750675.2750683}, language = {EN}, talktype = {none}, url = {http://delivery.acm.org/10.1145/2760000/2750683/p33-scherer.pdf?ip=143.205.122.208&id=2750683&acc=ACTIVE%20SERVICE&key=9074CF143665B1C6.EF9309C4544B4D37.4D4702B0C3E38B35.4D4702B0C3E38B35&CFID=736686875&CFTOKEN=42529581&__acm__=1449667683_6d2e816f622de719bc19fd2f077632c2} } @InProceedings{Zaharieva_ICMR2015, author = {Zaharieva, Maia and Zeppelzauer, Matthias and Del Fabro, Manfred and Schopfhauser, Daniel}, booktitle = {Proceedings of the 5th ACM International Conference on Multimedia Retrieval}, title = {Social Event Mining in Large Photo Collections}, year = {2015}, address = {Shanghai, China}, editor = {Li, Xirong and Zhou, Xiangdong}, month = {jun}, pages = {1--8}, publisher = {ACM}, language = {EN}, talktype = {none} } @InProceedings{Xu2015, author = {Xu, He and Pereira, Fernando and Timmerer, Christian and Ebrahimi, Touradj}, booktitle = {Proceedings of 2015 European Conference on Networks and Communications (EUCNC)}, title = {Towards Quality of Sensory Experience in Multimedia}, year = {2015}, address = {Brussels, Belgium}, editor = {Demassieux, Nicolas and Campolargo, Mario}, month = {jun}, pages = {627-628}, publisher = {IEEE}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1570129963.pdf}, talktype = {none} } @InProceedings{Timmerer2015_ICME, author = {Timmerer, Christian and Weinberger, Daniel and Smole, Martin and Grandl, Reinhard and Mueller, Christopher and Lederer, Stefan}, booktitle = {2015 IEEE International Conference on Multimedia \& Expo Workshops (ICMEW)}, title = {Live Transcoding and Streaming-as-a-Service with MPEG-DASH}, year = {2015}, address = {Los Alamitos, CA}, editor = {Magli, Enrico and Tubaro, Stefano and Vetro, Anthony}, month = {jun}, pages = {1-4}, publisher = {IEEE}, abstract = {Multimedia content delivery and real-time streaming over the top of the existing infrastructure is nowadays part and parcel of every media ecosystem thanks to open standards and the adoption of the Hypertext Transfer Protocol (HTTP) as its primary mean for transportation. Hardware encoder manufacturers have adopted their product lines to support the dynamic adaptive streaming over HTTP but suffer from the inflexibility to provide scalability on demand, specifically for event-based live services that are only offered for a limited period of time. The cloud computing paradigm allows for this kind of flexibility and provide the necessary elasticity in order to easily scale with the demand required for such use case scenarios. In this paper we describe bitcodin, our transcoding and streaming-as-as-ervice platform based on open standards (i.e., MPEG-DASH) which is deployed on standard cloud and content delivery infrastructures to enable high-quality streaming to heterogeneous clients. It is currently deployed for video on demand, 24/7 live, and event-based live services using bitdash, our adaptive client framework.}, language = {EN}, location = {Torino, Italy}, pdf = {https://www.itec.aau.at/bib/files/icme2015-bitmovin_camera-ready.pdf}, talkdate = {2015.06.30}, talktype = {poster} } @InProceedings{Taschwer2015, author = {Taschwer, Mario and Marques, Oge}, booktitle = {{CLEF} 2015 Working Notes}, title = {AAUITEC at ImageCLEF 2015: Compound Figure Separation}, year = {2015}, address = {Padova, Italy}, editor = {Capellato, Linda and Ferro, Nicola and Jones, Gareth and Juan, Eric}, month = {sep}, pages = {9}, publisher = {CLEF Association}, series = {CEUR Workshop Proceedings, ISSN 1613-0073}, volume = {1391}, abstract = {Our approach to automatically separating compound figures appearing in biomedical articles is split into two image processing algorithms: one is based on detecting separator edges, and the other tries to identify background bands separating sub gures. Only one algorithm is applied to a given image, according to the prediction of a binary classifier trained to distinguish graphical illustrations from other images in biomedical articles. Our submission to the ImageCLEF 2015 compound figure separation task achieved an accuracy of 49% on the provided test set of about 3400 compound images. This stays clearly behind the best submission of other participants (85% accuracy), but is by an order of magnitude faster than other approaches reported in the literature.}, language = {EN}, location = {Toulouse, France}, pdf = {https://www.itec.aau.at/bib/files/aauitec-fig-separation.pdf}, slides = {https://www.itec.aau.at/bib/files/poster-aauitec-fig-separation.pdf}, talkdate = {2015.09.09}, talktype = {poster}, url = {http://ceur-ws.org/Vol-1391/25-CR.pdf} } @InProceedings{SchoeffmannBurgstaller2015, author = {Schoeffmann, Klaus and Burgstaller, Lukas}, booktitle = {Proceedings of the IEEE International Symposium on Multimedia 2015 (ISM 2015)}, title = {Scrubbing Wheel: An Interaction Concept to Improve Video Content Navigation on Devices with Touchscreens}, year = {2015}, address = {Los Alamitos, CA}, editor = {Del Bimbo, Alberto and Chen, Shu-Ching and Wang, Haohong and Yu, Heather and Zimmermann, Roger}, month = {dec}, pages = {1-6}, publisher = {IEEE}, abstract = {We propose a new interface that facilitates content navigation in videos on devices with touchscreen interaction. This interface allows both coarse-grained and fine-grained navigation in an intuitive way and enables better performance when used to locate specific scenes in videos. We implemented this interface on a 5.5-inch smartphone and tested it with 24 users.Our results show that for video navigation tasks the proposed interface significantly outperforms the seeker-bar interface, commonly used with video players on mobile devices. Moreover, we found that the interaction concept of the Scrubbing Wheel has a much lower perceived workload than the widely used seeker-bar, and is the preferred tool to locate scenes in videos for all tested users in our study.}, language = {EN}, location = {Miami, FLorida, USA}, talkdate = {2015.12.14}, talktype = {registered} } @InProceedings{Rainer2015_MMSysDemo, author = {Rainer, Benjamin and Petscharnig, Stefan and Timmerer, Christian}, booktitle = {Proceedings of the 6th ACM International Conference on Multimedia Systems}, title = {Merge And Forward - Self-organized Inter-Destination Multimedia Synchronization}, year = {2015}, address = {New York, U.S.A}, editor = {not, available}, month = {mar}, pages = {77-80}, publisher = {ACM International Conference on Multimedia Systems}, abstract = {Social networks have become ubiquitous and with these new possible ways for social communication and experiencing multimedia together the traditional TV scenario drifts more and more towards a distributed social experience. Asynchronism in the multimedia playback of the users may have a significant impact on the acceptability of systems providing the distributed multimedia experience. The synchronization needed in such systems is called Inter-Destination Multimedia Synchronization. In this paper we propose a demo that implements IDMS by the means of our self-organized and distributed approach assisted by pull-based streaming. We also provide a video of the planned demonstration and provide the mobile application as open source licensed under the GNU LGPL.}, language = {EN}, location = {Portland, Oregon}, talkdate = {2015.03.18}, talktype = {poster} } @InProceedings{Rain1502:IDMSQoMEX, author = {Rainer, Benjamin and Petscharnig, Stefan and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Seventh International Workshop on Quality of Multimedia Experience (QoMEX 2015)}, title = {Is One Second Enough? - Evaluating QoE for Inter-Destination Multimedia Synchronization using Human Computation and Crowdsourcing}, year = {2015}, address = {Greece, Messinia}, editor = {Skodras, Athanassios}, month = {may}, pages = {1-6}, publisher = {IEEE}, abstract = {Modern-age technology enables us to consume multimedia for enjoyment and as a social experience. The traditional way to consume multimedia together (e.g., with family or friends in the living room) is being superseded by a location-independent scenario where geographically distributed users consume the same content while having a real-time communication channel among each other. Inter-Destination Multimedia Synchronization (IDMS) is the tool of choice in order to enable users a high-quality multimedia experience. In this paper, we investigate the influence of asynchronism when consuming multimedia content together while being geographically distributed. In particular, we adopt the concept of human computation and developed a reaction game which we used to conduct a crowdsourced subjective quality assessment in order to evaluate a threshold for multimedia synchronization within an IDMS scenario. Our results show a significant decrease in overall Quality of Experience (QOE) at an asynchronism level of 750ms. At the same time, we were able to show that asynchronism at a level of 400ms does not have significant differences regarding the QoE when compared to the synchronous reference case.}, language = {EN}, location = {Greece, Messinia, Costa Navarino}, pdf = {https://www.itec.aau.at/bib/files/07148107.pdf}, talkdate = {2015.05.27}, talktype = {registered} } @InProceedings{Raffelsberger2015, author = {Raffelsberger, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the 13th IEEE International Conference on Pervasive Computing and Communications Workshops ({PerCom Workshops '15})}, title = {A Multimedia Delivery System for Delay-/Disruption-Tolerant Networks}, year = {2015}, address = {Los Alamitos, CA, USA}, editor = {Hurson, Ali and Das, Sajal K}, month = {mar}, pages = {530-536}, publisher = {IEEE}, abstract = {Multimedia delivery systems and protocols usually assume end-to-end connections and low delivery delays between multimedia sources and consumers. However, neither of these two properties can always be achieved in hastily formed networks for emergency response operations. In particular, disruptions may break end-to-end connections, which makes it impossible to deliver multimedia content instantly. This work presents a multimedia delivery system that can operate in disrupted networks and hence may help improve the situational awareness in emergency response operations. The multimedia delivery system is based on HTTP adaptive streaming (HAS) and uses a modified version of HTTP which is able to deliver data in partitioned networks. The multimedia delivery system is evaluated in a realistic emergency response scenario.}, doi = {10.1109/PERCOMW.2015.7134093}, isbn10 = {978-1-4799-8425-1}, language = {EN}, location = {Saint Louis, MO, USA}, pdf = {https://www.itec.aau.at/bib/files/CR-PerNEM15.pdf}, talkdate = {2015.03.27}, talktype = {registered} } @InProceedings{Primus_CBMI2015, author = {Primus, Manfred Jürgen and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {13th International Workshop on Content-Based Multimedia Indexing}, title = {Instrument Classification in Laparoscopic Videos}, year = {2015}, address = {Los Alamitos, CA, USA}, editor = {Skopal, Tomas and Lokoc, Jakub}, month = {jun}, pages = {1--6}, publisher = {IEEE Computer Society}, abstract = {In medical endoscopy more and more surgeons record videos of their interventions in a long-term storage archive for later retrieval. In order to allow content-based search in such endoscopic video archives, the video data needs to be indexed first. However, even the very basic step of content-based indexing, namely content segmentation, is already very challenging due to the special characteristics of such video data. Therefore, we propose to use instrument classification to enable semantic segmentation of laparoscopic videos. In this paper, we evaluate the performance of such an instrument classification approach. Our results show satisfying performance for all instruments used in our evaluation.}, doi = {10.1109/CBMI.2015.7153616}, isbn10 = {978-1-4673-6870-4}, language = {EN}, location = {Prague, Czech Republic}, talkdate = {2015.06.12}, talktype = {registered}, url = {http://siret.ms.mff.cuni.cz/cbmi2015/} } @InProceedings{Mueller2015_ICME, author = {Mueller, Christopher and Lederer, Stefan and Grandl, Reinhard and Timmerer, Christian}, booktitle = {Proceedings of 2015 IEEE International Conference on Multimedia and Expo (ICME)}, title = {Oscillation Compensating Dynamic Adaptive Streaming over HTTP}, year = {2015}, address = {Los Alamitos, CA}, editor = {Magli, Enrico and Tubaro, Stefano and Vetro, Anthony}, month = {jul}, pages = {1-6}, publisher = {IEEE}, abstract = {Streaming multimedia over the Internet is omnipresent but still in its infancy, specifically when it comes to the adaptation based on bandwidth/throughput measurements, clients competing for limited/shared bandwidth, and the presence of a caching infrastructure. In this paper we present a buffer-based adaptation logic in combination with a toolset of client metrics to compensate for erroneous adaptation decisions. These erroneous adaptation decisions are due to insufficient network information available at the client and issues introduced when multiple clients compete for limited/shared bandwidth and/or when caches are deployed. Our metrics enable the detection of oscillations on the client - in contrast to server-based approaches - and provide an effective compensation mechanism. We evaluate the proposed adaptation logic, which incorporates the oscillation detection and compensation method, and compare it against a throughput-based adaptation logic for scenarios comprising competing clients with and without caching enabled. In anticipation of the results, we show how the presented metrics detect oscillation periods and how such undesirable situations can be compensated while increasing the effective media throughput of the clients.}, doi = {10.1109/ICME.2015.7177435}, language = {EN}, location = {Torino, Italy}, pdf = {https://www.itec.aau.at/bib/files/icme2015paper.pdf}, talkdate = {2015.07.02}, talktype = {registered} } @InProceedings{Martina4Klaus, author = {Hudelist, Marco A and Schöffmann, Klaus and Ahlström, David and Lux, Mathias}, booktitle = {Multimedia \& Expo Workshops (ICMEW), 2015 IEEE International Conference on}, title = {How Many, What and Why? Visual Media Statistics on Smartphones and Tablets}, year = {2015}, address = {Piscataway, NJ, USA}, editor = {Magli, Enrico and Tubaro, Stefano and Vetro, Anthony}, month = {jul}, pages = {1-6}, publisher = {IEEE}, abstract = {The focus of our research is on improving mobile image and video browsing interfaces. To get a better idea about real world mobile photo and video scenarios and to base our research on real world numbers we performed a survey of photo and video usage on smartphones and tablets. In an online survey we asked 215 participants of the German speaking region about their mobile image collections, their usage patterns, and their motives and intentions when capturing photos. Our results show, among other things, that users store considerable more photos on smartphones than on tablets, that the majority of our participants use their smartphone as primary camera and that users are unlikely to organize their photos on their mobile devices in any way. Moreover, the most popular motives are people, holiday photos, events, and landscapes. Furthermore, it is more popular to capture photos for private than for sharing purposes. We also report about various correlation hypothesis that we tested in the gathered data.}, doi = {10.1109/ICMEW.2015.7169868}, isbn10 = {978­1­4799­7079­7}, language = {EN}, location = {Turin, Italy}, talkdate = {2015.06.29}, talktype = {registered}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7169868&tag=1} } @InProceedings{LokocDemoMMM2015, author = {Lokoc, Jakub and Schoeffmann, Klaus and Del Fabro, Manfred}, booktitle = {Proceedings of the 21st International Conference on MultiMedia Modelling 2015 (MMM 2015)}, title = {Dynamic Hierarchical Visualization of Keyframes in Endoscopic Video}, year = {2015}, address = {Heidelberg, Berlin, New York}, editor = {He, Xiangjian and Xu, Changsheng}, month = {jan}, pages = {4}, publisher = {Springer}, language = {EN}, location = {Sydney, Australia}, talkdate = {2015.01.06}, talktype = {poster} } @InProceedings{Lokoc2015, author = {Lokoc, Jakub and Münzer, Bernd and Schoeffmann, Klaus and del Fabro, Manfred and Primus, Manfred Jürgen and Skopal, Tomas and Lansky, Jan}, booktitle = {Proceedings of the 2015 IEEE International Conference on Multimedia \& Expo Workshops (ICMEW)}, title = {What are the Salient Keyframes in Short Casual Videos? An Extensive User Study using a new Video Dataset}, year = {2015}, address = {Los Alamitos, CA}, editor = {Cesana, Matteo}, month = {jun}, pages = {1-6}, publisher = {IEEE}, language = {EN}, location = {Turin, Italy}, talkdate = {2015.06.29}, talktype = {registered} } @InProceedings{Kreuzberger2015b, author = {Kreuzberger, Christian and Rainer, Benjamin and Hellwagner, Hermann}, booktitle = {IEEE International Conference on Multimedia Expo Workshops}, title = {Modelling the Impact of Caching and Popularity on Concurrent Adaptive Multimedia Streams in Information-Centric Networks}, year = {2015}, address = {Los Alamitos, CA, USA}, editor = {Matteo, Cesana}, month = {jul}, pages = {1--6}, publisher = {IEEE}, series = {ICMEW '15}, abstract = {The Internet is nowadays mainly used for streaming of multimedia content, something it was not built for originally. To guarantee user satisfaction, one of the key concepts of the Internet as we know it is bandwidth sharing. While this concept is necessary to provide stability in the network, several issues can arise with adaptive multimedia streaming, e.g., efficiency and stability. Considering Information-Centric Networking (ICN) and its network-inherent caching, those issues tend to become worse. Many researchers have proposed to use traffic shaping on the server to enable fair bandwidth sharing and stabilize clients. However, existing research does not consider content popularity and in-network caching. The contribution of this paper is two-fold. First, we propose a cache-aware traffic shaping policy, in order to guarantee seamless playback of videos. Second, based on content popularity, we calculate an average video quality achieved by this traffic shaping policy for various cache sizes, to show the impact of popularity and caching for multimedia streaming in ICN.}, doi = {10.1109/ICMEW.2015.7169763}, keywords = {Content Popularity; Adaptive Multimedia Streaming; Information-Centric Networking; Traffic Shaping}, language = {EN}, location = {Torino, Italy}, pdf = {https://www.itec.aau.at/bib/files/music_modelling_streaming_revision1_v3.pdf}, talkdate = {2015.07.03}, talktype = {registered} } @InProceedings{Kreuzberger2015a, author = {Kreuzberger, Christian and Posch, Daniel and Hellwagner, Hermann}, booktitle = {Proceedings of the 6th ACM Multimedia Systems Conference}, title = {A Scalable Video Coding Dataset and Toolchain for Dynamic Adaptive Streaming over HTTP}, year = {2015}, address = {New York, NY, USA}, editor = {Wei, Tsang Ooi}, month = {mar}, pages = {213--218}, publisher = {ACM}, series = {MMSys '15}, abstract = {With video streaming becoming more and more popular, the number of devices that are capable of streaming videos over the Internet is growing. This leads to a heterogeneous device landscape with varying demands. Dynamic Adaptive Streaming over HTTP (DASH) offers an elegant solution to these demands. Smart adaptation logics are able to adjust the clients' streaming quality according to several (local) parameters. Recent research indicated benefits of blending Scalable Video Coding (SVC) with DASH, especially considering Future Internet architectures. However, except for a DASH dataset with a single SVC encoded video, no other datasets are publicly available. The contribution of this paper is two-fold. First, a DASH/SVC dataset, containing multiple videos at varying bitrates and spatial resolutions including 1080p, is presented. Second, a toolchain for multiplexing SVC encoded videos is provided, therefore making our results reproducible and allowing researchers to generate their own datasets.}, doi = {10.1145/2713168.2713193}, isbn13 = {978-1-4503-3351-1}, keywords = {DASH; Dataset; Toolchain; Scalable Video Coding}, language = {EN}, location = {Portland, Oregon}, pdf = {https://www.itec.aau.at/bib/files/dash_svc_dataset_v1.05.pdf}, talkdate = {2015.03.18}, talktype = {registered}, url = {http://concert.itec.aau.at/SVCDataset/} } @InProceedings{Hudelist2015a, author = {Hudelist, Marco Andrea and Schoeffmann, Klaus and Xu, Qing}, booktitle = {Proceedings of the 21st International Conference on MultiMedia Modelling 2015 (MMM 2015)}, title = {Improving Interactive Known-Item Search in Video with the Keyframe Navigation Tree}, year = {2015}, address = {Berlin, Heidelberg, New York}, editor = {He, Xiangjian and Luo, Suhuai}, month = {jan}, pages = {12}, publisher = {Springer}, language = {EN}, location = {Sydney, Australia}, talkdate = {2015.6.1}, talktype = {registered} } @InProceedings{HH2015a, author = {Hellwagner, Hermann and Kacianka, Severin}, booktitle = {MoVid '15 Proceedings of the 7th ACM International Workshop on Mobile Video}, title = {Adaptive Video Streaming for UAV Networks}, year = {2015}, address = {New York, USA}, editor = {Halvorsen, Pal and Dutt, Nikil}, month = {mar}, pages = {25-30}, publisher = {ACM International Conference on Multimedia Systems}, abstract = {The core problem for any adaptive video streaming solution, particularly over wireless networks, is the detection (or even prediction) of congestion. IEEE 802.11 is especially vulnerable to fast movement and change of antenna orientation. When used in UAV networks (Unmanned Aerial Vehicles), the network throughput can vary widely and is almost impossible to predict. this paper evaluates an approach originally developed by Kofler for home networks, in a single-hop UAV wireless network setting: the delay between the sending of an IEEE 802.11 packet and the receipt of its corresponding acknowledgement is used as an early indicator of the link quality and as a trigger to adapt (reduce or increase) the video stream' s bitrate. Our real-world flight-tests indicate, that this avoids congestion and can frequently avoid the complete loss of video pictures which happens without adaptation.}, doi = {10.1145/2727040.2727043}, isbn13 = {978-1-4503-3353-5}, keywords = {Video Streaming, Adaptive Streaming, UAVs, UAV Communication}, language = {EN}, location = {Portland, OR, USA}, talktype = {none} } @InProceedings{Cobarzan2015a, author = {Cobarzan, Claudiu and Hudelist, Marco Andrea and Schoeffmann, Klaus and Primus, Manfred Jürgen}, booktitle = {Proceedings of the 21st International Conference on MultiMedia Modelling 2015 (MMM 2015)}, title = {Mobile Image Analysis: Android vs. iOS}, year = {2015}, address = {Berlin, Heidelberg, New York}, editor = {He, Xiangjian and Luo, Suhuai}, month = {jan}, pages = {12}, publisher = {Springer}, language = {EN}, location = {Sydney, Australia}, talkdate = {2015.6.1}, talktype = {registered} } @InProceedings{BeecksEndoRetrieval2015, author = {Beecks, Christian and Schoeffmann, Klaus and Lux, Mathias and Uysal, Merih Seran and Seidl, Thomas}, booktitle = {Proceedings of the IEEE International Symposium on Multimedia 2015 (ISM 2015)}, title = {Endoscopic Video Retrieval: A Signature-based Approach for Linking Endoscopic Images with Video Segments}, year = {2015}, address = {Los Alamitos, CA}, editor = {Del Bimbo, Alberto and Chen, Shu-Ching and Wang, Haohong and Yu, Heather and Zimmermann, Roger}, month = {dec}, pages = {1-6}, publisher = {IEEE}, abstract = {In the field of medical endoscopy more and more surgeons are changing over to record and store videos of their endoscopic procedures, such as surgeries and examinations, in long-term video archives. In order to support surgeons in accessing these endoscopic video archives in a content-based way, we propose a simple yet effective signature-based approach: the Signature Matching Distance based on adaptive-binning feature signatures. The proposed distance-based similarity model facilitates an adaptive representation of the visual properties of endoscopic images and allows for matching these properties efficiently. We conduct an extensive performance analysis with respect to the task of linking specific endoscopic images with video segments and show the high efficacy of our approach. We are able to link more than 88% of the endoscopic images to their corresponding correct video segments, which improves the current state of the art by one order of magnitude.}, language = {EN}, location = {Miami, Florida, USA}, talkdate = {2015.12.14}, talktype = {registered} } @InProceedings{Bacher2015a, author = {Bacher, Florian and Rainer, Benjamin and Hellwagner, Hermann}, booktitle = {Proceedings of IEEE International Conference on Multimedia and Expo Workshops}, title = {Towards Controller-aided Multimedia Dissemination in Named Data Networking}, year = {2015}, address = {Los Alamitos, CA, USA}, editor = {not, available}, month = {jul}, pages = {1--6}, publisher = {IEEE}, series = {ICMEW '15}, abstract = {Software Defined Networking (SDN) and Named Data Networking (NDN) are two topics which have received lots of attention in the networking research community in recent years. While both have emerged independently from each other we believe that their core features can be well aligned to each other. Hence combining both may hold potential benefits for network operators. In this paper we investigate the advantage of having a central SDN controller which is aware of the complete topology of an underlying NDN network. In our approach we use the controller for routing Interests for names unknown to the forwarding elements and to find alternative routes in case of link congestion. Another advantage of SDN is the ability to analyze and control the network on an application-layer component which communicates with the controller. This allows the development of application-aware networks that support the specific needs of the applications that use them. As an example use case we assumed a network whose main purpose is to disseminate multimedia content with Zipf-distributed popularity among users. Having an application layer which knows about content popularity statistics we improve the dissemination of multimedia content by instructing dedicated nodes in the network to prefetch content which is expected to become popular in their geographical region or autonomous system (AS) in the near future. The aim of this approach is to reduce the distance to potential consumers and reduce the load of the core network.}, doi = {10.1109/ICMEW.2015.7169842}, isbn10 = {978­1­4799­7079­7}, keywords = {Information Centric Networking; Named Data Networking; Software Defined Networking; Routing; Forwarding; Caching}, language = {EN}, location = {Turino, Italy}, pdf = {https://www.itec.aau.at/bib/files/07169842.pdf}, talkdate = {2015.07.03}, talktype = {registered} } @InProceedings{lux2014user, author = {Lux, Mathias and Xhura, Desara and Kopper, Alexander}, booktitle = {MultiMedia Modeling}, title = {User Intentions in Digital Photo Production: A Test Data Set}, year = {2014}, address = {Heidelberg, New York}, editor = {Currin, C and Hopfgartner, F and Hurst, W and Johansen, H and Lee, H and O’Connor, N}, month = {jan}, pages = {172--182}, publisher = {Springer International Publishing}, series = {LNCS}, abstract = {Taking a photo with a digital camera or camera phone is a process triggered by a certain motivation. People want for instance to document the progress of a task, others want to preserve a moment of joy. In this contribution we present an openly available dataset with 1,309 photos along with annotations specifying the intentions of the photographers. This data set is the result of a large survey on Flickr and shall provide a common basis for joint research on user intentions in photo production. The survey data was validated using Amazon Mechanical Turk. Besides discussing the process of creating the data set we also present information of the structure and give statistics on the data set.}, language = {EN}, location = {Dublin, Ireland}, talkdate = {2014.01.09}, talktype = {poster} } @InProceedings{ZaharievaSEM2014, author = {Zaharieva, M and Riegler, M and Del Fabro, M}, booktitle = {Working Notes Proceedings of the MediaEval 2014 Workshop}, title = {Multimodal Synchronization of Image Galleries}, year = {2014}, address = {Vol-1263}, editor = {De Natale, F and Mezaris, V and Conci, N}, month = {oct}, pages = {1--2}, publisher = {CEUR-WS}, language = {EN}, location = {Barcelona, Spain}, talkdate = {2014.10.16}, talktype = {registered} } @InProceedings{ZaharievaSED2014, author = {Zaharieva, M and Schopfhauser, M and Del Fabro, M and Zeppelzauer, M}, booktitle = {Working Notes Proceedings of the MediaEval 2014 Workshop}, title = {Clustering and Retrieval of Social Events in Flickr}, year = {2014}, address = {Vol-1263}, editor = {Petkos, G and Papadopoulos, S and Rizzo, G and Mezaris, V and Troncy, R}, month = {oct}, pages = {1--2}, publisher = {CEUR-WS}, language = {EN}, location = {Barcelona, Spain}, talkdate = {2014.10.16}, talktype = {registered} } @InProceedings{XiaoxiaoICME2014, author = {Luo, Xiaoxiao and Xu, Qing and Sbert, Mateu and Schoeffmann, Klaus}, booktitle = {Multimedia and Expo (ICME), 2014 IEEE International Conference on}, title = {Video Navigation on Tablets with Multi-Touch Gestures}, year = {2014}, address = {Los Alamitos, CA, USA}, editor = {Ebrahimi, Touradj and Li, Shipeng and Wang, Houjun and Yang, Jie}, month = {jul}, pages = {6}, publisher = {IEEE}, doi = {10.1109/ICMEW.2014.6890560}, language = {EN}, location = {Chengdu, China}, talkdate = {2014.7.18}, talktype = {registered} } @InProceedings{TimmererBegen2014, author = {Timmerer, Christian and Begen, Ali Cengiz}, booktitle = {Proceedings of the 2014 ACM Multimedia Conference}, title = {Over the Top Content Delivery: State of the Art and Challenges Ahead}, year = {2014}, address = {New York, NY, USA}, editor = {Hua, Kien and Rui, Yong and Steinmetz, Ralf and Hanjalic, Alan and Natsev, Apostol and Zhu, Wenwu}, month = {nov}, pages = {1231--1232}, publisher = {ACM}, abstract = {In this tutorial we present state of the art and challenges ahead in over-the-top content delivery. It particular, the goal of this tutorial is to provide an overview of adaptive media delivery, specifically in the context of HTTP adaptive streaming (HAS) including the recently ratified MPEG-DASH standard. The main focus of the tutorial will be on the common problems in HAS deployments such as client design, QoE optimization, multi-screen and hybrid delivery scenarios, and synchronization issues. For each problem, we will examine proposed solutions along with their pros and cons. In the last part of the tutorial, we will look into the open issues and review the work-in-progress and future research directions.}, doi = {10.1145/2647868.2654849}, isbn13 = {978-1-4503-3063-3}, keywords = {adaptive media streaming, dynamic adaptive streaming over HTTP, MPEG-DASH, over-the-top video video}, language = {EN}, location = {Orlando, FL, USA}, pdf = {https://www.itec.aau.at/bib/files/tut02-timmerer.pdf}, slides = {https://www.itec.aau.at/bib/files/ACM_MM_Tutorial_11_2014.pdf}, talkdate = {2014.11.03}, talktype = {registered} } @InProceedings{Timmerer2014, author = {Timmerer, Christian and Mueller, Christopher and Lederer, Stefan}, booktitle = {2014 NAB Broadcast Engineering Conference Proceedings \& CD}, title = {Adaptive Media Streaming over Emerging Protocols}, year = {2014}, address = {Washington DC, USA}, editor = {available, not}, month = {apr}, pages = {4}, publisher = {National Association of Broadcasters (NAB)}, abstract = {The emerging MPEG standard Dynamic Adaptive Streaming over HTTP (MPEG-DASH) is designed for media delivery over the top of existing infrastructures and enables smooth multimedia streaming towards heterogeneous devices including both wired and wireless environments. The MPEG-DASH standard was designed to work with HTTP-URLs but mandates neither the actual version nor which underlying protocols to be used. This paper will provide a detailed introduction into emerging protocols (HTTP/2.0 and beyond) to be used in the context of adaptive media streaming, specifically DASH.}, language = {EN}, location = {Las Vegas, NV, USA}, pdf = {https://www.itec.aau.at/bib/files/TimmererC012314_revised.pdf}, slides = {https://www.itec.aau.at/bib/files/NAB2014-BEC.pdf}, talkdate = {2014.04.07}, talktype = {registered} } @InProceedings{Taschwer2014a, author = {Taschwer, Mario}, booktitle = {Proceedings of the ACM International Conference on Multimedia}, title = {Medical Case Retrieval}, year = {2014}, address = {New York, NY, USA}, editor = {n/a, n/a}, month = {nov}, pages = {639--642}, publisher = {ACM}, series = {MM '14}, doi = {10.1145/2647868.2654856}, isbn13 = {978-1-4503-3063-3}, keywords = {biomedical information retrieval, ImageCLEF medical tasks, multimodal information retrieval}, language = {EN}, location = {Orlando, Florida, USA}, pdf = {https://www.itec.aau.at/bib/files/Taschwer_ACM_MM_2014.pdf}, slides = {https://www.itec.aau.at/bib/files/Taschwer_ACM_MM_2014_slides.pdf}, talkdate = {2014.11.05}, talktype = {registered} } @InProceedings{SchoeffmannMM2014, author = {Schoeffmann, Klaus}, booktitle = {Proceedings of the ACM International Conference on Multimedia 2014 (ACM MM 2014)}, title = {The Stack-of-Rings Interface for Large-Scale Image Browsing on Mobile Touch Devices}, year = {2014}, address = {New York, NY, USA}, editor = {Hua, Kien and Rui, Yong and Steinmetz, Ralf}, month = {nov}, pages = {1097-1100}, publisher = {ACM}, language = {EN}, location = {Orlando, FL, USA}, talkdate = {2014.11.4}, talktype = {poster} } @InProceedings{SchoeffmannICME2014a, author = {Schoeffmann, Klaus and Chromik, Kevin and Böszörmenyi, Laszlo}, booktitle = {Multimedia and Expo Workshops (ICMEW), 2014 IEEE International Conference on}, title = {Video Navigation on Tablets with Multi-Touch Gestures}, year = {2014}, address = {Los Alamitos, CA, USA}, editor = {Mei, Tao and Stiefelhagen, Rainer and Tian, Qi}, month = {jul}, pages = {6}, publisher = {IEEE}, doi = {10.1109/ICMEW.2014.6890560}, language = {EN}, location = {Chengdu, China}, talkdate = {2014.7.18}, talktype = {registered} } @InProceedings{RassRainer2014b, author = {Rass, Stefan and Rainer, Benjamin and Matthias, Vavti and Göllner, Johannes and Peer, Andreas and Schauer, Stefan}, booktitle = {International Conference on Software-Defined and Virtualized Future Wireless Networks}, title = {Secure Communication over Software-Defined Networks}, year = {2014}, address = {R, I}, editor = {n,A}, month = {oct}, pages = {0-0}, publisher = {Springer}, keywords = {Risk management; Network-level security and protection; Network communications; Privacy; Security}, language = {EN}, location = {Rome, Italy}, talkdate = {2014.10.28}, talktype = {registered} } @InProceedings{RassRainer2014a, author = {Rass, Stefan and Rainer, Benjamin}, booktitle = {Conference on Decision and Game Theory for Security}, title = {Numerical Computation of Multi-Goal Security Strategies}, year = {2014}, address = {LA, CA}, editor = {O'Conner, Lisa}, month = {nov}, pages = {0-0}, publisher = {Springer}, keywords = {Risk management; Network-level security and protection; Network communications; Privacy; Security}, language = {EN}, location = {Los Angeles, California}, talkdate = {2014.11.06}, talktype = {registered} } @InProceedings{Rainer2014_NOMS_QCMAN, author = {Rainer, Benjamin and Timmerer, Christian}, booktitle = {In Proceedings of the IEEE Network Operations and Management Symposium (IEEE NOMS 2014)}, title = {A Subjective Evaluation using Crowdsourcing of Adaptive Media Playout utilizing Audio-Visual Content Features}, year = {2014}, address = {Los Alamitos, CA, USA}, editor = {Lutfiyya, Hanan and Cholda, Piotr}, month = {may}, pages = {0--0}, publisher = {IEEE}, abstract = {Synchronizing multimedia playback among geographically distributed clients is a challenging task and is referred to as Inter-Destination Media Synchronization (IDMS). In this paper we discuss the uses cases of IDMS as identified within the SocialSensor Project and based on these use cases we derive a novel Adaptive Media Playout (AMP) scheme which aims on carrying out the process of synchronizing the media playback at the clients to a given synchronization point. We propose how visual and acoustic features can be used to achieve a QoE-aware and context-aware AMP scheme.}, isbn13 = {-}, keywords = {Adaptive Media Playout, Inter-Destination Media Synchronization, Social TV}, language = {EN}, location = {Krakow, Poland}, pdf = {https://www.itec.aau.at/bib/files/qcman-final.pdf}, talkdate = {2014.05.09}, talktype = {registered}, url = {http://www.qomex2013.org} } @InProceedings{Rainer2014_Mobiquituous, author = {Klusch, Matthais and Kapahnke, Patrick and Cao, Xiaoqi and Rainer, Benjamin and Timmerer, Christian and Mangold, Stefan}, booktitle = {Proceedings of the 11th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services}, title = {MyMedia: Mobile Semantic Peer-to-Peer Video Search and Live Streaming}, year = {2014}, address = {New York, NY, USA}, editor = {Youssef, Moustafa}, month = {dec}, pages = {10}, publisher = {ACM}, abstract = {Mobile peer-to-peer (P2P) computing with applications such as for video on demand, file sharing, and video conferencing is gaining momentum based on new standards and technologies such as IETF PPSP, WiFi-Direct and BitTorrent live streaming. In this paper, we describe the mobile system MyMedia, that allows users to search, share and experience videos and live recordings using P2P and at the best quality possible with respect to available network capacity. In particular, the MyMedia system features a high-precision semantic P2P search and dynamic network-adaptive P2P live streaming of MPEG videos over HTTP based on the ISO/IEC standard MPEG-DASH from mobile to mobile devices in unstructured wireless P2P networks. These features have been integrated in the mobile application TIFF EventLive of the 54th Thessaloniki international film festival. The evaluation of their performance and device energy consumption, and a first user evaluation at the festival showed that the MyMedia system is suitable and accepted by users for its purpose in practice. The MyMedia system is available as open-source software for the Android operating system.}, isbn13 = {-}, language = {EN}, location = {London, Great Britain}, pdf = {https://www.itec.aau.at/bib/files/mobi_mymedia_paper.pdf}, talkdate = {2014.12.05}, talktype = {registered}, url = {http://mobiquitous.org/2014} } @InProceedings{Rainer2014_LP2P, author = {Rainer, Benjamin and Timmerer, Christian and Kapahnke, Patrick and Klusch, Matthias}, booktitle = {Proceedings of the 10th IEEE Consumer Communication and Networking Conference (CCNC)}, title = {Real-time Multimedia Streaming in Unstructured Peer-to-Peer Networks}, year = {2014}, address = {Las Vegas, U.S.A}, editor = {not, available}, month = {jan}, pages = {n.a.}, publisher = {IEEE Consumer Communication and Networking Conference}, abstract = {With the introduction of social networks like Facebook, Google+, and Twitter, the ways of sharing impressions of events has changed. We try to go a step further than social networks do. We offer the possibility to share events live with friends and colleagues. Our approach is based on semantic search in unstructured peer-to-peer (P2P) networks for querying content in mobile ad hoc networks and dynamic adaptive streaming over HTTP for the actual delivery of the real-time media impressions.}, language = {EN}, location = {Planet Hollywood, Las Vegas}, pdf = {https://www.itec.aau.at/bib/files/1999764446.pdf}, talkdate = {2014.01.11}, talktype = {poster} } @InProceedings{Rainer2014_ACM_MM_SELFORG, author = {Rainer, Benjamin and Timmerer, Christian}, booktitle = {Proceedings of the 22st ACM International Conference on Multimedia}, title = {Self-Organized Inter-Destination Multimedia Synchronization For Adaptive Media Streaming}, year = {2014}, address = {New York, NY, USA}, editor = {ACM,}, month = {nov}, pages = {10}, publisher = {ACM}, abstract = {Social networks have become pervasive and have changed the way of social interaction. The traditional TV experience drifts from an event tied to a certain place with the family or friends to a location-independent and distributed social experience. Additionally, more and more video on-demand services adopt a pull-based streaming approach. In order to provide a synchronized and distributed TV experience we introduce a self-organized Inter-Destination Multimedia Synchronization (IDMS) framework for adaptive media streaming. In particular, we extend the principles of IDMS to adaptive media streaming over HTTP (i.e., MPEG-DASH) and enable a synchronized multimedia playback among geographically distributed clients. Therefore, we introduce session management to MPEG-DASH and for negotiating on a reference playback timestamp among the participating peers in an IDMS session we propose a distributed control scheme. We evaluate our proposed scheme with respect to scalability and time required for negotiating on the reference playback timestamp. Furthermore, we investigate how to compensate the identified asynchronism by using adaptive media playout with respect to the Quality of Experience (QoE). Therefore, we define a temporal distortion measure for audio and video which allows us to model the impact of playback rate variations on the QoE. This measure is evaluated by conducting a subjective quality assessment using crowdsourcing.}, isbn13 = {-}, keywords = {Inter-Destination Multimedia Synchronization, Adaptive Media Streaming, Self-Organization, Quality of Experience, Dynamic Adaptive Streaming over HTTP}, language = {EN}, location = {Orlando, Florida}, pdf = {https://www.itec.aau.at/bib/files/acmm14.pdf}, talkdate = {2014.11.03}, talktype = {registered}, url = {http://acmmm.org/2014/} } @InProceedings{Rain1412:VNext, title = {Quality of Experience of Web-based Adaptive HTTP Streaming Clients in Real-World Environments using Crowdsourcing}, author = {Rainer, Benjamin and Timmerer, Christian}, booktitle = {First International Workshop on VideoNext: Design, Quality and Deployment of Adaptive Video Streaming}, year = {2014}, address = {Australia, Sydney}, editor = {N, N}, month = {dec}, pages = {1-6}, publisher = {ACM}, keywords = {Dynamic Adaptive Streaming over HTTP; Crowdsourcing; Subjective Quality Assessment; Quality of Experience; QoE; DASH; MPEG}, language = {EN}, location = {Singapore}, pdf = {https://www.itec.aau.at/bib/files/videoNextDASH.pdf}, talkdate = {2014.12.02}, talktype = {registered} } @InProceedings{Rain1409:Quality, author = {Rainer, Benjamin and Timmerer, Christian}, booktitle = {Sixth International Workshop on Quality of Multimedia Experience (QoMEX 2014)}, title = {A Quality of Experience Model for Adaptive Media Playout}, year = {2014}, address = {Singapore, Singapore}, editor = {Winkler, Stefan}, month = {sep}, pages = {1-4}, publisher = {IEEE}, abstract = {In the past decade Adaptive Media Playout (AMP) has been intensively studied with respect to the detection of when to increase or decrease the playback rate in order to maintain a certain buffer fill state. In this paper we subjectively assess the QoE of AMP with respect to non-periodically and randomly selected content sections of a video sequence by us- ing crowdsourcing. Furthermore, we introduce features that allow to quantify the distortion for audio and video that are caused by increasing or decreasing the playback rate. With these preliminaries we study the correlation between the introduced features and the subjectively assessed QoE. Therefore, we derive a utility model that allows to estimate the QoE with the introduced features. We instantiate and validate the model by the use of the data gathered by the conducted study.}, keywords = {Adaptive Media Playout; Inter-Destination Media Synchronization; Crowdsourcing; Subjective Quality Assessment; Quality of Experience}, language = {EN}, location = {Singapore}, pdf = {https://www.itec.aau.at/bib/files/QoMEX-paper_Rainer.pdf}, talkdate = {2014.09.19}, talktype = {registered} } @InProceedings{Raffelsberger2014, title = {Combined Mobile Ad-Hoc and Delay/Disruption-Tolerant Routing}, author = {Raffelsberger, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the 13th International Conference on Ad-hoc, Mobile, and Wireless Networks (ADHOC-NOW '14)}, year = {2014}, address = {Berlin Heidelberg}, editor = {Guo, Song and Manzoni, Pietro and Lloret, Jaime and Ruehrup, Stefan}, month = {jun}, pages = {1-14}, publisher = {Springer}, series = {Lecture Notes in Computer Science (LNCS 8487)}, volume = {8487}, isbn13 = {978-3-319-07424-5}, keywords = {mobile ad-hoc networks; disruption-tolerant networks; routing; simulation}, language = {EN}, location = {Benidorm, Spain}, pdf = {https://www.itec.aau.at/bib/files/cr-adhocnow-authorver2.pdf}, talkdate = {2014.06.24}, talktype = {registered} } @InProceedings{Primus_ACM2014, author = {Primus, Manfred Jürgen}, booktitle = {Proceedings of the ACM International Conference on Multimedia}, title = {Segmentation and Indexing of Endoscopic Videos}, year = {2014}, address = {New York, NY, USA}, editor = {n/a, n/a}, month = {nov}, pages = {659--662}, publisher = {ACM}, series = {MM '14}, abstract = {Over the last few years it has become common to archive video recordings of endoscopic surgeries. These videos are of high value for medics, junior doctors, patients and hospital management but currently they are used rarely or not at all. Each day tens to hundreds of hours of new videos are added to archives without metadata that would support content-based search. In order to fully utilize these videos it is necessary to analyze the content of the recordings. Endoscopic videos are in some aspects fundamentally different to other types of videos. Therefore, pre-existing content-based analysis methods must be tested for their ability to operate with this kind of video and, if required, they must be adopted or new methods must be found. Especially, we address video segmentation and indexing in this work. We present our preliminary work and ideas for future work to add content-based information to endoscopic videos.}, language = {EN}, location = {Orlando, Florida, USA}, talkdate = {2014.11.05}, talktype = {registered} } @InProceedings{Posch2014b, author = {Posch, Daniel and Kreuzberger, Christian and Rainer, Benjamin and Hellwagner, Hermann}, booktitle = {Proceedings of the 10th International Conference on Emerging Networking Experiments and Technologies, VideoNext Workshop}, title = {Using In-Network Adaptation to Tackle Inefficiencies Caused by DASH in Information-Centric Networks}, year = {2014}, address = {New York, NY, USA}, editor = {Dixon, Colin}, month = {dec}, pages = {1-6}, publisher = {ACM Digital Library}, abstract = {The consumption of audio-visual content is the most dominant traffic source in today's Internet. Novel architectural approaches, such as Information-Centric Networking (ICN), are developed to support efficient multimedia dissemination. As ICN and MPEG-DASH have several concepts in common, recent proposals consider a fusion of both technologies. However, MPEG-DASH relies on pure client-driven adaptation. This often rather selfish adaptation strategy inhibits benefits gained from ICN's inherent caching and multi-path transmission capabilities. In order to overcome this challenge, the contribution of this work is the integration of in-network adaptation (INA) in ICN. We illustrate that INA can be realized despite ICN's content-based security model. Our proposal rests on scalable content, which enables INA without management and transmission overhead.}, keywords = {Information-Centric Networking; In-Network Adaptation; Adaptive Streaming; Multimedia Dissemination}, language = {EN}, location = {Sydney, Australia}, pdf = {https://www.itec.aau.at/bib/files/video01fp.pdf}, talkdate = {2014.12.02}, talktype = {registered} } @InProceedings{Posch2014, author = {Posch, Daniel and Kreuzberger, Christian and Rainer, Benjamin and Hellwagner, Hermann}, booktitle = {Proceedings of the 1st ACM Conference on Information-Centric Networking}, title = {Client Starvation: A Shortcoming of Client-driven Adaptive Streaming in Named Data Networking}, year = {2014}, address = {New York, NY, USA}, editor = {Mendes, Paulo}, month = {sep}, pages = {1-2}, publisher = {ACM Digital Library}, abstract = {Information-centric Networking (ICN) as a potential Future Internet architecture has to efficiently support the consumption of multimedia content. Recent proposals consider the reuse of MPEG-DASH to provide adaptive streaming in ICN. Due to the fact that MPEG-DASH relies on pure client-driven adaptation, it encounters difficulties dealing with ICN's inherent caching and multi-path transmission. By conducting simulations using the concrete ICN approach Named Data Networking (NDN), we show that pure client-driven adaptation leads to shortcomings. Furthermore, we propose to use in-network adaptation based on scalable content for overcoming these shortcomings in NDN.}, doi = {10.1145/2660129.2660162}, keywords = {Information-centric Networking; Adaptive Streaming}, language = {EN}, location = {Paris, Frankreich}, pdf = {https://www.itec.aau.at/bib/files/icn14_final.pdf}, talkdate = {2014.09.26}, talktype = {poster}, url = {http://dx.doi.org/10.1145/2660129.2660162} } @InProceedings{Muenzer2014, author = {Münzer, Bernd and Schoeffmann, Klaus and Böszörmenyi, Laszlo and Smulders, Johannes Franciscus and Jakimowicz, Jack J}, booktitle = {27th International Symposium on Computer-Based Medical Systems (CBMS'14)}, title = {Investigation of the Impact of Compression on the Perceptional Quality of Laparoscopic Videos}, year = {2014}, address = {New York City, USA}, editor = {Krol, Marina}, month = {may}, pages = {153-158}, publisher = {IEEE}, language = {EN}, location = {New York City, USA}, talkdate = {2014.05.27}, talktype = {registered} } @InProceedings{Iscram2014a, author = {Al-Akkad, Amro and Raffelsberger, Christian and Boden, Alexander and Ramirez, Leonardo and Zimmermann, Andreas}, booktitle = {Proceedings of the 11th International Conference on Information Systems for Crisis Response and Management (ISCRAM '14)}, title = {Tweeting 'When Online is Off'? Opportunistically Creating Mobile Ad-hoc Networks in Response to Disrupted Infrastructure}, year = {2014}, address = {University Park, Pennsylvania, USA}, editor = {Hiltz, Star Roxanne and Pfaff, Mark S and Plotnick, Linda and Shih, Patrick C}, month = {may}, pages = {657-666}, publisher = {The Pennsylvania State University, USA}, isbn13 = {978-0-692-21194-6}, language = {EN}, location = {University Park, Pennsylvania, USA}, pdf = {https://www.itec.aau.at/bib/files/iscram2014-p35.pdf}, talkdate = {2014.05.21}, talktype = {registered} } @InProceedings{Iscram2014, author = {Al-Akkad, Amro and Raffelsberger, Christian}, booktitle = {Proceedings of the 11th International Conference on Information Systems for Crisis Response and Management (ISCRAM '14)}, title = {How do I get this App? A Discourse on Distributing Mobile Applications Despite Disrupted Infrastructure}, year = {2014}, address = {University Park, Pennsylvania, USA}, editor = {Hiltz, Star Roxanne and Pfaff, Mark S and Plotnick, Linda and Shih, Patrick C}, month = {may}, pages = {560-564}, publisher = {The Pennsylvania State University, USA}, isbn13 = {978-0-692-21194-6}, language = {EN}, location = {University Park, Pennsylvania, USA}, pdf = {https://www.itec.aau.at/bib/files/iscram2014-p155.pdf}, talkdate = {2014.05.21}, talktype = {registered} } @InProceedings{Hudelist:2014:OPM:2578726.2578798, title = {OpenCV Performance Measurements on Mobile Devices}, author = {Hudelist, Marco Andrea and Cob\^{a}rzan, Claudiu and Schoeffmann, Klaus}, booktitle = {Proceedings of International Conference on Multimedia Retrieval}, year = {2014}, address = {New York, NY, USA}, editor = {Jose, Joemon and Van Rijsbergen, Keith}, month = {apr}, pages = {479:479--479:482}, publisher = {ACM}, series = {ICMR '14}, doi = {10.1145/2578726.2578798}, keywords = {Mobile devices, OpenCV, performance evaluation}, language = {EN}, location = {Glasgow, United Kingdom}, talkdate = {2014.04.02}, talktype = {poster}, url = {http://doi.acm.org/10.1145/2578726.2578798} } @InProceedings{Hossfeld2014, author = {Ho{\ss}feld, Tobias and Hirth, Matthias and Korshunov, Pavel and Hanhart, Philippe and Gardlo, Bruno and Keimel, Christian and Timmerer, Christian}, booktitle = {2014 IEEE International Workshop on Multimedia Signal Processing (MMSP 2014)}, title = {Survey of Web-based Crowdsourcing Frameworks for Subjective Quality Assessment}, year = {2014}, address = {Piscataway, N.J. 08854, U.S.A.}, editor = {Rahardja, Susanto and Zhang, Zhengyou and Pereira, Fernando and Loui, Alexander}, month = {sep}, pages = {6}, publisher = {IEEE}, abstract = {The popularity of the crowdsourcing for performing various tasks online increased significantly in the past few years. The low cost and flexibility of crowdsourcing, in particular, attracted researchers in the field of subjective multimedia evalua- tions and Quality of Experience (QoE). Since online assessment of multimedia content is challenging, several dedicated frameworks were created to aid in the designing of the tests, including the support of the testing methodologies like ACR, DCR, and PC, setting up the tasks, training sessions, screening of the subjects, and storage of the resulted data. In this paper, we focus on the web-based frameworks for multimedia quality assessments that support commonly used crowdsourcing platforms such as Amazon Mechanical Turk and Microworkers. We provide a detailed overview of the crowdsourcing frameworks and evaluate them to aid researchers in the field of QoE assessment in the selection of frameworks and crowdsourcing platforms that are adequate for their experiments.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/PDF_check_PID3271407.pdf}, talktype = {none} } @InProceedings{CobarzanVBS2014, author = {Cobarzan, Claudiu and Hudelist, Marco Andrea and Del Fabro, Manfred}, booktitle = {MultiMedia Modeling, 20th Anniversary International Conference}, title = {Content-Based Video Browsing with Collaborating Mobile Clients}, year = {2014}, address = {Berlin, Germany}, editor = {Gurrin, C and Hopfgartner, F and Hurst, W and Johansen, H and Lee, H and O'Connor, N}, month = {jan}, pages = {402-406}, publisher = {Springer}, language = {EN}, location = {Dublin, Ireland}, talkdate = {2014.01.07}, talktype = {poster} } @InProceedings{CobarzanMMM2014, author = {Cobarzan, Claudiu and Schoeffmann, Klaus}, booktitle = {Proceedings of the 20th International Conference on MultiMedia Modeling (MMM2014)}, title = {How do Users Search with Basic HTML5 Video Players?}, year = {2014}, address = {Berlin Heidelberg}, editor = {O'Connor,Noel and Hurst,Wolfgang and Lee,Hyowon and Gurrin,Cathal}, month = {jan}, pages = {12}, publisher = {Springer}, language = {EN}, location = {Dublin,Ireland}, talkdate = {2014.01.08}, talktype = {registered} } @InProceedings{Zeppelzauer_MediaEval2013, author = {Zeppelzauer, Matthias and Zaharieva, Maia and Del Fabro, Manfred}, booktitle = {MediaEval 2013 - Multimedia Benchmark Workshop}, title = {Unsupervised Clustering of Social Events}, year = {2013}, address = {Aachen, Germany}, editor = {Larson, Martha and Anguera, Xavier and Reuter, Timo and Jones, Gareth and Ionescu, Bogdan and Schedl, Markus and Piatrik, Tomas and Hauff, Claudia and Soleymani, Mohammad}, month = {oct}, pages = {1--2}, publisher = {CEUR-WS.org/Vol-1043}, language = {EN}, location = {Barcelona, Spain}, pdf = {https://www.itec.aau.at/bib/files/mediaeval2013_submission_37.pdf}, talkdate = {2013.10.19}, talktype = {poster} } @InProceedings{Waltl2013_QoMEX2013_4DPlayer, author = {Waltl, Markus and Rainer, Benjamin and Lederer, Stefan and Timmerer, Christian and Gassner, Katharina and Terlutter, Ralf}, booktitle = {Proceedings of the 5th International Workshop on Quality of Multimedia Experience (QoMEX'13)}, title = {A 4D Multimedia Player enabling Sensory Experience}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Timmerer, Christian and Le Callet, Patrick and Varela, Martin and Winkler, Stefan and Falk, Tiago H}, month = {jul}, pages = {126-127}, publisher = {IEEE}, abstract = {Lately, 3D is gaining momentum in cinemas and home environments. However, 2D and 3D video content only stimulates senses like hearing and seeing. In this paper we focus on a more enhanced level of entertainment by presenting a 4D multimedia player and a corresponding demonstration setup, which stimulates further senses such as haptics using the MPEG-V: Media Context and Control standard. The presented demonstration setup uses stereoscopic 3D and sensory devices, i.e., fans, vibration panels and lights. The combination of conventional 3D content with tailored sensory effects allows us to further enhance the viewing experience of the users.}, isbn13 = {-}, keywords = {3D, 4D, Sensory Effects, Sensory Experience, MPEG-V}, language = {EN}, location = {Klagenfurt am Wörthersee, Austria}, pdf = {https://www.itec.aau.at/bib/files/QoMEX2013_4DPlayer.pdf}, talkdate = {2013.07.04}, talktype = {poster}, url = {http://www.qomex2013.org} } @InProceedings{Timmerer2013_QoMEX2013_UtilityModel, author = {Timmerer, Christian and Rainer, Benjamin and Markus, Waltl}, booktitle = {Proceedings of the 5th International Workshop on Quality of Multimedia Experience (QoMEX'13)}, title = {A Utility Model for Sensory Experience}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Timmerer, Christian and Le Callet, Patrick and Varela, Martin and Winkler, Stefan and Falk, Tiago H}, month = {jul}, pages = {224-229}, publisher = {IEEE}, abstract = {Enriching multimedia with additional effects such as olfaction, light, wind, or vibration is gaining more and more momentum in both research and industry. Hence, there is the need to determine the influence of individual effects on the Quality of Experience (QoE). In this paper, we present a subjective quality assessment using the MPEG-V standard to annotate video sequences with individual sensory effects (i.e., wind, light, and vibration) and all combinations thereof. Based on the results we derive a utility model for sensory experience that accounts for the assessed sensory effects. Finally, we provide an example instantiation of the utility model and validate it against current and past results of our subjective quality assessments conducted so far.}, isbn13 = {-}, keywords = {Quality of Multimedia Experience, Sensory Effects, MPEG-V, Sensory Experience, Utility Model}, language = {EN}, location = {Klagenfurt am Wörthersee, Austria}, pdf = {https://www.itec.aau.at/bib/files/QoMEX2013_UtilityModel.pdf}, talkdate = {2013.07.05}, talktype = {registered}, url = {http://www.qomex2013.org} } @InProceedings{Taschwer2013, author = {Taschwer, Mario}, booktitle = {{CLEF} 2013 Evaluation Labs and Workshop, Online Working Notes}, title = {Text-Based Medical Case Retrieval Using {MeSH} Ontology}, year = {2013}, address = {Padua, Italy}, editor = {Forner, Pamela and Navigli, Roberto and Tufis, Dan}, month = {sep}, pages = {5}, publisher = {CLEF Initiative}, abstract = {Our approach to the ImageCLEF medical case retrieval task consists of text-only retrieval combined with utilizing the Medical Subject Headings (MeSH) ontology. MeSH terms extracted from the query are used for query expansion or query term weighting. MeSH annotations of documents available from PubMed Central are added to the corpus. Retrieval results improve slightly upon full-text retrieval.}, isbn13 = {978-88-904810-5-5}, language = {EN}, location = {Valencia, Spain}, pdf = {https://www.itec.aau.at/bib/files/aau_mcr_mesh.pdf}, slides = {https://www.itec.aau.at/bib/files/poster_clef2013.pdf}, talkdate = {2013.09.24}, talktype = {poster}, url = {http://www.clef-initiative.eu/documents/71612/4b93fc08-a8fa-4985-873d-c2c18bd4cd3d} } @InProceedings{Sieber2013, author = {Sieber, Christian and Ho{\ss}feld, Tobias and Zinner, Thomas and Tran-Gia, Phuoc and Timmerer, Christian}, booktitle = {Integrated Network Management (IM 2013), 2013 IFIP/IEEE International Symposium on}, title = {Implementation and User-centric Comparison of a Novel Adaptation Logic for DASH with SVC}, year = {2013}, address = {New York, NY, USA}, editor = {De Turck, Filip and Diao, Yixin and Hong, Choong Seon and Medhi, Deep and Sadre, Ramin}, month = {may}, pages = {1318-1323}, publisher = {IEEE Communications Society}, abstract = {The MPEG-DASH standard allows the client-centric access to different representations of video content via the HTTP protocol. The client can flexibly switch between different qualities, i.e., different bit rates and thus avoid waiting times during the video playback due to empty playback buffers. However, quality switches and the playback of lower qualities is perceived by the user which may reduce the Quality of Experience (QoE). Therefore, novel algorithms are required which manage the streaming behavior with respect to the user's requirements and which do not waste network resources. As indicated by recent studies, scalable video coding (SVC) may use the current network and content distribution infrastructure in a more efficient way than with single layer codecs. The contribution of this paper is the design and the implementation of a novel DASH/SVC streaming algorithm. By means of measurements in a test-bed, its performance and benefits are evaluated and compared to existing algorithms from an user-centric view point with objective performance metrics. Our findings show that the proposed algorithm outperforms other DASH mechanisms in terms of video quality, low switching frequency and usage of the available resources in a realistic mobile network scenario. This is a first step towards true QoE management of video streaming in the Internet with DASH and SVC.}, isbn13 = {978-1-4673-5229-1}, keywords = {quality of experience, mpeg-dash, scalable video coding, adaptive media streaming}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/06573184.pdf}, talktype = {none} } @InProceedings{SchoeffmannAMR2011, author = {Schoeffmann, Klaus and Ahlström, David and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the International Workshop on Adaptive Multimedia Retrieval (AMR2011), LNCS 7836}, title = {A User Study of Visual Search Performance of Interactive 2D and 3D Storyboards}, year = {2013}, address = {Barcelona, Spain}, editor = {Detyniecki, M and Garcia-Serrano, A and Nürnberger, A and Stober, S}, month = {jul}, pages = {18-32}, publisher = {Springer}, language = {EN}, location = {Berlin Heidelberg}, talkdate = {2011.7.15}, talktype = {registered} } @InProceedings{Schoeffmann2013, author = {Schoeffmann, Klaus and Cobarzan, Claudiu}, booktitle = {Proceedings of 2013 IEEE International Conference on Multimedia and Expo Workshops (ICME)}, title = {An evaluation of interactive search with modern video players}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Hua,Xian-Sheng and Cheng,Irene and Basu,Anup and Ling,Nam and Panchanathan,Sethuraman}, month = {jan}, pages = {1-4}, publisher = {IEEE}, abstract = {The navigation features of video players are often used for interactive search in videos, when users want to find a specific segment. Especially non-experts make use of these navigation facilities because they typically do not have any video retrieval tool at hand and - maybe more important - the navigation features of video players are very easy to use. However, in order to design professional video browsing tools that allow for better search performance but still provide ease of use, we need to know how users search with common video players. Therefore, we analyze logging data from a user study with 17 participants that performed Known Item Search tasks with an HTML5 video player. We classify search behavior by type of interaction and speed of interactive search and discuss what we can learn for the design and development of professional video search tools.}, doi = {10.1109/ICMEW.2013.6618282}, keywords = {hypermedia markup languages;interactive systems;search problems;video retrieval;video signal processing;HTML5 video player;interactive search;interactive search evaluation;known item search tasks;modern video players;navigation facilities;search behavior;video browsing tools;video retrieval tool;Browsers;Computers;Multimedia communication;Navigation;Search problems;Streaming media;Switches;HCI;Interactive Search;Video Browsing}, language = {EN}, location = {San Jose, CA, USA}, talkdate = {2013.07.15}, talktype = {registered} } @InProceedings{Riegler2013, author = {Riegler, M and Lux, Mathias and Kofler, Ch}, booktitle = {MediaEval 2013 - Multimedia Benchmark Workshop}, title = {Frame the Crowd: Global Visual Features Labeling boosted with Crowdsourcing Information}, year = {2013}, address = {Barcelona, Spain}, editor = {Larson, M and Anguera, X and Reuter, T and Jones, G and Ionescu, B and Schedl, M and Piatrik, T and Hauff, C and Soleymani, M}, month = {October}, pages = {--}, publisher = {CEUR Workshop Proceedings}, abstract = {In this paper we present our approach to the Crowd Sourcing Task of the MediaEval 2013 Benchmark [2] using transfer learning and visual features. For the visual features we adopt an existing approach for search based classification using content based image retrieval on global features with feature selection and feature combination to boost the performance. Our approach gives a baseline evaluation indicating the usefulness of global visual features, hashing and search-based classification.}, edition = {Vol 1043}, language = {EN}, talktype = {none}, url = {http://ceur-ws.org/Vol-1043/} } @InProceedings{Rass2013a, title = {A Network Modeling and Analysis Tool for Perfectly Secure Communication}, author = {Rass, Stefan and Rainer, Benjamin and Vavti, Matthias and Schauer, Stefan}, booktitle = {The 27th IEEE International Conference on Advanced Information Networking and Applications (AINA-2013)}, year = {2013}, address = {BARCELONA, Spain}, editor = {O'Conner, Lisa}, month = {mar}, pages = {267-275}, publisher = {IEEE}, abstract = {Secure communication is often based on encryption thus hinges on (public-key) infrastructures that handle all the key-management. This inevitably requires human intervention, thus creating a rather vulnerable point in the system. So it appears desirable to automate key-management tasks to the widest possible extent. In this work, we report on a software implementation of secure multipath transmission. Our system takes a network infrastructure model as input and determines the maximal achievable security for a communication between a chosen sender and receiver, while handling all key-management transparently for the user. The security is information-theoretic, and unlike public-key or symmetric cryptography does neither hinge on computational intractability nor empirical evidence. More importantly, security can be measured in quantitative terms, thus making the results useful in enterprise risk management. Our software computes the risk for a given transmission under multipath transmission and generates simple OmNet++ models to demonstrate the channel construction as practically doable and to measure the additional network overhead. This is for a-priori decision-support and practical guidance for an installation of secure multipath transmission as a high-security transmission service within the enterprise network.}, keywords = {Risk management; Network-level security and protection; Network communications; Privacy; Security}, language = {EN}, location = {BARCELONA, Spain}, talkdate = {2013.03.25}, talktype = {registered} } @InProceedings{Rainer_2013_PQS, author = {Rainer, Benjamin and Timmerer, Christian and Waltl, Markus}, booktitle = {4th International Workshop on Perceptual Quality of Systems 2013 (PQS 2013)}, title = {Recommendations for the Subjective Evaluation of Sensory Experience}, year = {2013}, address = {Vienna, Austria}, editor = {Schatz, Raimund}, month = {sep}, pages = {1-6}, publisher = {IEEE}, abstract = {Selecting and adopting the appropriate assessment method for conducting subjective quality assessments is a challenging task. The method decides whether the assessment is successful in delivering the correct answers to previously set up hypotheses. Therefore, in this paper we provide recommendations on test methods used in the domain of Sensory Experience. The proposed test methods comprise single stimulus and double stimulus methods. These test methods were used in previous studies and are presented in combination with the results of the subjective quality assessments with which they were used. Furthermore, we briefly outline our test setup, test design, and test content for assessing Sensory Experience which have been validated through conducted assessments.}, keywords = {Subjective Evaluation Methods; Sensory Experience; Recommendations}, language = {EN}, location = {Vienna, Austria}, talkdate = {2013.09.03}, talktype = {registered} } @InProceedings{Rainer2013_QoMEX2013_MediaPlayout, author = {Rainer, Benjamin and Timmerer, Christian}, booktitle = {Proceedings of the 5th International Workshop on Quality of Multimedia Experience (QoMEX'13)}, title = {Adaptive Media Playout for Inter-Destination Media Synchronization}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Timmerer, Christian and Le Callet, Patrick and Varela, Martin and Winkler, Stefan and Falk, Tiago H}, month = {jul}, pages = {44-45}, publisher = {IEEE}, abstract = {Synchronizing multimedia playback among geographically distributed clients is a challenging task and is referred to as Inter-Destination Media Synchronization (IDMS). In this paper we discuss the uses cases of IDMS as identified within the SocialSensor Project and based on these use cases we derive a novel Adaptive Media Playout (AMP) scheme which aims on carrying out the process of synchronizing the media playback at the clients to a given synchronization point. We propose how visual and acoustic features can be used to achieve a QoE-aware and context-aware AMP scheme.}, isbn13 = {-}, keywords = {Adaptive Media Playout, Inter-Destination Media Synchronization, Social TV}, language = {EN}, location = {Klagenfurt am Wörthersee, Austria}, pdf = {https://www.itec.aau.at/bib/files/QoMEX2013_MediaPlayout.pdf}, talkdate = {2013.07.03}, talktype = {poster}, url = {http://www.qomex2013.org} } @InProceedings{Rainer2013_QoMEX2013_EvalPlatform, author = {Rainer, Benjamin and Waltl, Markus and Timmerer, Christian}, booktitle = {Proceedings of the 5th International Workshop on Quality of Multimedia Experience (QoMEX'13)}, title = {A Web based Subjective Evaluation Platform}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Timmerer, Christian and Le Callet, Patrick and Varela, Martin and Winkler, Stefan and Falk, Tiago H}, month = {jul}, pages = {24-25}, publisher = {IEEE}, abstract = {Preparing and conducting subjective quality assessments is a time consuming and expensive task. Therefore, we present a Web-based evaluation framework which aims on reducing the time needed for planning and designing a subjective quality assessment. The presented framework can be used for both crowdsourced and laboratory experiments. It should ease the task of designing a subjective quality assessment by providing a flexible framework. The framework has proven its applicability and flexibility to design and conduct assessments in the past and is available as open source.}, isbn13 = {-}, keywords = {Evaluation Platform, Crowdsourced Quality Evaluation, Laboratory Quality Evaluation, Quality Assessment Framework}, language = {EN}, location = {Klagenfurt am Wörthersee, Austria}, pdf = {https://www.itec.aau.at/bib/files/QoMEX2013_EvalPlatform.pdf}, talkdate = {2013.07.03}, talktype = {poster}, url = {http://www.qomex2013.org} } @InProceedings{Raffelsberger2013a, author = {Raffelsberger, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the Eleventh IEEE International Conference on Pervasive Computing and Communications Workshops ({PerCom Workshops '13})}, title = {A Hybrid {MANET-DTN} Routing Scheme For Emergency Response Scenarios}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Indulska, Jadwiga and Bisdikian, Chatschik}, month = {mar}, pages = {505-510}, publisher = {IEEE}, abstract = {Emergency response operations are a promising application area for mobile ad-hoc networks (MANETs). Most existing MANET routing protocols assume that an end-toend path between source and destination can be established. However, this assumption may not hold in a hastily formed network established during an emergency response. This paper evaluates a store-and-forward mechanism for proactive routing protocols to mitigate the effects of network disruptions. The mechanism is integrated into two routing protocols. The modified protocols are evaluated in an emergency response scenario that includes a disaster area mobility model and a wireless obstacle model. The scenario represents a realistic first responder operation after an incident in a chemical facility. The evaluation results show that networks for disaster responses benefit from the modified routing protocols.}, language = {EN}, location = {San Diego, CA, USA}, pdf = {https://www.itec.aau.at/bib/files/PerNEM2013-cr.pdf}, talkdate = {2013.03.22}, talktype = {registered} } @InProceedings{Raffelsberger2013, author = {Raffelsberger, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the Combined workshop on Self-organizing, Adaptive, and Context-Sensitive Distributed Systems and Self-organized Communication in Disaster Scenarios ({SACS/SoCoDiS} '13)}, title = {Overview of Hybrid {MANET-DTN} Networking and its Potential for Emergency Response Operations}, year = {2013}, address = {Berlin, Germany}, editor = {Zapf, Michael and Evers, Florian}, month = {mar}, pages = {1 -12}, publisher = {Electronic Communications of the EASST ({ECEASST})}, abstract = {Communication networks for emergency response operations have to operate in harsh environments. As fixed infrastructures may be unavailable (e.g., they are destroyed or overloaded), mobile ad-hoc networks (MANETs) are a promising solution to establish communication for emergency response operations. However, networks for emergency responses may provide diverse connectivity characteristics which imposes some challenges, especially on routing. Routing protocols need to take transmission errors, node failures and even the partitioning of the network into account. Thus, there is a need for routing algorithms that provide mechanisms from Delay or Disruption Tolerant Networking (DTN) in order to cope with network disruptions but at the same time are as efficient as MANET routing schemes in order to preserve network resources. This paper reviews several hybrid MANET-DTN routing schemes that can be found in the literature. Additionally, the paper evaluates a realistic emergency response scenario and shows that MANET-DTN routing schemes have the potential to improve network performance as the resulting network is diverse in terms of connectivity. In particular, the network provides well-connected regions whereas other parts are only intermittently connected.}, issn = {1863-2122}, language = {EN}, location = {Stuttgart, Germany}, pdf = {https://www.itec.aau.at/bib/files/SoCoDis2013-cr.pdf}, talkdate = {2013.03.15}, talktype = {registered} } @InProceedings{Primus_CBMI2013, author = {Primus, Manfred Jürgen and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {11th International Workshop on Content-Based Multimedia Indexing}, title = {Segmentation of Recorded Endoscopic Videos by Detecting Significant Motion Changes}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Czuni, Laszlo}, month = {jun}, pages = {223--228}, publisher = {IEEE Computer Society}, abstract = {In the medical domain it has become common to store recordings of endoscopic surgeries or procedures. The storage of these endoscopic videos provides not only evidence of the work of the surgeons but also facilitates research, the training of new surgeons and supports explanations to the patients. However, an endoscopic video archive, where tens or hundreds of new videos are added each day, needs content-based analysis in order to provide content-based search. A fundamental first step in content analysis is the segmentation of the video. We propose a new method for segmentation of endoscopic videos, based on spatial and temporal differences of motion in these videos. Through an evaluation with 20 videos we show that our approach provides reasonable performance.}, language = {EN}, location = {Veszprem, Hungary}, pdf = {https://www.itec.aau.at/bib/files/CBMI_2013_39.pdf}, talkdate = {2013.06.18}, talktype = {registered} } @InProceedings{Posch2013, author = {Posch, Daniel and Hellwagner, Hermann and Schartner, Peter}, booktitle = {Proceedings of the 8th International Workshop on Secure Network Protocols (NPSec' 13)}, title = {On-Demand Video Streaming based on Dynamic Adaptive Encrypted Content Chunks}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Li, Jun and Maennel, Olaf}, month = {oct}, pages = {6}, publisher = {IEEE}, abstract = {This paper proposes a framework for on-demand video streaming that enables secure and efficient delivery of data towards the end user. Our proposal requires the combined usage of three different technologies. The first one is a recent proposal by Jacobsen et al. called Content-Centric Networking (also known as Named Data Networking). It is a network architecture that introduces named data as the most valuable element in the network and divides it into so called content chunks, which are self-identifying and self-authenticating data units. The second concept we utilize derives from the approach of Dynamic Adaptive Streaming over HTTP, which allows clients to dynamically choose the quality of the received video stream according to their available resources. Finally, we adapt the concept of Broadcast Encryption to form a tool to control the access to provided content streams. The combination of these technologies enables us to design a framework that allows streaming providers to transport data to customers as dynamic adaptive encrypted content chunks, which is an efficient, flexible and scalable way of multimedia data transport.}, keywords = {Content-Centric Networking, CCN, Named Data Networking, NDN, Dynamic Adaptive Streaming, DASH, Broadcast Encryption, Video on Demand}, language = {EN}, location = {Germany, Göttingen}, pdf = {https://www.itec.aau.at/bib/files/ICNP_NPSEC_Streaming.pdf}, talkdate = {2013.10.07}, talktype = {registered} } @InProceedings{Pohl2013a, author = {Pohl, Daniela and Bouchachia, Abdelhamid and Hellwagner, Hermann}, booktitle = {12th International Conference on Machine Learning and Applications}, title = {Online Processing of Social Media Data for Emergency Management}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Tecuci, Gheorghe and Boicu, Mihai and Kubat, Miroslav}, month = {dec}, pages = {1-6}, publisher = {IEEE}, abstract = {Social media offers an opportunity for emergency management to identify issues that need immediate reaction. To support the effective use of social media, an analysis approach is needed to identify crisis-related hotspots. We consider in this investigation the analysis of social media (i.e., Twitter, Flickr and YouTube) to support emergency management by identifying sub-events. Sub-events are significant hotspots that are of importance for emergency management tasks. Aiming at sub-event detection, recognition and tracking, the data is processed online in real-time. We introduce an incremental feature selection mechanism to identify meaningful terms and use an online clustering algorithm to uncover sub-events on-the-fly. Initial experiments are based on tweets enriched with Flickr and YouTube data collected during Hurricane Sandy. They show the potential of the proposed approach to monitor sub-events for real-world emergency situations.}, keywords = {Online Clustering, Sub-Event Detection, Crisis Management}, language = {EN}, location = {Miami, Florida, USA}, pdf = {https://www.itec.aau.at/bib/files/Pohl_ICMLA13.pdf}, talkdate = {2013.12.01}, talktype = {poster} } @InProceedings{Muenzer2013b, author = {Münzer, Bernd and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {IEEE International Symposium on Multimedia (ISM2013)}, title = {Relevance Segmentation of Laparoscopic Videos}, year = {2013}, address = {Anaheim, CA, USA}, editor = {Liao, Anthony Y H}, month = {dec}, pages = {84-91}, publisher = {IEEE}, abstract = {In recent years, it became common to record video footage of laparoscopic surgeries. This leads to large video archives that are very hard to manage. They often contain a considerable portion of completely irrelevant scenes which waste storage capacity and hamper an efficient retrieval of relevant scenes. In this paper we (1) define three classes of irrelevant segments, (2) propose visual feature extraction methods to obtain irrelevance indicators for each class and (3) present an extensible framework to detect irrelevant segments in laparoscopic videos. The framework includes a training component that learns a prediction model using nonlinear regression with a generalized logistic function and a segment composition algorithm that derives segment boundaries from the fuzzy frame classifications. The experimental results show that our method performs very good both for the classification of individual frames and the detection of segment boundaries in videos and enables considerable storage space savings.}, language = {DE}, location = {Anaheim, CA, USA}, talkdate = {2013.12.11}, talktype = {registered} } @InProceedings{Muenzer2013a, author = {Münzer, Bernd and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the IEEE International Conference on Multimedia and Expo (ICME) 2013}, title = {Improving Encoding Efficiency of Endoscopic Videos by using Circle Detection based Border Overlays}, year = {2013}, address = {San Jose, USA}, editor = {Zabulis, Xenophon}, month = {jul}, pages = {1-4}, publisher = {IEEE}, abstract = {Videos of endoscopic procedures typically feature a circular content area in the image center. This area is surrounded by a dark border that carries no relevant information but is subject to noise. Thus, a considerable proportion of the available bitrate has to be wasted to encode the border regions. We propose to superimpose the border regions with a homogenous black mask so that it can be encoded efficiently with skipped macroblocks. To determine the exact position and size of the circular content area we use an efficient circle detection algorithm. Through an evaluation with 138 videos we show that the border overlay can significantly reduce the bitrate without degrading the visual quality of the content area.}, doi = {10.1109/ICMEW.2013.6618304}, language = {EN}, location = {San Jose, USA}, talkdate = {2013.07.18}, talktype = {poster} } @InProceedings{Muenzer2013, author = {Münzer, Bernd and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {26th International Symposium on Computer-Based Medical Systems (CBMS'13)}, title = {Detection of Circular Content Area in Endoscopic Videos}, year = {2013}, address = {Porto, Portugal}, editor = {Soda, Paolo}, month = {jun}, pages = {534-536}, publisher = {IEEE}, abstract = {The actual content of endoscopic videos is typically limited to a circular area in the image center. This area has a dynamic position and size and is surrounded by a dark, but noisy border. In this paper we present a novel algorithm that (1) classifies which frames of an endoscopic video feature the circular content area and (2) determines its exact position and size, if present. This information is very useful for improving the performance of subsequent analysis techniques. It can also be used for more efficient video encoding and economic printing of still images in findings and reports. The evaluation shows that the proposed method is very accurate, robust and efficient in terms of runtime.}, doi = {10.1109/CBMS.2013.6627865}, language = {EN}, location = {Porto, Portugal}, talkdate = {2013.06.20}, talktype = {poster} } @InProceedings{Mueller2013b, author = {Mueller, Christopher and Lederer, Stefan and Pöcher, Jörg and Timmerer, Christian}, booktitle = {In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME) 2013}, title = {libdash – An Open Source Software Library for the MPEG-DASH Standard}, year = {2013}, address = {San Jose, USA}, editor = {Servetti, Antonio and Aydin, Alatan}, month = {jul}, pages = {1-2}, publisher = {IEEE}, abstract = {Dynamic Adaptive Streaming over HTTP (DASH) is an ISO/IEC MPEG standard which enables the convenient and smooth transportation of multimedia data to heterogeneous end devices over networks with variable bandwidth conditions. This kind of streaming technology is mainly used with HTTP 1.0 and 1.1 respectively, which both have some drawbacks. Therefore, the IETF has started the development of HTTP 2.0, which is based on Google’s SPDY proposal and already supported by several major companies, e.g., Facebook, Twitter, Akamai, Mozilla and obviously Google. Furthermore, Content Centric Networking (CCN) is another novel approach for future networks that is considered as an revolutionary approach compared to HTTP 2.0. The CCN communication paradigm is completely different and does not rely on direct connections between hosts, it rather focuses on the content. This paper demonstrates DASH with HTTP 2.0/SPDY and CCN using our universal libdash library. Moreover, different mechanisms of DASH will be shown that can be used to provide on-demand and live content in an efficient and comfortable way.}, language = {EN}, location = {San Jose, USA}, pdf = {https://www.itec.aau.at/bib/files/libdash-demo.pdf}, talkdate = {2013.07.18}, talktype = {poster} } @InProceedings{Mueller2013, author = {Mueller, Christopher and Lederer, Stefan and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME) 2013}, title = {Dynamic Adaptive Streaming over HTTP/2.0}, year = {2013}, address = {San Jose, USA}, editor = {Li, Jin}, month = {jul}, pages = {1-6}, publisher = {IEEE}, abstract = {MPEG Dynamic Adaptive Streaming over HTTP (DASH) is a new streaming standard that has been recently ratified as an international standard (IS). In comparison to other streaming systems, e.g., HTTP progressive download, DASH is able to handle varying bandwidth conditions providing smooth streaming. Furthermore, it enables NAT and Firewall traversal, flexible and scalable deployment as well as reduced infrastructure costs due to the reuse of existing Internet infrastructure components, e.g., proxies, caches, and Content Distribution Networks (CDN). Recently, the Hypertext Transfer Protocol Bis (httpbis) working group of the IETF has officially started the development of HTTP 2.0. Initially three major proposals have been submitted to the IETF i.e., Googles' SPDY, Microsofts' HTTP Speed+Mobility and Network-Friendly HTTP Upgrade, but SPDY has been chosen as working draft for HTTP 2.0. In this paper we implemented MPEG-DASH over HTTP 2.0 (i.e., SPDY), demonstrating its potential benefits and drawbacks. Moreover, several experimental evaluations have been performed that compare HTTP 2.0 with HTTP 1.1 and HTTP 1.0 in the context of DASH. In particular, the protocol overhead, the performance for different round trip times, and DASH with HTTP 2.0 in a lab test scenario has been evaluated in detail.}, language = {EN}, location = {San Jose, USA}, pdf = {https://www.itec.aau.at/bib/files/paper_330.pdf}, talkdate = {2013.07.17}, talktype = {registered} } @InProceedings{Marques2013, author = {Marques, Oge and Snyder, Justyn and Lux, Mathias}, booktitle = {CHI '13 Extended Abstracts on Human Factors in Computing Systems}, title = {How Well Do You Know Tom Hanks?: Using a Game to Learn About Face Recognition}, year = {2013}, address = {New York, USA}, editor = {Mackay, W and Brewster, St and Bodker, S}, month = {jan}, pages = {337--342}, publisher = {ACM}, series = {CHI EA '13}, abstract = {Human face recognition abilities vastly outperform computer-vision algorithms working on comparable tasks, especially in the case of poor lighting, bad image quality, or partially hidden faces. In this paper, we describe a novel game with a purpose in which players must guess the name of a celebrity whose face appears blurred. The game combines a successful casual game paradigm with meaningful applications in both human- and computer-vision science. Preliminary user studies were conducted with 28 users and more than 7,000 game rounds. The results supported and extended pre-existing knowledge and hypotheses from controlled scientific experiments, which show that humans are remarkably good at recognizing famous faces, even with a significant degree of blurring. Our results will be further incorporated into research in human vision as well as machine-learning and computer-vision algorithms for face recognition.}, doi = {10.1145/2468356.2468416}, keywords = {computer vision, face recognition, games, human vision}, language = {EN}, talktype = {none}, url = {http://doi.acm.org/10.1145/2468356.2468416} } @InProceedings{Lux_MMSys_Feb_2013, author = {Lux, Mathias and Riegler, Michael}, booktitle = {Proceedings of the 4th ACM Multimedia Systems Conference}, title = {Annotation of Endoscopic Videos on Mobile Devices: A Bottom-up Approach}, year = {2013}, address = {New York, NY, USA}, editor = {Griwodz, C}, month = {jan}, pages = {141--145}, publisher = {ACM}, series = {MMSys '13}, abstract = {Video annotation is a tedious task. But especially in medical domain the knowledge of experts for the interpretation of videos is of high value. Typically medical doctors do not have time for extensive annotation, but are used to manual notes, speech recordings, and pointing. In this demo paper we present an application for annotation of medical videos, focusing on endoscopic surgery. We adopt common interaction method of medical experts to mobile computing and provide a tool for experts to annotate videos by drawing on the video and recording speech annotations.}, doi = {10.1145/2483977.2483996}, keywords = {medical multimedia information systems, video annotation}, language = {EN}, location = {Oslo, Norway}, talkdate = {2013.02.28}, talktype = {registered}, url = {http://doi.acm.org/10.1145/2483977.2483996} } @InProceedings{Lux2013, author = {Lux, Mathias}, booktitle = {Proceedings of the 21st ACM International Conference on Multimedia}, title = {LIRE: Open Source Image Retrieval in Java}, year = {2013}, address = {New York, NY, USA}, editor = {Jaimes, A and Sebe, N and Boujemaa, N and Gatica-Perez, D and Shamma, DA and Worring, M and Zimmermann, R}, month = {oct}, pages = {843--846}, publisher = {ACM}, series = {MM '13}, abstract = {Content based image retrieval has been around for some time. There are lots of different test data sets, lots of published methods and techniques, and manifold retrieval challenges, where content based image retrieval is of interest. LIRE is a Java library, that provides a simple way to index and retrieve millions of images based on the images' contents. LIRE is robust and well tested and is not only recommended by the websites of ImageCLEF and MediaEval, but is also employed in industry. This paper gives an overview on LIRE, its use, capabilities and reports on retrieval and runtime performance.}, doi = {10.1145/2502081.2502226}, keywords = {content based image retrieval}, language = {EN}, location = {Barcelona, Spain}, talkdate = {2013.10.21}, talktype = {registered}, url = {http://doi.acm.org/10.1145/2502081.2502226} } @InProceedings{Liu2013, author = {Liu, Yaning and Geurts, Joost and Point, Jean-Charles and Lederer, Stefan and Rainer, Benjamin and Mueller, Christopher and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the IEEE international Conference on Communication (ICC) 2013 – Next-Generation Networking Symposium}, title = {Dynamic Adaptive Streaming over CCN: A Caching and Overhead Analysis}, year = {2013}, address = {Budapest}, editor = {Mattheisen, Christopher and Murase, Tutomu}, month = {jun}, pages = {2222-2226}, publisher = {IEEE}, abstract = {In this paper, we present our implementation and evaluation of Dynamic Adaptive Streaming over Content centric networking (DASC) which implements MPEG Dynamic Adaptive Streaming over HTTP (DASH) utilizing a Content Centric Networking (CCN) naming scheme to identify content segments in a CCN network. In particular, video segments formatted according to MPEG-DASH are available in different quality levels but instead of HTTP, CCN is used for referencing and delivery. Based on the conditions of the network, the DASC client issues interests for segments achieving the best throughput. Due to segment caching within the network, subsequent requests for the same content can be served quicker. As a result, the quality of the video a user receives progressively improves, effectively overcoming bottlenecks in the network. We present two sets of experiments to evaluate the performance of DASC showing that throughput indeed improves. However, the generated overhead is relatively large and the adaptation strategy used for DASH that assumes an end-to-end connection could be revised for the hop-by-hop architecture of CCN.}, keywords = {Content Centric Networking, Dynamic Adaptive Streaming, HTTP Video Streaming, MPEG-DASH}, language = {EN}, location = {Budapest, Hungary}, pdf = {https://www.itec.aau.at/bib/files/ICC2013 -DASH Over CCN.PDF}, talkdate = {2013.06.11}, talktype = {registered}, url = {http://www.ieee-icc.org} } @InProceedings{Lederer2013c, author = {Lederer, Stefan and Mueller, Christopher and Rainer, Benjamin and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the IEEE International Conference on Multimedia and Expo (ICME) 2013}, title = {An Experimental Analysis of Dynamic Adaptive Streaming over HTTP in Content Centric Networks}, year = {2013}, address = {San Jose, USA}, editor = {Wang, Haohong}, month = {jul}, pages = {1-6}, publisher = {IEEE}, abstract = {This paper presents the usage of CCN, which is a candidate for the next-generation Internet, in combination with the new Dynamic Adaptive Streaming over HTTP (DASH) standard, which was recently ratified by ISO/IEC MPEG. In contrast to the Internet Protocol, which is mainly based on the host-to-host connection paradigm originated in the 1970s, Content Centric Networking (CCN) focuses on the content itself, instead of its location. Considering the dominance of multimedia traffic in todays' Internet, the streaming performance of DASH over CCN as well as the problems introduced by this combination is worth to be investigated in detail. Therefore, we evaluate the protocol overhead introduced by the usage of CCN compared to the HTTP versions 1.0 and 1.1. Furthermore, the performance of DASH over CCN under different network conditions is compared to the performance of HTTP 1.0/1.1. Our results showed that although CCN comes together with higher protocol overhead than HTTP 1.0/1.1 as well as a prototype implementation, it can definitely compete with HTTP 1.0 in media streaming. Based on the evaluation results, problems as well as improvement possibilities are identified, which are the basis for future work in this area.}, language = {EN}, location = {San Jose, USA}, pdf = {https://www.itec.aau.at/bib/files/ICME_Overhead-Performance-DASHoverCCN.pdf}, talkdate = {2013.07.18}, talktype = {registered} } @InProceedings{Lederer2013b, author = {Lederer, Stefan and Mueller, Christopher and Rainer, Benjamin and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {In Proceedings of the IEEE ICC'13 - Workshop on Immersive \& Interactive Multimedia Communications over the Future Internet}, title = {Adaptive Streaming over Content Centric Networks in Mobile Networks using Multiple Links}, year = {2013}, address = {Budapest}, editor = {Assuncao, Pedro and Atzori, Luigi and Dagiuklas, Tasos and Kondoz, Ahmet}, month = {jun}, pages = {687-691}, publisher = {IEEE}, abstract = {This paper presents the usage of Content Centric Networking (CCN) for adaptive multimedia streaming in mobile environments, leveraging the recent ISO/IEC MPEG Dynamic Adaptive Streaming over HTTP (DASH) standard. The performance of DASH over CCN is evaluated using real-world mobile bandwidth traces and compared to previous evaluations of different DASH-based as well as proprietary systems. As there are no client-server connections in CCN, it offers the possibility to transfer data from multiple sources as well as over multiple links in parallel, which is definitely an important feature, e.g., for mobile devices offering multiple network links. This functionality is used and evaluated in this paper in combination with DASH, making it possible to dynamically choose the best performing link for media streaming, which is a clear advantage over DASH using HTTP and the TCP/IP protocol stack. The evaluation therefore investigates DASH over CCN in two scenarios using synthetic and real-world mobile bandwidth traces respectively, showing a significantly better performance than conventional DASH using only one connection.}, keywords = {MPEG-DASH, CCN, Dynamic Adaptive Streaming over HTTP, Content Centric Networking, Evaluation}, language = {EN}, location = {Budapest, Hungary}, pdf = {https://www.itec.aau.at/bib/files/ICC2013_Mobile_DASHoverCCN.pdf}, talkdate = {2013.06.13}, talktype = {registered}, url = {http://multicomm.diee.unica.it/} } @InProceedings{Lederer2013a, author = {Lederer, Stefan and Mueller, Christopher and Timmerer, Christian and Concolato, Cyril and Le Feuvre, Jean and Fliegel, Karel}, booktitle = {Proceedings of the 4th ACM Multimedia Systems Conference}, title = {Distributed DASH Dataset}, year = {2013}, address = {New York, NY, USA}, editor = {Griwodz, Carsten}, month = {feb}, pages = {pp. 131-135}, publisher = {ACM}, abstract = {The delivery of multimedia content over HTTP and on top of existing Internet infrastructures is becoming the preferred method within heterogeneous environment. The basic design principle is having an intelligent client which selects given and applicable media representations by issuing HTTP requests for individual segments based on the users' context and current conditions. Typically, this client behavior differs between implementations of the same kind and for the objective evaluations thereof appropriate datasets are needed. This paper presents a distributed dataset for the recently published MPEG-DASH standard which is mirrored at different sites across Europe, namely Klagenfurt, Paris, and Prague. A client implementation may choose to request segments from these sites and dynamically switch to a different location, e.g., in case the one currently used causes any issues. Thus, this distributed DASH dataset can be used for real-world evaluations enabling the simulation of switching between different content delivery networks.}, keywords = {Dataset, Dynamic Adaptive Streaming over HTTP, DASH.}, language = {EN}, location = {Oslo, Norway}, pdf = {https://www.itec.aau.at/bib/files/MMSys_CDN_Simulation_Dataset_v2.0.pdf}, talkdate = {2013.02.27}, talktype = {registered}, url = {http://www.mmsys.org/} } @InProceedings{HudelistMM2013, author = {Hudelist, Marco Andrea and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the ACM International Conference on Multimedia (MM2013)}, title = {Mobile Video Browsing with the ThumbBrowser}, year = {2013}, address = {New York, NY, USA}, editor = {Gatica-Perez, Daniel and Shamma, David and Worring, Marcel and Zimmermann, Roger and Jaimes, Alejandro and Sebe, Nicu and Boujemaa, Nozha}, month = {oct}, pages = {2}, publisher = {ACM Digital Library}, language = {EN}, location = {Barcelona, Spain}, talkdate = {2013.10.23}, talktype = {poster} } @InProceedings{HudelistISM2013, author = {Hudelist, Marco Andrea and Schoeffmann, Klaus and Ahlström, David}, booktitle = {IEEE International Symposium on Multimedia (ISM2013)}, title = {Evaluation of Image Browsing Interfaces for Smartphones and Tablets}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Friedland, Gerald and Liu, Zhu and Steinmetz, Nadine}, month = {dec}, pages = {8}, publisher = {IEEE}, language = {EN}, location = {Anaheim, CA, USA}, talkdate = {2013.12.09}, talktype = {registered} } @InProceedings{Hudelist2013_ICMRa, author = {Hudelist, Marco Andrea and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 3rd ACM International Conference on Multimedia Retrieval (ICMR 2013)}, title = {Next Generation Image and Video Browsing on Mobile Devices}, year = {2013}, address = {New York, NY, USA}, editor = {Jain, Ramesh and Prabhakaran, Balakrishnan}, month = {apr}, pages = {333--336}, publisher = {ACM}, language = {EN}, location = {Dallas, Texas, USA.}, talkdate = {2013.04.18}, talktype = {registered} } @InProceedings{Hudelist2013_ICMR, author = {Hudelist, Marco Andrea and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 3rd ACM International Conference on Multimedia Retrieval}, title = {Mobile Video Browsing with a 3D Filmstrip}, year = {2013}, address = {New York, NY, USA}, editor = {Jain, Ramesh and Prabhakaran, Balakrishnan}, month = {apr}, pages = {299--300}, publisher = {ACM}, language = {EN}, location = {Dallas, Texas, USA}, talkdate = {2013.04.19}, talktype = {poster} } @InProceedings{Grafl2013_ViDEv, author = {Grafl, Michael and Timmerer, Christian and Hellwagner, Hermann and Cherif, Wael and Ksentini, Adlen}, booktitle = {Proceedings of the 2nd {IEEE} {WoWMoM} Workshop on Video Everywhere ({ViDEv} 2013)}, title = {Evaluation of Hybrid Scalable Video Coding for {HTTP}-based Adaptive Media Streaming with High-Definition Content}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Todd, Terence D and Paterakis, Michael}, month = {jun}, pages = {7}, publisher = {IEEE}, abstract = {Scalable Video Coding (SVC) in media streaming enables dynamic adaptation based on device capabilities and network conditions. In this paper, we investigate deployment options of SVC for Dynamic Adaptive Streaming over HTTP (DASH) with a special focus on scalability options, which are relevant for dynamic adaptation, especially in wireless and mobile environments. We evaluate the performance of SVC with respect to spatial and quality scalability options and compare it to non-scalable Advanced Video Coding (AVC). Performance evaluations are performed for various encoder implementations with high-definition (1080p) content. We show that a hybrid approach with multiple independent SVC bitstreams can have advantages in storage requirements at comparable rate-distortion performance.}, keywords = {scalable video coding; HTTP streaming; adaptation; high-definition; hybrid SVC-DASH}, language = {EN}, location = {Madrid, Spain}, pdf = {https://www.itec.aau.at/bib/files/Hybrid_SVC-DASH.pdf}, talkdate = {2013.06.04}, talktype = {registered} } @InProceedings{Grafl2013_PQS, author = {Grafl, Michael and Timmerer, Christian}, booktitle = {Proceedings of the 4th International Workshop on Perceptual Quality of Systems ({PQS} 2013)}, title = {Representation Switch Smoothing for Adaptive {HTTP} Streaming}, year = {2013}, address = {Vienna, Austria}, editor = {Schatz,Raimund and Hoßfeld, Tobias}, month = {sep}, pages = {178-183}, publisher = {FTW}, abstract = {When an adaptive media streaming system has to switch from one representation of the content to another, the switch causes viewer distraction. We introduce the concept of representation switch smoothing for alleviating the distraction and improving the overall quality of experience. As adaptive HTTP streaming systems typically deploy video buffers on the client side, the adaptation decision is known far enough ahead of playout time to perform a seamless transition between quality representations. We discuss implementation considerations for an adaptive HTTP streaming system with scalable video coding, present a subjective evaluation of the proposed approach, and identify factors that influence how smooth transitions are perceived.}, keywords = {adaptive streaming; representation switching; quality of experience}, language = {EN}, location = {Vienna, Austria}, pdf = {https://www.itec.aau.at/bib/files/representation_switch_smoothing.pdf}, talkdate = {2013.09.04}, talktype = {registered} } @InProceedings{Grafl2013_ISCC, author = {Grafl, Michael and Timmerer, Christian and Hellwagner, Hermann and Cherif, Wael and Negru, Daniel and Battista, Stefano}, booktitle = {Proceedings of the 18th {IEEE} Symposium on Computers and Communication ({ISCC} 2013)}, title = {Scalable Video Coding Guidelines and Performance Evaluations for Adaptive Media Delivery of High Definition Content}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Douligeris, Christos and Gotovac, Sven and Vojnović, Milan}, month = {jul}, pages = {6}, publisher = {IEEE}, abstract = {Scalability within media coding allows for content adaptation towards heterogeneous user contexts and enables in-network adaptation. However, there is no straightforward solution how to encode the content in a scalable way while maximizing rate-distortion performance. In this paper we provide encoding guidelines for scalable video coding based on a survey of media streaming industry solutions and a comprehensive performance evaluation using four state of the art scalable video codecs with a focus on high-definition content (1080p).}, keywords = {scalable video coding; adaptation; high-definition video; encoding; adaptive media streaming; content-aware networking}, language = {EN}, location = {Split, Coratia}, pdf = {https://www.itec.aau.at/bib/files/SVC_guide_and_eval.pdf}, talkdate = {2013.07.10}, talktype = {registered} } @InProceedings{DelFabro_CBMI2013, author = {Del Fabro, Manfred and Schoeffmann, Klaus and Guggenberger, Mario and Taschwer, Mario}, booktitle = {11th International Workshop on Content-Based Multimedia Indexing}, title = {A Filtering Tool to Support Interactive Search in Internet Video Archives}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Czuni, Laszlo}, month = {jun}, pages = {7--10}, publisher = {IEEE Computer Society}, language = {EN}, location = {Veszprem, Hungary}, talkdate = {2013.06.18}, talktype = {poster} } @InProceedings{DelFabro2013a, author = {Del Fabro, Manfred and Münzer, Bernd and Böszörmenyi, Laszlo}, booktitle = {Advances in Multimedia Modeling}, title = {AAU Video Browser with Augmented Navigation Bars}, year = {2013}, address = {Berlin Heidelberg}, editor = {Li, Shipeng and El-Saddik, Abdulmotaleb and Wang, Meng and Mei, Tao and Sebe, Nicu and Yan, Shuicheng and Hong, Richang and Gurrin, Cathal}, month = {jan}, pages = {544-546}, publisher = {Springer}, series = {Lecture Notes in Computer Science Volume 7733}, abstract = {We present an improved version of last year’s winner of the Video Browser Showdown. In a preprocessing step video segments are detected and clustered in several latent classes of similar content based on color and motion information. The navigation bars of our video browser are then augmented with different colors indicating where elements of the detected clusters are located. As humans are able to classify the content of clusters fast, they can benefit from this information when browsing through a video.}, doi = {10.1007/978-3-642-35728-2_9}, isbn10 = {978-3-642-35727-5}, isbn13 = {978-3-642-35728-2}, language = {EN}, location = {Huangshan, China}, subtitle = {19th International Conference, MMM 2013, Huangshan, China, January 7-9, 2013, Proceedings, Part II}, talkdate = {2013.01.08}, talktype = {poster} } @InProceedings{DelFabro2013, author = {Del Fabro, Manfred and Münzer, Bernd and Böszörmenyi, Laszlo}, booktitle = {Advances in Multimedia Modeling}, title = {Smart Video Browsing With Augmented Navigation Bars}, year = {2013}, address = {Berlin Heidelberg}, editor = {Li, Shipeng and El-Saddik, Abdulmotaleb and Wang, Meng and Mei, Tao and Sebe, Nicu and Yan, Shuicheng and Hong, Richang and Gurrin, Cathal}, month = {jan}, pages = {88-98}, publisher = {Springer}, series = {Lecture Notes in Computer Science Volume 7733}, abstract = {While accuracy and speed get a lot of attention in video retrieval research, the investigation of interactive retrieval tools gets less attention and is often regarded as trivial. We want to show that even simple ideas have potential to improve the retrieval performance by giving some automated support to the browsing user. We present a video browsing concept where video segments are clustered in several latent classes of similar content. The navigation bars of our video browser are augmented with different colors indicating where elements of these clusters are located. As humans are able to classify the content of clusters fast, they can benefit from this information when browsing a video. We present a study where we investigated how humans can be supported in different video browsing tasks with a color-based and a motion-based clustering of video content.}, doi = {10.1007/978-3-642-35728-2_9}, isbn10 = {978-3-642-35727-5}, isbn13 = {978-3-642-35728-2}, language = {EN}, location = {Huangshan, China}, subtitle = {19th International Conference, MMM 2013, Huangshan, China, January 7-9, 2013, Proceedings, Part II}, talkdate = {2013.01.08}, talktype = {registered} } @InProceedings{Crabtree2013, author = {Crabtree, Barry and Stevens, Tim and Allan, Brahin and Lederer, Stefan and Posch, Daniel and Mueller, Christopher and Timmerer, Christian}, booktitle = {CCNxConn 2013}, title = {Video Adaptation in Limited or Zero Network Coverage}, year = {2013}, address = {Palo Alto}, editor = {Mahadevan, Priya}, month = {sep}, pages = {1-2}, publisher = {PARC}, abstract = {This paper shows how adaptive streaming and on-device caching can be used to provide an always available video service. A DASH client has been extended to deal with periods of zero network connectivity, and seamlessly works in conjunction with CCN to provide local storage that is intelligently updated to provide an improved quality of experience.}, language = {EN}, location = {Palo Alto, CA, USA}, pdf = {https://www.itec.aau.at/bib/files/Video adaptation in limited or zero network coverage-CCNxCon.pdf}, talkdate = {2013.09.06}, talktype = {poster}, url = {http://www.ccnx.org/ccnxcon2013/ccnxcon-2013-official-agenda/} } @InProceedings{Bailer2013, author = {Bailer, Werner and Schoeffmann, Klaus and Ahlström, David and Weiss, Wolfgang and Del Fabro, Manfred}, booktitle = {Advances in Multimedia Modeling}, title = {Interactive Evaluation of Video Browsing Tools}, year = {2013}, address = {Berlin Heidelberg}, editor = {Li, Shipeng and El-Saddik, Abdulmotaleb and Wang, Meng and Mei, Tao and Sebe, Nicu and Yan, Shuicheng and Hong, Richang and Gurrin, Cathal}, month = {jan}, pages = {81-91}, publisher = {Springer}, series = {Lecture Notes in Computer Science Volume 7732}, abstract = {The Video Browser Showdown (VBS) is a live competition for evaluating video browsing tools regarding their efficiency at known-item search (KIS) tasks. The first VBS was held at MMM 2012 with eight teams working on 14 tasks, of which eight were completed by expert users and six by novices. We describe the details of the competition, analyze results regarding the performance of tools, the differences between the tasks and the nature of the false submissions.}, doi = {10.1007/978-3-642-35728-2_9}, isbn10 = {978-3-642-35724-4}, isbn13 = {978-3-642-35725-1}, language = {EN}, location = {Huangshan, China}, subtitle = {19th International Conference, MMM 2013, Huangshan, China, January 7-9, 2013, Proceedings, Part I}, talkdate = {2013.01.07}, talktype = {registered} } @InProceedings{Alberti_QoMEX2013_DASH, author = {Alberti, Claudio and Renzi, Daniele and Timmerer, Christian and Mueller, Christopher and Lederer, Stefan and Battista, Stefano and Mattavelli, Marco}, booktitle = {Proceedings of the 5th International Workshop on Quality of Multimedia Experience (QoMEX'13)}, title = {Automated QoE Evaluation of Dynamic Adaptive Streaming over HTTP}, year = {2013}, address = {Los Alamitos, CA, USA}, editor = {Timmerer, Christian and Le Callet, Patrick and Varela, Martin and Winkler, Stefan and Falk, Tiago}, month = {jul}, pages = {58--63}, publisher = {IEEE}, abstract = {Dynamic Adaptive Streaming over HTTP (DASH) is referred to as a multimedia streaming standard to deliver high quality multimedia content over the Internet using conventional HTTP Web servers. As a fundamental feature, it enables automatic switching of quality levels according to network conditions, user requirements, and expectations. Currently, the proposed adaptation schemes for HTTP streaming mostly rely on throughput measurements and/or buffer-related metrics, such as buffer exhaustion and levels. In this paper, we propose to enhance the DASH adaptation logic by feeding it with additional information from our evaluation of the users' perception approximating the user- perceived quality of video playback. The proposed model aims at conveniently combining TCP-, buffer-, and media content-related metrics as well as user requirements and expectations to be used as an input for the DASH adaptation logic. Experiments have demonstrated that the chosen model enhances the capability of the adaptation logic to select the optimal video quality level. Finally, we integrated all our findings into a real DASH system with QoE monitoring capabilities.}, keywords = {DASH, Quality of Experience, monitoring, content adaptation}, language = {EN}, location = {Klagenfurt am Wörthersee, Austria}, pdf = {https://www.itec.aau.at/bib/files/p20-Alberti.pdf}, talkdate = {2013.07.03}, talktype = {registered} } @InProceedings{lux2012did, author = {Lux, Mathias and Huber, Jochen}, booktitle = {Image Analysis for Multimedia Interactive Services (WIAMIS), 2012 13th International Workshop on}, title = {Why did you record this video? An exploratory study on user intentions for video production}, year = {2012}, address = {Los Alamitos, CA, USA}, editor = {O'Connor, Noel and Daras, Petros and Pereira, Fernando}, month = {jan}, organization = {IEEE}, pages = {1-4}, publisher = {IEEE}, abstract = {Why do people record videos and share them? While the question seems to be simple, user intentions have not yet been investigated for video production and sharing. A general taxonomy would lead to adapted information systems and multimedia interfaces tailored to the users' intentions. We contribute (1) an exploratory user study with 20 participants, examining the various facets of user intentions for video production and sharing in detail and (2) a novel set of user intention clusters for video production, grounded empirically in our study results. We further reflect existing work in specialized domains (i.e. video blogging and mobile phone cameras) and show that prevailing models used in other multimedia fields (e.g. photography) cannot be used as-is to reason about video recording and sharing intentions.}, doi = {10.1109/WIAMIS.2012.6226758}, isbn10 = {978-1-4673-0789-5}, isbn13 = {978-1-4673-0791-8}, issn = {2158-5873}, keywords = {Communication, Networking & Broadcasting ; Components, Circuits, Devices & Systems ; Computing & Processing (Hardware/Software) ; Signal Processing & Analysis}, language = {EN}, location = {Dublin, Ireland}, talkdate = {2012.05.25}, talktype = {registered} } @InProceedings{Waltl2012_QoMEX2012_SensoryEffects, author = {Waltl, Markus and Timmerer, Christian and Rainer, Benjamin and Hellwagner, Hermann}, booktitle = {Proceedings of the 4th International Workshop on Quality of Multimedia Experience (QoMEX'12)}, title = {Sensory Effect Dataset and Test Setups}, year = {2012}, address = {Yarra Valley, Australia}, editor = {Burnett, Ian and Wu, Henry}, month = {jul}, pages = {115--120}, publisher = {IEEE}, abstract = {Additional constituents for the representation of multimedia content gained more and more attention. For example, the amount of cinemas equipped with additional devices (e.g., ambient light, vibrating seats, wind generators, water sprayers, heater/coolers) that stimulate senses going beyond audition and vision increases. On the content side the MPEG-V standard specifies – among others – Sensory Effect Metadata (SEM) which provides means to describe sensory effects such as wind, vibration, light, etc. to be attached to audio-visual content and, thus, offering an enhanced and immersive experience for the user. However, there is a lack of a common set of test content allowing for various subjective user studies and verification across different test sites. In this paper we provide our dataset comprising a number of videos from different genres enriched with MPEG-V compliant Sensory Effect Metadata descriptions. Furthermore, we describe possible test setups using off-the-shelf hardware for conducting subjective quality assessments.}, isbn13 = {-}, keywords = {Sensory Experience, Sensory Effects, MPEG-V, Dataset, Test Environment}, language = {EN}, location = {Yarra Valley, Australia}, pdf = {https://www.itec.aau.at/bib/files/QoMEX2012_Dataset.pdf}, talkdate = {2012.07.05}, talktype = {registered}, url = {http://www.qomex2012.org} } @InProceedings{Waltl2012_MMM, author = {Waltl, Markus and Rainer, Benjamin and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Advances in Multimedia Modeling}, title = {Enhancing the User Experience with the Sensory Effect Media Player and AmbientLib}, year = {2012}, address = {Berlin, Heidelberg, New York}, editor = {Schoeffmann, Klaus and Merialdo, Bernard and Hauptmann, Alexander and Ngo, Chong-Wah and Andreopoulos, Yiannis and Breiteneder, Christian}, month = {jan}, pages = {624--626}, publisher = {Springer}, series = {LNCS 7131}, abstract = {Multimedia content is increasingly used in every area of our life. Still, each type of content only stimulates the visual and/or the hearing system. Thus, the user experience depends only on those two stimuli. In this paper we introduce a standard which offers the possibility to add additional effects to multimedia content. Furthermore, we present a multimedia player and a Web browser plug-in which uses this standard to stimulate further senses by using additional sensory effects (i.e., wind, vibration, and light) to enhance the user experience resulting in a unique, worthwhile sensory experience.}, keywords = {MPEG-V, User Experience, Sensory Experience, Media Player, Ambient, World Wide Web}, language = {EN}, location = {Klagenfurt, Austria}, pdf = {https://www.itec.aau.at/bib/files/mwbrcthh_mmm2012.pdf}, talkdate = {2012.01.05}, talktype = {poster} } @InProceedings{Waltl2012_ACMMM_OSSC, author = {Waltl, Markus and Rainer, Benjamin and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the 20th ACM Multimedia (MM'12)}, title = {A Toolset for the Authoring, Simulation, and Rendering of Sensory Experiences}, year = {2012}, address = {Nara, Japan}, editor = {Babaguchi, Noboru and Aizawa, Kiyoharu and Smith, John}, month = {oct}, pages = {1469-1472}, publisher = {ACM}, abstract = {This paper describes a toolset for the authoring, simulating, and rendering of multimedia content annotated with Sensory Effect Metadata (SEM) descriptions as specified in Part 3 of the MPEG V standard. This part of MPEG-V standardizes the description of sensory effects (e.g., light, wind) in order to be rendered on sensory devices (e.g., fans, vibration chairs) aiming at generating a sensory experience stimulating possibly all human senses. Our implementation comprises a toolset to author sensory effects associated with multimedia content and the simulation thereof. Furthermore, it includes a library, a standalone player, and a Web browser plug-in which enables the playback and rendering of sensory effects on off-the-shelf rendering devices and in various contexts. All software modules are available under the GNU General Public License (GPL) v3 and the GNU Lesser General Public License (LGPL) v3 respectively.}, isbn13 = {-}, keywords = {MPEG-V, Annotation Tool, Simulator, Media Player, Web Browser Plug-in, Sensory Effects, Sensory Experience}, language = {EN}, location = {Nara, Japan}, pdf = {https://www.itec.aau.at/bib/files/acmmm2012_ossc_mwbrcthh.pdf}, talkdate = {2012.10.31}, talktype = {registered}, url = {http://www.acmm2012.org} } @InProceedings{Timmerer2012_ACMMM, title = {Dynamic adaptive streaming over HTTP: from content creation to consumption}, author = {Timmerer, Christian and Griwodz, Carsten}, booktitle = {Proceedings of the 20th ACM international conference on Multimedia}, year = {2012}, address = {New York, NY, USA}, editor = {Babaguchi, Noboru and Aizawa, Kiyoharu and Smith, John}, month = {oct}, pages = {1533--1534}, publisher = {ACM}, series = {MM '12}, abstract = {In this tutorial we present dynamic adaptive streaming over HTTP ranging from content creation to consumption. It particular, it provides an overview of the recently ratified MPEG-DASH standard, how to create content to be delivered using DASH, its consumption, and the evaluation thereof with respect to competing industry solutions. The tutorial can be roughly clustered into three parts. In part I we will provide an introduction to DASH, part II covers content creation, delivery, and consumption, and, finally, part III deals with the evaluation of existing (open source) MPEG-DASH implementations compared to state-of-art deployed industry solutions.}, doi = {10.1145/2393347.2396553}, keywords = {MPEG, adaptation, dash, dynamic adaptive http streaming, streaming}, language = {EN}, location = {Nara, Japan}, pdf = {https://www.itec.aau.at/bib/files/mtu008-timmerer.pdf}, slides = {https://www.itec.aau.at/bib/files/mtu008-timmerer-slides.pdf}, talkdate = {2012.10.29}, talktype = {registered}, url = {http://doi.acm.org/10.1145/2393347.2396553} } @InProceedings{Taschwer2012, author = {Taschwer, Mario}, booktitle = {Advances in Multimedia Modeling}, title = {A Key-Frame-Oriented Video Browser}, year = {2012}, address = {Berlin / Heidelberg}, editor = {Schoeffmann, Klaus and Merialdo, Bernard and Hauptmann, Alexander and Ngo, Chong-Wah and Andreopoulos, Yiannis and Breiteneder, Christian}, month = {jan}, pages = {655-657}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, volume = {7131}, abstract = {We propose a video browser facilitating known-item search in a single video. Key frames are presented as four images at a time and can be navigated quickly in both forward and backward directions using a slider. Alternatively, key frames can be displayed automatically at different frame rates. The user may choose between three mappings of key frames to the four key frame widgets based on video time stamps and color similarity.}, doi = {10.1007/978-3-642-27355-1_68}, isbn13 = {978-3-642-27354-4}, language = {EN}, location = {Klagenfurt}, talkdate = {2012.01.06}, talktype = {poster}, url = {http://dx.doi.org/10.1007/978-3-642-27355-1_68} } @InProceedings{SobeEMCS2012, author = {Sobe, Anita and Elmenreich, Wilfried and Del Fabro, Manfred}, booktitle = {European Meeting on Cybernetics and Systems Research Book of Abstracts}, title = {Self-organizing content sharing at social events}, year = {2012}, address = {Vienna}, editor = {Bichler, Robert and Blachfellner, Stefan and Hofkirchner, Wolfgang}, month = {apr}, pages = {197--200}, publisher = {EMCSR}, language = {EN}, location = {Vienna, Austria}, talkdate = {2012.04.11}, talktype = {registered}, url = {http://www.emcsr.net/wp-content/uploads/2012/EMCSR_Book_of_Abstracts_V2.pdf} } @InProceedings{SchoeffmannWIAMIS2012, author = {Schoeffmann, Klaus and Ahlström, David}, booktitle = {Proceedings of The 13th International Workshop on Image Analysis for Multimedia Interactive Services ({WIAMIS} 2012)}, title = {Using a Cylindrical Interface for Image Browsing to Improve Visual Search Performance}, year = {2012}, address = {Los Alamitos, CA, USA}, editor = {O'Connor, Noel and Daras, Petros and Pereira, Fernando}, month = {may}, pages = {1-4}, publisher = {IEEE}, abstract = {In this paper we evaluate a 3D cylindrical interface that arranges image thumbnails by visual similarity for the purpose of image browsing. Through a user study we compare the performance of this interface to the performance of a common scrollable 2D list of thumbnails in a grid arrangement. Our evaluation shows that the 3D Cylinder interface enables significantly faster visual search and is the preferred search interface for the majority of tested users.}, language = {EN}, location = {Dublin, Ireland}, talkdate = {2012.05.23}, talktype = {registered} } @InProceedings{SchoeffmannMMM12, author = {Schoeffmann, Klaus and Ahlström, David and Böszörmenyi, Laszlo}, booktitle = {Advances in Multimedia Modeling}, title = {Video Browsing with a 3D Thumbnail Ring Arranged by Color Similarity}, year = {2012}, address = {Berlin, Heidelberg, New York}, editor = {Schoeffmann, Klaus and Merialdo, Bernard and Hauptmann, Alexander and Ngo, Chong-Wah and Andreopoulos, Yiannis and Breiteneder, Christian}, month = {jan}, pages = {660--662}, publisher = {Springer}, language = {EN}, location = {Klagenfurt, Austria}, talkdate = {2012.01.06}, talktype = {poster} } @InProceedings{SchoeffmannICMR2012, author = {Schoeffmann, Klaus and Hudelist, Marco Andrea and Schaefer, Gerald and Del Fabro, Manfred}, booktitle = {Proceedings of the 2nd ACM International Conference on Multimedia Retrieval}, title = {Mobile Image Browsing on a 3D Globe}, year = {2012}, address = {New York, NY, USA}, editor = {Horace, H S Ip and Rui, Yong}, month = {jun}, pages = {61:1--61:2}, publisher = {ACM}, abstract = {With users increasingly using their mobile devices such as smartphones as digital photo albums, effective methods for managing these collections are becoming increasingly important. Standard solutions provide only limited facilities for organising, browsing and searching image collections on mobile devices, making it challenging and time-consuming to locate images of interest. In this demo paper, we present an intuitive interface for organising and browsing image collections on mobile devices. Images are arranged on a 3D globe according to colour similarity. To avoid image overlap image thumbnails are placed on a regular grid structure while large image collections are organised using a hierarchical data structure. Through multi-touch user interaction image browsing can be performed in an intuitive and effective manner.}, doi = {10.1145/2324796.2324866}, isbn10 = {978-1-4503-1329-2}, language = {EN}, location = {Hong Kong, China}, talkdate = {2012.06.08}, talktype = {poster}, url = {http://dl.acm.org/citation.cfm?id=2324866} } @InProceedings{SchoeffmannICME2012_1, author = {Schoeffmann, Klaus and Ahlström, David and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the {IEEE} International Conference on Multimedia and Expo ({ICME} 2012)}, title = {3D Storyboards for Interactive Visual Search}, year = {2012}, address = {Los Alamitos, CA, USA}, editor = {Zhang, Jian and Schonfeld, Dan and Feng, David Dagan and Nanyang, Jianfei Cai and Hanjalic, Alan and Magli, Enrico and Pickering, Mark and Friedland, Gerald and Hua, Xian-Sheng}, month = {July}, pages = {848-853}, publisher = {IEEE Computer Society}, abstract = {Interactive image and video search tools typically use a grid-like arrangement of thumbnails for preview purpose. Such a display, which is commonly known as storyboard, provides limited flexibility at interactive search and it does not optimally exploit the available screen estate. In this paper we design and evaluate alternatives to the common two-dimensional storyboard. We take advantage of 3D graphics in order to present image thumbnails in cylindrical arrangements. Through a user study we evaluate the performance of these interfaces in terms of visual search time and subjective performance.}, language = {EN}, location = {Melbourne, Australia}, talkdate = {2012.07.12}, talktype = {registered} } @InProceedings{Reiners2012, author = {Reiners, René and Halvorsrud, Ragnhild and Eide, Aslak Wegner and Pohl, Daniela}, booktitle = {Proceedings of the 19th Conference on Pattern Languages of Programs (PLoP)}, title = {An Approach to Evolutionary Design Pattern Engineering}, year = {2012}, address = {New York, NY, USA}, editor = {Guerra, Eduardo}, month = {oct}, pages = {1-14}, publisher = {ACM}, abstract = {The design of interactive systems, especially in distributed research projects, is a challenging process in which many concepts are developed with successful outcomes but also with dissatisfying results. In order to structure and relay knowledge about good or bad approaches, design patterns are a well-known instrument in research and development. Due to the condition that a design pattern must be easy to read, different stakeholders in the system engineering and design process are able to understand the described concepts without the need of specific expert knowledge . In distributed projects, application design knowledge may be scattered and documented in different manners. This means, before we can start formulating patterns, we need to discover and gather the available and partially concealed design knowledge. Since these fragments of knowledge may not always be accurately formulated for being used as design patterns, we seek for a collaborative method for collecting and formulating early findings together with established design knowledge. In this paper we present a concept of an evolutionary process for capturing, formulating, refining and validating design patterns. Our approach aims at involving as many stakeholders as possible in order to shape a pattern language over a project’s lifetime in a collaborative process allowing facile participation. We implement our approach in the scope of the EU research project BRIDGE that aims at supporting inter-agency collaboration during emergency response. We close with a discussion of the current state and envisioned next steps in order to foster our considerations.}, keywords = {Design Patterns, Pattern Languages, Pattern Evolution Process, Collaboration}, language = {EN}, location = {Tucson, Arizona, USA}, pdf = {https://www.itec.aau.at/bib/files/An Approach to Evolutionary Design Pattern Engineering.pdf}, talkdate = {2012.10.20}, talktype = {registered}, url = {http://www.hillside.net/plop/2012/index.php} } @InProceedings{Rainer2012_QoMEX2012_SensoryEffects, author = {Rainer, Benjamin and Waltl, Markus and Cheng, Eva and Shujau, Muawiyath and Timmerer, Christian and Davis, Stephen and Burnett, Ian and Hellwagner, Hermann}, booktitle = {Proceedings of the 4th International Workshop on Quality of Multimedia Experience (QoMEX'12)}, title = {Investigating the Impact of Sensory Effects on the Quality of Experience and Emotional Response in Web Videos}, year = {2012}, address = {Yarra Valley, Australia}, editor = {Burnett, Ian and Wu, Henry}, month = {jul}, pages = {278--283}, publisher = {IEEE}, abstract = {Multimedia is ubiquitously available online with large amounts of video increasingly consumed through Web sites such as YouTube or Google Video. However, online multimedia typically limits users to visual/auditory stimulus, with onscreen visual media accompanied by audio. The recent introduction of MPEG-V proposed multi-sensory user experiences in multimedia environments, such as enriching video content with so-called sensory effects like wind, vibration, light, etc. In MPEG-V, these sensory effects are represented as Sensory Effect Metadata (SEM), which is additionally associated to the multimedia content. This paper presents three user studies that utilize the sensory effects framework of MPEG-V, investigating the emotional response of users and enhancement of Quality of Experience (QoE) of Web video sequences from a range of genres with and without sensory effects. In particular, the user studies were conducted in Austria and Australia to investigate whether geography and cultural differences affect users’ elicited emotional responses and QoE.}, isbn13 = {-}, keywords = {Quality of Multimedia Experience, Sensory Effects, MPEG-V, Subjective Quality Assessment, World Wide Web, Sensory Experience}, language = {EN}, location = {Yarra Valley, Australia}, pdf = {https://www.itec.aau.at/bib/files/QoMEX2012_UserStudy.pdf}, talkdate = {2012.07.07}, talktype = {registered}, url = {http://www.qomex2012.org} } @InProceedings{Rainer2012_EUSIPCO2012, author = {Rainer, Benjamin and Lederer, Stefan and Mueller, Christopher and Timmerer, Christian}, booktitle = {Proceedings of the 20th European Signal Processing Conference (EUSIPCO)}, title = {A Seamless Web Integration of Adaptive HTTP streaming}, year = {2012}, address = {Bucharest, Romania}, editor = {Pesquet-Popescu, Béatrice and Burileanu, Corneliu}, month = {aug}, pages = {1519-1523}, publisher = {European Signal Processing (EURASIP) Society}, abstract = {Nowadays video is an important part of the Web and Web sites like YouTube, Hulu, etc. count millions of users consuming their content every day. However, these Web sites mainly use media players based on proprietary browser plug-ins (i.e., Adobe Flash) and do not leverage adaptive streaming systems. This paper presents a seamless integration of the recent MPEG standard on Dynamic Adaptive Streaming over HTTP (DASH) in the Web using the HTML5 video element. Therefore, we present DASHJS, a JavaScript-based MPEG-DASH client which adopts the Media Source API of Google’s Chrome browser to present a flexible and potentially browser independent DASH client. Furthermore, we present the integration of WebM based media segments in DASH giving a detailed description of the used container format structure and a corresponding Media Presentation Description (MPD). Our preliminary evaluation demonstrates the bandwidth adaption capabilities to show the effectiveness of the system.}, language = {EN}, location = {Bucharest, Romania}, pdf = {https://www.itec.aau.at/bib/files/DASHJS-Eusipco.pdf}, talkdate = {2012.08.30}, talktype = {registered} } @InProceedings{Raffelsberger2012, author = {Raffelsberger, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the Tenth Workshop on Intelligent Solutions in Embedded Systems ({WISES '12})}, title = {Evaluation of MANET Routing Protocols in a Realistic Emergency Response Scenario}, year = {2012}, address = {Los Alamitos, CA, USA}, editor = {Quaritsch, Markus and Fehervari, Istvan}, month = {jul}, pages = {88-92}, publisher = {IEEE}, abstract = {We evaluate the performance of several routing protocols for mobile ad-hoc networks (MANETs) in an emergency response scenario. The simulated scenario uses a disaster area mobility model and a wireless shadowing model to represent realistic first responder movements in a hybrid indoor/outdoor environment. The resulting scenario imposes some challenges on the MANET routing protocols such as intermittent connectivity and network partitions. The simulation results show that nodes have diverse connectivity characteristics which are challenging for state-of-the-art MANET routing protocols.}, language = {EN}, location = {Klagenfurt, Austria}, pdf = {https://www.itec.aau.at/bib/files/WISES2012-cr.pdf}, talkdate = {2012.07.05}, talktype = {poster} } @InProceedings{RT_ICME_1, author = {Tusch, Roland and Pletzer, Felix and Kraetschmer, Armin and Böszörmenyi, Laszlo and Rinner, Bernhard and Mariacher, Thomas and Harrer, Manfred}, booktitle = {ICME '12 Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops}, title = {Efficient Level of Service Classification for Traffic Monitoring in the Compressed Video Domain}, year = {2012}, address = {Piscataway (NJ)}, editor = {Zhang, Jian and Schonfeld, Dan and Deagan, David Feng}, month = {jul}, pages = {967-972}, publisher = {IEEE}, abstract = {This paper presents a new method for estimating the level of service (LOS) on motorways in the compressed video domain. The method performs statistical computations on motion vectors of MPEG4 encoded video streams within a predefined region of interest to determine a set of four motion features describing the speed and density of the traffic stream. These features are fed into a Gaussian radial basis function network to classify the corresponding LOS. To improve the classification results, vectors of moving objects are clustered and outliers are eliminated. The proposed method is designed to be executed on a server system, where a large number of camera live streams can be analyzed in parallel in real-time. Evaluations with a comprehensive set of real-world training and test data from an Austrian motorway have shown an average accuracy of 86.7% on the test data set for classifying all four LOS levels. With a mean execution time of 48 microseconds per frame on a common server, hundreds of video streams can be analyzed in real-time.}, doi = {10.1109/ICME.2012.101}, isbn13 = {978-1-4673-1659-0}, language = {EN}, location = {Melbourne, Australia}, talkdate = {2012.07.12}, talktype = {registered} } @InProceedings{RT_ICME, author = {Tusch, Roland and Pletzer, Felix and Mudunuri, Vijay and Kraetschmer, Armin and Sabbavarapu, Karuna and Kogler, Marian and Böszörmenyi, Laszlo and Rinner, Bernhard and Harrer, Manfred and Mariacher, Thomas and Hrassnig, P}, booktitle = {ICMEW '12 Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops}, title = {LOOK2 - A Video-based System for Real-time Notification of Relevant Traffic Events.}, year = {2012}, address = {Piscataway (NJ)}, editor = {Zhang, Jian and Schonfeld, Dan and Feng, Deagan David}, month = {jul}, pages = {670}, publisher = {IEEE}, abstract = {We demonstrate our novel video-based real-time traffic event notification and verification system LOOK2. It generates fast and reliable traffic information about relevant traffic state and road conditions changes on observed roads. It utilizes installed road-side sensors providing low-level traffic and environmental data, as well as video sensors which gain high-level traffic information from live video analysis. Spatio-temporal data fusion is applied on all available traffic and environmental data to gain reliable traffic information. This traffic information is published by a DATEXII compliant web service to a web-based traffic desk application. Road network and traffic channel operators receive real-time and relevant traffic event notifications by using this application. The system also enables a visual verification of the notified situations.}, doi = {10.1109/ICMEW.2012.126}, isbn10 = {978-1-4673-2027-6}, language = {EN}, location = {Melbourne, Australia}, talkdate = {2012.07.10}, talktype = {poster} } @InProceedings{RT_AVSS_2012, author = {Pletzer, Felix and Tusch, Roland and Böszörmenyi, Laszlo and Rinner, Bernhard}, booktitle = {Proceedings of the IEEE Conference on Advanced Vision and Signal-based Surveillance}, title = {Robust traffic state estimation on smart cameras.}, year = {2012}, address = {Piscataway (NJ)}, editor = {Porikli, Fatih and Wang, Liang and Maybank, Steve}, month = {sep}, pages = {434-439}, publisher = {IEEE}, abstract = {This paper presents a novel method for video-based traffic state detection on motorways performed on smart cameras. Camera calibration parameters are obtained from the known length of lane markings. Mean traffic speed is estimated from Kanade-Lucas-Tomasi (KLT) optical flow method using a robust outlier detection. Traffic density is estimated using a robust statistical counting method. Our method has been implemented on an embedded smart camera and evaluated under different road and illumination conditions. It achieves a detection rate of more than 95% for stationary traffic.}, language = {EN}, talktype = {none}, url = {http://doi.ieeecomputersociety.org/10.1109/AVSS.2012.63} } @InProceedings{Pohl2012c, author = {Pohl, Daniela and Bouchachia, Abdelhamid and Hellwagner, Hermann}, booktitle = {11th International Conference on Machine Learning and Applications}, title = {Automatic Identification of Crisis-Related Sub-Events using Clustering}, year = {2012}, address = {Los Alamitos, CA, USA}, editor = {Han, Jiawei and Khoshgoftaar, Taghi M and Zhu, Xingquan}, month = {dec}, pages = {333-338}, publisher = {IEEE}, abstract = {Social media are becoming an important instrument for supporting crisis management, due to their broad acceptance and the intensive usage of mobile devices for accessing them. Social platforms facilitate collaboration among the public during a crisis and also support after-the-fact analysis. Thus, social media are useful for the processes of understanding, learning, and decision making. In particular, having information from social networks in a suitable, ideally summarized, form can speed up such processes. The present study relies on Flickr and YouTube as social media and aims at automatically identifying individual sub-events within a crisis situation. The study applies a two-phase clustering approach to detect those sub-events. The first phase uses geo-referenced data to locate a sub-event, while the second phase uses the natural language descriptions of pictures and videos to further identify the ”what-about” of those sub-events. The results show high potential of this social media-based clustering approach for detecting crisis-related sub-events.}, keywords = {Clustering, Sub-Event Detection, Crisis Management}, language = {EN}, location = {Boca Raton, Florida, USA}, pdf = {https://www.itec.aau.at/bib/files/06406815.pdf}, talkdate = {2012.12.12}, talktype = {registered}, url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6406815} } @InProceedings{Pohl2012b, author = {Pohl, Daniela and Bouchachia, Abdelhamid and Hellwagner, Hermann}, booktitle = {IEEE 21st International Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE)}, title = {Supporting Crisis Management via Sub-Event Detection in Social Networks}, year = {2012}, address = {Toulouse, Fance}, editor = {Diaz, Michel and Senac, Patrick}, month = {jun}, pages = {373 -378}, publisher = {IEEE}, abstract = {Social networks give the opportunity to gather and share knowledge about a situation of relevance. This so called user-generated content is getting increasingly important during crisis management. It facilitates the collaboration with citizens or parties involved from the very beginning of the crisis. The information captured in form of images, text or videos is a valuable source of identifying sub-events of a crisis. In this study, we use metadata of images and videos collected from Flickr and YouTube to extract sub-events in crisis situations. We investigate the suitability of clustering techniques to detect sub-events. In particular two algorithms are evaluated on several data sets related to crisis situations. The results show the high potential of the approach proposed.}, doi = {10.1109/WETICE.2012.58}, issn = {1524-4547}, keywords = {Crisis Management, Information Retrieval, Clustering, Sub-Event Detection}, language = {EN}, location = {Toulouse, Fance}, talkdate = {2012.06.26}, talktype = {registered} } @InProceedings{Pohl2012a, author = {Pohl, Daniela and Bouchachia, Abdelhamid and Hellwagner, Hermann}, booktitle = {Proceedings of the 21st International Conference Companion on World Wide Web}, title = {Automatic Sub-Event Detection in Emergency Management using Social Media}, year = {2012}, address = {New York, NY, USA}, editor = {Mille, Alain and Gandon, Fabien and Misselis, Jacques}, month = {apr}, pages = {683--686}, publisher = {ACM}, series = {WWW '12 Companion}, abstract = {Emergency management is about assessing critical situations, followed by decision making as a key step. Clearly, information is crucial in this two-step process. The technology of social (multi)media turns out to be an interesting source for collecting information about an emergency situation. In particular, situational information can be captured in form of pictures, videos, or text messages. The present paper investigates the application of multimedia metadata to identify the set of sub-events related to an emergency situation. The used metadata is compiled from Flickr and YouTube during an emergency situation, where the identification of the events relies on clustering. Initial results presented in this paper show how social media data can be used to detect different sub-events in a critical situation.}, keywords = {Emergency Management, Social Media, Clustering}, language = {EN}, location = {Lyon, France}, pdf = {https://www.itec.aau.at/bib/files/p683.pdf}, talkdate = {2012.04.17}, talktype = {registered} } @InProceedings{Muller2012, author = {Müller, Alexander and Lux, Mathias and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 12th International Conference on Knowledge Management and Knowledge Technologies}, title = {The video summary GWAP: summarization of videos based on a social game}, year = {2012}, address = {New York, NY, USA}, editor = {Lindstaedt, Stefanie and Granitzer, Michael}, month = {jan}, pages = {15:1--15:7}, publisher = {ACM}, series = {i-KNOW '12}, doi = {10.1145/2362456.2362476}, keywords = {games with a purpose, human computation, video retrieval, video summarization}, language = {EN}, talktype = {none}, url = {http://doi.acm.org/10.1145/2362456.2362476} } @InProceedings{MuellerICME2012, author = {Mueller, Christopher and Smole, Martin and Schoeffmann, Klaus}, booktitle = {Proceedings of the IEEE International Conference on Multimedia and Expo (ICME 2012)}, title = {A Demonstration of A Hierarchical Multi-Layout 3D Video Browser}, year = {2012}, address = {Los Alamitos, CA, USA}, editor = {Zhang, Jian and Schonfeld, Dan and Feng, David Dagan and Nanyang, Jianfei Cai and Hanjalic, Alan and Magli, Enrico and Pickering, Mark and Friedland, Gerald and Hua, Xian-Sheng}, month = {jul}, pages = {665}, publisher = {IEEE Computer Society}, abstract = {This paper demonstrates a novel 3D Video Browser (3VB) that enables interactive search within a single video as well as video collections by utilizing 3D projection and an intuitive interaction. The browsing approach is based on hierarchical search, which means that the user can split a video into several segments. The 3VB disposes a convenient interface that allows flexible arrangement of video segments in the 3D space. It allows for concurrent playback of video segments and flexible inspection of these segments at any desired level of detail through convenient user interaction.}, language = {EN}, location = {Melbourne, Australia}, pdf = {https://www.itec.aau.at/bib/files/A_Demo_of_a_Hierarchical_Multi-Layout_3D_Video_Browser.pdf}, talkdate = {2012.07.10}, talktype = {registered} } @InProceedings{Mueller2012b, author = {Mueller, Christopher and Renzi, Daniele and Lederer, Stefan and Battista, Stefano and Timmerer, Christian}, booktitle = {Proceedings of the 20th European Signal Processing Conference (EUSIPCO12)}, title = {Using Scalable Video Coding for Dynamic Adaptive Streaming over HTTP in Mobile Environments}, year = {2012}, address = {Bucharest, Romania}, editor = {Burileanu, Corneliu and Pesquet-Popescu, Béatrice}, month = {aug}, pages = {2208-2212}, publisher = {European Signal Processing (EURASIP) Society}, abstract = {Dynamic Adaptive Streaming over HTTP (DASH) is a convenient approach to transfer videos in an adaptive and dynamic way to the user. As a consequence, this system provides high bandwidth flexibility and is especially suitable for mobile use cases where the bandwidth variations are tremendous. In this paper we have integrated the Scalable Video Coding (SVC) extensions of the Advanced Video Coding (AVC) standard into the recently ratified MPEG-DASH standard. Furthermore, we have evaluated our solution under restricted conditions using bandwidth traces from mobile environments and compared it with an improved version of our MPEG-DASH implementation using AVC as well as major industry solutions.}, keywords = {Dynamic Adaptive Streaming over {HTTP}, {MPEG-DASH}, Scalable Video Coding, Evaluation, Mobile Networks, Vehicular Mobility}, language = {EN}, location = {Bucharest, Romania}, pdf = {https://www.itec.aau.at/bib/files/mueller_svc-dash.pdf}, talkdate = {2012.08.31}, talktype = {registered} } @InProceedings{Mueller2012a, author = {Mueller, Christopher and Lederer, Stefan and Timmerer, Christian}, booktitle = {Proceedings of the Fourth Annual ACM SIGMM Workshop on Mobile Video (MoVid12)}, title = {An Evaluation of Dynamic Adaptive Streaming over HTTP in Vehicular Environments}, year = {2012}, address = {New York, NY, USA}, editor = {Hefeeda, Mohamed and Hsu, Cheng-Hsin and Chatterjee, Mainak and Venkatasubramanian, Nalini and Ganguly, Samrat}, month = {feb}, pages = {37-42}, publisher = {ACM}, abstract = {MPEGs' Dynamic Adaptive Streaming over HTTP (MPEG-DASH) is an emerging standard designed for media delivery over the top of existing infrastructures and able to handle varying bandwidth conditions during a streaming session. This requirement is very important, specifically within mobile environments and, thus, DASH could potentially become a major driver for mobile multimedia streaming. Hence, this paper provides a detailed evaluation of our implementation of MPEG DASH compared to the most popular propriety systems, i.e., Microsoft Smooth Steaming, Adobe HTTP Dynamic Streaming, and Apple HTTP Live Streaming. In particular, these systems will be evaluated under restricted conditions which are due to vehicular mobility. In anticipation of the results, our prototype implementation of MPEG-DASH can very well compete with state-of-the-art solutions and, thus, can be regarded as a mature standard ready for industry adaption.}, keywords = {Dynamic Adaptive Streaming over HTTP, MPEG-DASH, Microsoft Smooth Streaming, Adobe HTTP Dynamic Streaming, Evaluation, Apple HTTP Live Streaming, Mobile Networks, Vehicular Mobility}, language = {EN}, location = {Chapel Hill, North Carolina, USA}, pdf = {https://www.itec.aau.at/bib/files/p37-mueller.pdf}, talkdate = {2012.02.24}, talktype = {registered} } @InProceedings{Mueller2012VCIP, author = {Mueller, Christopher and Lederer, Stefan and Timmerer, Christian}, booktitle = {Proceedings of the IEEE Conference on Visual Communications and Image Processing Conference (VCIP 2012)}, title = {A Proxy Effect Analysis and Fair Adaptation Algorithm for Multiple Competing Dynamic Adaptive Streaming over HTTP Clients}, year = {2012}, address = {San Diego, CA, USA}, editor = {Aizawa, Kiyoharu and Kuo, Jay and Liu, Zicheng}, month = {nov}, pages = {6}, publisher = {IEEE}, abstract = {Multimedia streaming technologies based on the Hypertext Transfer Protocol (HTTP) are very popular and used by many content providers such as Netflix, Hulu, and Vudu. Recently, ISO/IEC MPEG has ratified Dynamic Adaptive Streaming over HTTP (DASH) which extends the traditional HTTP streaming with an adaptive component addressing the issue of varying bandwidth conditions that users are facing in networks based on the Internet Protocol (IP). Additionally, industry has already deployed several solutions based on such an approach which simplifies large scale deployment because the whole streaming logic is located at the client. However, these features may introduce drawbacks when multiple clients compete for a network bottleneck due to the fact that the clients are not aware of the network infrastructure such as proxies or other clients. This paper identifies these negative effects and the evaluation thereof using MPEG-DASH and Microsoft Smooth Streaming. Furthermore, we propose a novel adaptation algorithm introducing the concept of fairness regarding a cluster of clients. In anticipation of the results we can conclude that we achieve more efficient bottleneck bandwidth utilization and less quality switches.}, language = {EN}, location = {San Diego, USA}, pdf = {https://www.itec.aau.at/bib/files/PID2500949.pdf}, talkdate = {2012.11.29}, talktype = {registered}, url = {http://www.vcip2012.org} } @InProceedings{Mueller2012, author = {Lederer, Stefan and Mueller, Christopher and Timmerer, Christian}, booktitle = {Proceedings of the Third Annual {ACM SIGMM} Conference on Multimedia Systems ({MMSys12})}, title = {Dynamic Adaptive Streaming over {HTTP} Dataset}, year = {2012}, address = {New York, NY, USA}, editor = {Claypool, Mark and Griwodz, Carsten and Mayer-Patel, Ketan}, month = {feb}, pages = {89-94}, publisher = {ACM}, abstract = {Adaptive HTTP streaming got lot of attention in recent years and with dynamic adaptive streaming over HTTP (DASH) a standard is available. Many papers cover this topic and present their research results, but unfortunately all of them use their own private dataset which – in most cases – is not publicly available. Hence, it is difficult to compare, e.g., adaptation algorithms in an objective way due to the lack of a common dataset which shall be used as basis for such experiments. In this paper, we present our DASH dataset featuring our DASHEncoder, an open source DASH content generation tool. We also provide basic evaluations of the different segment lengths, the influence of HTTP server settings, and, in this context, we show some of the advantages as well as problems of shorter segment lengths.}, keywords = {Dynamic Adaptive Streaming over HTTP, DASH, Dataset, Encoder, Content Generation Tool}, language = {EN}, location = {Chapel Hill, North Carolina, USA}, pdf = {https://www.itec.aau.at/bib/files/p89-lederer.pdf}, talkdate = {2012.02.22}, talktype = {registered} } @InProceedings{Marques2012, author = {Marques, Oge and Lux, Mathias}, booktitle = {Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval}, title = {Visual information retrieval using Java and LIRE}, year = {2012}, address = {New York, NY, USA}, editor = {Hersh, William and Callan, Jamie and Maarek, Yoelle and Sanderson, Mark}, month = {jan}, pages = {1193--1193}, publisher = {ACM}, series = {SIGIR '12}, doi = {10.1145/2348283.2348538}, keywords = {content-based image retrieval, image search, java, visual information retrieval}, language = {EN}, location = {Portland, Oregon, USA}, talkdate = {2012.08.12}, talktype = {registered}, url = {http://doi.acm.org/10.1145/2348283.2348538} } @InProceedings{Lux2012b, author = {Lux, Mathias and Taschwer, Mario and Marques, Oge}, booktitle = {Proceedings of the 20th ACM international conference on Multimedia}, title = {Classification of photos based on good feelings: ACM MM 2012 multimedia grand challenge submission}, year = {2012}, address = {New York, NY, USA}, editor = {Aizawa, Kiyoharu and Babaguchi, Noboru and Smith, John}, month = {jan}, pages = {1367--1368}, publisher = {ACM}, series = {MM '12}, doi = {10.1145/2393347.2396488}, keywords = {affection, image classification, image search, user intentions}, language = {EN}, location = {Nara, Japan}, talkdate = {2012.11.01}, talktype = {registered}, url = {http://doi.acm.org/10.1145/2393347.2396488} } @InProceedings{Lux2012a, author = {Lux, Mathias and Taschwer, Mario and Marques, Oge}, booktitle = {Proceedings of the ACM multimedia 2012 workshop on Crowdsourcing for multimedia}, title = {A closer look at photographers' intentions: a test dataset}, year = {2012}, address = {New York, NY, USA}, editor = {Aizawa, Kiyoharu and Babaguchi, Noboru and Smith, John}, month = {jan}, pages = {17--18}, publisher = {ACM}, series = {CrowdMM '12}, doi = {10.1145/2390803.2390811}, keywords = {digital photos, user intentions}, language = {EN}, location = {Nara, Japan}, talkdate = {2012.10.29}, talktype = {registered}, url = {http://doi.acm.org/10.1145/2390803.2390811} } @InProceedings{Lux2012, author = {Lux, Mathias and Guggenberger, Mario and Müller, Alexander}, booktitle = {Proceedings of the Eighth Artificial Intelligence and Interactive Digital Entertainment International Conference (AIIDE 2012)}, title = {Finding Image Regions with Human Computation and Games with a Purpose}, year = {2012}, address = {Palo Alto, California, USA}, editor = {Riedl, Mark and Sukthankar, Gita}, month = {jan}, pages = {220}, publisher = {Association for the Advancement of Artificial Intelligence (AAAI Press)}, abstract = {Manual image annotation is a tedious and time-consuming task, while automated methods are error prone and limited in their results. Human computation, and especially games with a purpose, have shown potential to create high quality annotations by "hiding the complexity" of the actual annotation task and employing the "wisdom of the crowds". In this demo paper we present two games with a single purpose: finding regions in images that correspond to given terms. We discuss approach, implementation, and preliminary results of our work and give an outlook to immediate future work.}, isbn10 = {978-1-57735-582-3}, keywords = {Games with a Purpose; Human Computation}, language = {EN}, talktype = {none}, url = {http://www.aaai.org/ocs/index.php/AIIDE/AIIDE12/paper/view/5474} } @InProceedings{Lederer2012c, author = {Liu, Yaning and Geurts, Joost and Rainer, Benjamin and Lederer, Stefan and Mueller, Christopher and Timmerer, Christian}, booktitle = {CCNx Community Meeting (CCNxConn 2012)}, title = {DASH over CCN: A CCN use-case for a Social Media based collaborative project}, year = {2012}, address = {Sophia Antipolis}, editor = {Carofiglio, Giovanna}, month = {sep}, pages = {1-1}, publisher = {Parc}, keywords = {CCN, DASH}, language = {EN}, location = {Sophia Antipolis, France}, pdf = {https://www.itec.aau.at/bib/files/DashOverCCN.pdf}, talkdate = {2012.09.12}, talktype = {registered}, url = {http://www.ccnx.org/ccnxcon2012/} } @InProceedings{Lederer2012b, author = {Lederer, Stefan and Mueller, Christopher and Rainer, Benjamin and Waltl, Markus and Timmerer, Christian}, booktitle = {Proceedings of the IEEE Conference on Visual Communications and Image Processing Conference (VCIP 2012)}, title = {An open source MPEG DASH evaluation suite}, year = {2012}, address = {San Diego, CA, USA}, editor = {Izquierdo, Ebroul and Wang, Xin}, month = {nov}, pages = {1-1}, publisher = {IEEE}, abstract = {In this paper we demonstrate our MPEG-DASH evaluation suite, which comprises several components on the client side as well as on the server side. The major client components are the VLC DASH plugin, libDASH, and DASH-JS, a JavaScript-based DASH client. These tools enable performance tests on various platforms, e.g., Windows and Linux as well as mobile platforms such as Android. Moreover, due to their flexible structure it is possible to integrate adaptation logics and evaluate them under consistent conditions. On the server side we provide the content generation tool DASHEncoder, our MPEG-DASH datasets well as the MPEG-DASH conformance validator.}, keywords = {MPEG DASH, Open Source, Demo}, language = {EN}, location = {San Diego, USA}, pdf = {https://www.itec.aau.at/bib/files/open-source_MPEG-DASH_evaluation_suite.pdf}, talkdate = {2012.11.29}, talktype = {registered}, url = {http://www.vcip2012.org} } @InProceedings{Lederer2012, author = {Lederer, Stefan and Mueller, Christopher and Timmerer, Christian}, booktitle = {Proceedings of the 19th International Packet Video Workshop ({PV} 2012)}, title = {Towards Peer-Assisted Dynamic Adaptive Streaming over HTTP}, year = {2012}, address = {Munich, Germany}, editor = {Guillemot, Christine and Chakareski, Jacob and Steinbach, Eckehard}, month = {may}, pages = {1-6}, publisher = {IEEE}, abstract = {This paper presents our peer-assisted Dynamic Adaptive Streaming over HTTP (pDASH) proposal as well as an evaluation based on our DASH simulation environment in comparison to conventional approaches, i.e., non-peer-assisted DASH. Our approach maintains the standard conformance to MPEG-DASH enabling an easy and straightforward way of enhancing a streaming system with peer assistance to reduce the bandwidth and infrastructure requirements of the content/service provider. In anticipation of the results our system achieves a bandwidth reduction of Content Distribution Networks (CDN) and as a consequence the corresponding infrastructure costs of the content/service providers by up to 25% by leveraging the upstream capacity of neighboring peers. Furthermore, the cost savings have been evaluated using a cost model that is based on the current Amazon CloudFront pricing scheme. Furthermore, we have also evaluated the performance impact that various combinations of quality levels of the content could have in a peer-assisted streaming system as well as the client behavior in such an environment.}, keywords = {Peer-Assisted Streaming, MPEG-DASH, Dynamic Adaptive Streaming over HTTP, CDN Bandwidth Reduction, Peer-to-Peer Streaming.}, language = {EN}, location = {Munich, Germany}, pdf = {https://www.itec.aau.at/bib/files/Paper53.pdf}, talkdate = {2012.05.10}, talktype = {registered} } @InProceedings{Kuschnig2012a, author = {Kuschnig, Robert and Yanmaz, Evsen and Kofler, Ingo and Rinner, Bernhard and Hellwagner, Hermann}, booktitle = {Proceedings of the Austrian Robotics Workshop (ARW-12)}, title = {{Profiling IEEE 802.11 Performance on Linux-based UAVs}}, year = {2012}, address = {Graz, Austria}, editor = {Gerald Steinbauer, Suzana Uran}, month = {may}, pages = {6}, publisher = {Graz University of Technology}, language = {EN}, location = {Graz, Austria}, pdf = {https://www.itec.aau.at/bib/files/Kuschnig_ARW2012.pdf}, talktype = {none} } @InProceedings{Kogler2012, author = {Kogler, Marian and Lux, Mathias}, booktitle = {i-KNOW '12 Proceedings of the 12th International Conference on Knowledge Management and Knowledge Technologies}, title = {Robust image retrieval using bag of visual words with fuzzy codebooks and fuzzy assignment}, year = {2012}, address = {New York, NY, USA}, editor = {Lindstaedt, Stefanie}, month = {jan}, pages = {34.1 - 34.4}, publisher = {ACM}, series = {i-KNOW '12}, abstract = {Content-based retrieval systems leverage low level features such as color, texture or local information of images to find similar images to a respective query image. In recent years the Bag of Visual Words (BoVW) approach, which relies on quantized visual information around local image patches, has gained importance in image retrieval. In this paper we focus on fuzzy algorithms, in order to improve the descriptiveness of image descriptors. We extend the BoVW approach by applying fuzzy clustering and fuzzy assignment to take a step towards more effective visual descriptors, which are matched against each other in content-based similarity searches.}, doi = {10.1145/2362456.2362498}, keywords = {bag of visual words, content based image retrieval, fuzzy, visual information retrieval}, language = {EN}, talktype = {none}, url = {http://doi.acm.org/10.1145/2362456.2362498} } @InProceedings{Kofler2012, author = {Kofler, Ingo and Kuschnig, Robert and Hellwagner, Hermann}, booktitle = {Proceedings of the 9th {IEEE} Consumer Communications and Networking Conference ({CCNC})}, title = {Implications of the {ISO Base Media File Format} on Adaptive {HTTP} Streaming of {H.264/SVC}}, year = {2012}, address = {Los Alamitos, CA, USA}, editor = {Shirazi, Behrooz}, month = {jan}, pages = {5}, publisher = {IEEE}, abstract = {HTTP streaming has gained significant attraction in the last few years. Currently many commercial as well as standardized streaming systems are already offering adaptive streaming. In most cases, the adaptation is achieved by switching between separately encoded video streams in different qualities. In contrast to that, this paper focuses on the applicability of scalable video coding based on the H.264/SVC standard for adaptive HTTP streaming. Recent work has already highlighted the conceptual advantages like better cache utilization, fine-grained bit rate scalability, and lower storage requirements. This paper discusses the actual realization and design options for implementing priority streaming using the ISO~Base Media File Format (BMFF). We propose three different strategies for organizing the scalable video bit stream that consider both the possibilities as well as limitations of the ISO BMFF. The proposed strategies are discussed and evaluated both conceptually and quantitatively. For that purpose, we provide a detailed analysis based on modeling both the overhead of the file format and the HTTP encapsulation. The results for all three priority streaming strategies show that the limitations of the ISO BMFF result in a high relative overhead in the case of low bit rate content. However, when applied to high quality content, priority streaming of H.264/SVC can be implemented at a very low cost. Depending on the number of layers and the offered scalability dimensions, different strategies should be chosen to minimize the overhead. Based on the analytical model and the discussion, this paper provides guidance for selecting the most efficient strategy.}, language = {EN}, location = {Las Vegas, NV, USA}, pdf = {https://www.itec.aau.at/bib/files/Kofler_PriorityStreamingISOBMFF_preprint.pdf}, talkdate = {2012.01.14}, talktype = {registered}, url = {http://www.ieee-ccnc.org/2012/} } @InProceedings{Grafl2012_TEMU, author = {Grafl, Michael and Timmerer, Christian and Waltl, Markus and Xilouris, George and Zotos, Nikolaos and Renzi, Daniele and Battista, Stefano and Chernilov, Alex}, booktitle = {Proceedings of the 2012 {IEEE} International Conference on Telecommunications and Multimedia ({TEMU} 2012)}, title = {Distributed Adaptation Decision-Taking Framework and Scalable Video Coding Tunneling for Edge and In-Network Media Adaptation}, year = {2012}, address = {Los Alamitos, CA, USA}, editor = {Pallis, Evangelos and Zacharopoulos, Vassilios and Kourtis, Anastasios}, month = {jul}, pages = {6}, publisher = {IEEE}, series = {TEMU}, abstract = {Existing and future media ecosystems need to cope with the ever-increasing heterogeneity of networks, devices, and user characteristics collectively referred to as (usage) context. The key to address this problem is media adaptation to various and dynamically changing contexts in order to provide a service quality that is regarded as satisfactory by the end user. The adaptation can be performed in many ways and at different locations, e.g., at the edge and within the network resulting in a substantial number of issues to be integrated within a media ecosystem. This paper describes research challenges, key innovations, target research outcomes, and achievements so far for edge and in-network media adaptation by introducing the concept of Scalable Video Coding (SVC) tunneling.}, doi = {http://dx.doi.org/10.1109/TEMU.2012.6294710}, keywords = {distributed adaptation decision-taking; SVC tunneling; research challenges; in-network adaptation; content-aware networking}, language = {EN}, location = {Heraklion, Greece}, pdf = {https://www.itec.aau.at/bib/files/TEMU2012_mgrafl.pdf}, talkdate = {2012.07.31}, talktype = {registered} } @InProceedings{Eberhard2012b, author = {Eberhard, Michael and Kumar, Amit and Mapelli, Licio and Palo, Andi and Petrocco, Riccardo and Uitto, Mikko}, booktitle = {Proceedings of the ACM Multimedia Systems Conference}, title = {NextSharePC: An Open-Source BitTorrent-based P2P Client Supporting SVC}, year = {2012}, address = {New York, U.S.A.}, editor = {Griwodz, Carsten}, month = {feb}, pages = {1-6}, publisher = {ACM}, language = {EN}, location = {Chapel Hill, North Carolina, U.S.A.}, pdf = {https://www.itec.aau.at/bib/files/next_share_pc.pdf}, talkdate = {2012.02.22}, talktype = {registered} } @InProceedings{Eberhard2012a, author = {Eberhard, Michael and Petrocco, Riccardo and Hellwagner, Hermann and Timmerer, Christian}, booktitle = {Proceedings of the Consumer Communication \& Networking Conference 2012}, title = {Comparison of Piece-Picking Algorithms for Layered Video Content in Peer-to-Peer Networks}, year = {2012}, address = {Los Alamitos, CA, U.S.A.}, editor = {Shirazi, Behrooz}, month = {jan}, pages = {1-5}, publisher = {IEEE}, language = {EN}, location = {Las Vegas, U.S.A.}, pdf = {https://www.itec.aau.at/bib/files/ccnc_pp_evaluation.pdf}, talkdate = {2012.01.15}, talktype = {registered} } @InProceedings{DelFabro2012c, author = {Del Fabro, Manfred and Lux, Mathias and Schoeffmann, Klaus and Taschwer, Mario}, booktitle = {Proceedings of TRECVID 2012}, title = {ITEC-UNIKLU Known-Item Search Submission 2012}, year = {2012}, address = {Gaithersburg, USA}, editor = {Over, Paul and Awad, George and Michel, Martial and Fiscus, Jonathan and Sanders, Greg and Shaw, Barbara and Kraaij, Wessel and Smeaton, Alan and Quénot, Georges}, month = {nov}, pages = {11}, publisher = {National Institute of Standards and Technology (NIST)}, abstract = {In this report we describe our approach to the known-item search task for TRECVID~2012. We describe how we index available metadata and how we gain additional information about the videos using content-based analysis. A rule-based query expansion and query reduction method is applied to increase the number of relevant videos in automatic runs. Furthermore, we describe an approach for quick, interactive filtering of large result sets. We outline how the parameters of our system were tuned for the IACC dataset and discuss our TRECVID 2012 KIS results.}, language = {EN}, location = {Gaithersburg, USA}, talkdate = {2012.11.28}, talktype = {poster}, url = {http://www-nlpir.nist.gov/projects/tvpubs/tv.pubs.org.html} } @InProceedings{DelFabro2012b, author = {Del Fabro, Manfred and Sobe, Anita and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the Fourth International Conferences on Advances in Multimedia (MMEDIA 2012)}, title = {Summarization of Real-Life Events Based on Community-Contributed Content}, year = {2012}, address = {France}, editor = {Davies, Philip and Newell, David}, month = {apr}, pages = {119--126}, publisher = {IARIA}, abstract = {In this paper, we investigate whether community-contributed multimedia content can be used to make video summaries of social events. We implemented an event summarization algorithm that uses photos from Flickr and videos from YouTube to compose summaries of well-known society events, which took place in the last three years. The comparison with a manually obtained ground truth shows a good coverage of the most important situations of these events. We do not claim to produce the best summaries possible, which may be compared to the work of a human director, but we analyze what can be achieved with community-contributed content by now.}, isbn13 = {978-1-61208-195-3}, keywords = {video summarization. event summarization. social media. real-life events. video retrieval. image retrieval. multimedia entertainment.}, language = {EN}, location = {Chamonix Mont-Blanc, France}, pdf = {https://www.itec.aau.at/bib/files/mmedia_2012_6_30_40058.pdf}, talkdate = {2012.05.02}, talktype = {registered}, url = {http://www.thinkmind.org/download.php?articleid=mmedia_2012_6_30_40058} } @InProceedings{DelFabro2012a, author = {Del Fabro, Manfred and Böszörmenyi, Laszlo}, booktitle = {Advances in Multimedia Modeling}, title = {{AAU} Video Browser: Non-Sequential Hierarchical Video Browsing without Content Analysis}, year = {2012}, address = {Berlin, Heidelberg, New York}, editor = {Schoeffmann, Klaus and Merialdo, Bernard and Hauptmann, Alexander and Ngo, Chong-Wah and Andreopoulos, Yiannis and Breiteneder, Christian}, month = {jan}, pages = {639--641}, publisher = {Springer}, abstract = {We participate in the Video Browser Showdown with our easy-to-use video browsing tool. It can be used for getting a quick overview of videos as well as for simple Known Item Search (KIS) tasks. It offers a parallel and a tree-like browsing interface for navigating through the content of single videos or even small video collections in a hierarchical, non-sequential manner. We want to validate whether simple KIS tasks can be completed without a time consuming content analysis in advance.}, doi = {10.1007/978-3-642-27355-1_63}, language = {EN}, location = {Klagenfurt, Austria}, pdf = {https://www.itec.aau.at/bib/files/delfabro_mmm2012_VBS.pdf}, talkdate = {2012.01.06}, talktype = {poster} } @InProceedings{DelFabro2012, author = {Del Fabro, Manfred and Böszörmenyi, Laszlo}, booktitle = {Advances in Multimedia Modeling}, title = {Summarization and Presentation of Real-Life Events Using Community-Contributed Content}, year = {2012}, address = {Berlin, Heidelberg, New York}, editor = {Schoeffmann, Klaus and Merialdo, Bernard and Hauptmann, Alexander and Ngo, Chong-Wah and Andreopoulos, Yiannis and Breiteneder, Christian}, month = {jan}, pages = {630--632}, publisher = {Springer}, abstract = {We present an algorithm for the summarization of social events with community-contributed content from Flickr and YouTube. A clustering algorithm groups content related to the searched event. Date information, GPS coordinates, user ratings and visual features are used to select relevant photos and videos. The composed event summaries are presented with our video browser.}, doi = {10.1007/978-3-642-27355-1_60}, language = {EN}, location = {Klagenfurt, Austria}, pdf = {https://www.itec.aau.at/bib/files/submission_145.pdf}, talkdate = {2012.01.05}, talktype = {poster} } @InProceedings{AhlstroemICME2012, author = {Ahlström, David and Schoeffmann, Klaus}, booktitle = {Proceedings of the 2012 {IEEE} International Conference on Multimedia and Expo Workshops}, title = {A Visual Search User Study on the Influences of Aspect Ratio Distortion of Preview Thumbnails}, year = {2012}, address = {Los Alamitos, CA, USA}, editor = {Zhang, Jian and Schonfeld, Dan and Feng, David Dagan and Nanyang, Jianfei Cai and Hanjalic, Alan and Magli, Enrico and Pickering, Mark and Friedland, Gerald and Hua, Xian-Sheng}, month = {jul}, pages = {546-551}, publisher = {IEEE Computing Society}, language = {EN}, location = {Melbourne, Australia}, talkdate = {2012.07.13}, talktype = {registered} } @InProceedings{ACM2012, author = {Ahlström, David and Hudelist, Marco Andrea and Schoeffmann, Klaus and Schaefer, Gerald}, booktitle = {Proceedings of the 20th ACM international conference on Multimedia}, title = {A User Study on Image Browsing on Touchscreens}, year = {2012}, address = {New York, USA}, editor = {Babaguchi, Noboru and Aizawa, Kiyoharu and Smith, John}, month = {nov}, pages = {pp. 925-928}, publisher = {ACM Digital Library}, abstract = {Default image browsing interfaces on touch-based mobile devices provide limited support for image search tasks. To facilitate fast and convenient searches we propose an alternative interface that takes advantage of 3D graphics and arranges images on a rotatable globe according to color similarity. In a user study we compare the new design to the iPad's image browser. Results collected from 24 participants show that for color-sorted image collections the globe can reduce search time by 23% without causing more errors and that it is perceived as being fun to use and preferred over the standard browsing interface by 70% of the participants.}, isbn10 = {978-1-4503-1089-5}, language = {EN}, location = {Nara, Japan}, talkdate = {2012.10.31}, talktype = {registered}, url = {http://dl.acm.org/citation.cfm?id=2393347&coll=DL&dl=ACM&CFID=159013035&CFTOKEN=94655035} } @InProceedings{schoeffmann2011mmm, author = {Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 17th International Conference on Multimedia Modeling}, title = {Video Sequence Identification in TV Broadcasts}, year = {2011}, address = {Taipeh}, editor = {Lee, Kuo-Tien and Tsai, Wen-Hsiang and Liao, Hong-Yuan and Chen, Tsuhan and Hsieh, Jun-Wei and Tseng, Chien-Cheng}, month = {jan}, note = {10.1007/978-3-642-17832-0_13}, pages = {129-139}, publisher = {Springer Berlin / Heidelberg}, series = {Lecture Notes in Computer Science}, volume = {6523}, language = {EN}, location = {Taipeh, Taiwan}, talkdate = {2011.1.5}, talktype = {registered}, url = {http://dx.doi.org/10.1007/978-3-642-17832-0_13} } @InProceedings{kogler2011, author = {Kogler, Marian and Lux, Mathias and Marques, Oge}, booktitle = {In Proceedings of the Workshop on Multimedia on the Web (MMWeb) 2011}, title = {Adaptive Visual Information Retrieval by changing visual vocabulary sizes in context of user intentions}, year = {2011}, address = {Graz}, editor = {","}, month = {sep}, pages = {3}, publisher = {IEEE}, language = {EN}, location = {Graz}, talkdate = {2011.09.08}, talktype = {poster} } @InProceedings{Yanmaz2011a, author = {Yanmaz, Evsen and Kuschnig, Robert and Bettstetter, Christian}, booktitle = {Proceedings of the GlobeCom 2010 (Wi-UAV Workshop)}, title = {Channel Measurements Over 802.11a-Based UAV-to-Ground Links}, year = {2011}, address = {Piscataway, NJ, USA}, editor = {How, Jonathan and Wietfeld, Christian}, month = {dec}, pages = {5}, publisher = {IEEE}, abstract = {The distribution of audio-visual content over the Internet has become very popular in recent years. However, due to the bandwidth requirements of videos in high definition, a costefficient distribution is desirable. In this paper we present a low-cost consumer electronics set-top box for streaming live video content using cost-efficient P2P networks. The main features of the set-top box include content discovery, highquality playback, easy user management, and social interaction.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/WIUAV2011_Yanmaz.pdf}, talktype = {none} } @InProceedings{Yanmaz2011, author = {Yanmaz, Evsen and Kuschnig, Robert and Quaritsch, Markus and Bettstetter, Christian and Rinner, Bernhard}, booktitle = {Proceedings of the {IEEE} Conference on Computer Communications Workshops, {INFOCOM M2MCN}, 2011}, title = {On Path Planning Strategies for Networked Unmanned Aerial Vehicles}, year = {2011}, address = {Piscataway, NJ, USA}, editor = {Ni, Lionel and Zhang, Wenjun}, month = {apr}, pages = {212--216}, publisher = {{IEEE}}, abstract = {The distribution of audio-visual content over the Internet has become very popular in recent years. However, due to the bandwidth requirements of videos in high definition, a costefficient distribution is desirable. In this paper we present a low-cost consumer electronics set-top box for streaming live video content using cost-efficient P2P networks. The main features of the set-top box include content discovery, highquality playback, easy user management, and social interaction.}, language = {EN}, location = {Shanghai, China}, pdf = {https://www.itec.aau.at/bib/files/p212-yanmaz.pdf}, talkdate = {2011.04.15}, talktype = {registered} } @InProceedings{Wieser2011c, author = {Wieser, Stefan and Böszörmenyi, Laszlo}, booktitle = {2011 IEEE International Symposium on Network Computing and Applications (NCA2011)}, title = {Decentralized topology aggregation for {QoS} estimation in large overlay networks}, year = {2011}, address = {Cambridge, USA}, editor = {Rasmus Løvenstein, Olsen and Paolo, Romano and Tatsuhiro, Tsuchiya}, month = {aug}, pages = {298-302}, publisher = {IEEE}, abstract = {This paper introduces a scalable approach for efficient, low-cost multi-level Quality of Service (QoS) estimation in large overlay networks (ON). We modify an existing distributed partitioning algorithm [1], and use it to create ”QoS maps”. QoS maps empower applications to quickly predict several QoS metrics for any given route, and to obtain multiple alternative routes to any target node in the ON. We show that our modifications of the partitioning algorithm permit the aggregation of large hubs, but still preserve the sublinear runtime of the original heuristic. Simulations with large ONs are performed to evaluate the proposed approach and demonstrate its scalability. Finally, we outline our estimation algorithm that we use to predict QoS and perform QoS aware routing in any given ON.}, language = {EN}, location = {Cambridge, USA}, pdf = {https://www.itec.aau.at/bib/files/NCA2011.pdf}, talkdate = {2011.08.25}, talktype = {registered} } @InProceedings{Waltl2011_WoWMoM, author = {Waltl, Markus}, booktitle = {Proceedings of the 12th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)}, title = {The Next Dimension of Video Experience: Sensory Effects}, year = {2011}, address = {Los Alamitos, CA, USA}, editor = {Gerla, Mario and Mingozzi, Enzo and Chatterjee, Mainak and Passarella, Andrea}, month = {jun}, pages = {3}, publisher = {IEEE}, abstract = {This work presents a new dimension for Quality of Experience (QoE), i.e., sensory information. Sensory information enhances the user experience by providing additional so-called sensory effects (e.g., wind, light, vibration) which are rendered together with multimedia content. Furthermore, the work describes two subjective quality assessments conducted in this area including their results.}, doi = {10.1109/WoWMoM.2011.5986375}, keywords = {Sensory Information, MPEG-V, Subjective Quality Assessments, Quality of Experience}, language = {EN}, location = {Lucca, Italy}, pdf = {https://www.itec.aau.at/bib/files/wowmom2011_mw.pdf}, talkdate = {2011.06.22}, talktype = {poster} } @InProceedings{Waltl2011_MMWeb, author = {Waltl, Markus and Rainer, Benjamin and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the Workshop on Multimedia on the Web (MMWeb) 2011}, title = {Sensory Experience for Videos on the Web}, year = {2011}, address = {Los Alamitos, CA, USA}, editor = {Böszörmenyi, Laszlo and Marques, Oge and Lux, Mathias and Klamma, Ralf}, month = {sep}, pages = {1--3}, publisher = {IEEE}, abstract = {More and more multimedia content is becoming available via the World Wide Web (WWW). These contents stimulate only senses like hearing or vision. Recently, it has been proposed to stimulate also other senses while consuming multimedia content, through so-called sensory effects. These sensory effects aim at enhancing the user’s viewing experience by providing effects such as light, wind, vibration, etc. These effects are represented as Sensory Effect Metadata (SEM) which is associated to multimedia content and is rendered on devices like fans, lamps, or vibration chairs. In this paper, we present a plug-in for Web browsers which is able to render such sensory effects provided via Web content, and we describe a demonstrator that uses this plug-in to control an amBX system.}, keywords = {Quality of Experience, Sensory Experience, MPEG-V, Web Browser Plug-in, World Wide Web}, language = {EN}, location = {Graz, Austria}, pdf = {https://www.itec.aau.at/bib/files/MMWeb2011_mwbrcthh.pdf}, talkdate = {2011.09.08}, talktype = {poster} } @InProceedings{Szkaliczki2011, author = {Szkaliczki, Tibor and Eberhard, Michael and Hellwagner, Hermann and Szobonya, Laszlo}, booktitle = {7th Japanese-Hungarian Symposium on Discrete Mathematics and its Applications}, title = {Knapsack Problem and Piece Picking Algorithms for Layered Video Streaming}, year = {2011}, address = {Kyoto, Japan}, editor = {Fukunaga, Takuro and Iwata, Satoru and Nagamochi, Hiroshi and Takazawa, Kenjiro}, month = {may}, pages = {419-426}, publisher = {published on workshop homepage}, language = {EN}, location = {Kyoto, Japan}, pdf = {https://www.itec.aau.at/bib/files/hj2011_sztibor_final.pdf}, talkdate = {2011.05.31}, talktype = {registered} } @InProceedings{Stuart2011, author = {Stuart, Mark and Buckham, Mike and Marsh, Richard and Eberhard, Michael and Ishmael, Johnathan and Needham, Chris and Timmerer, Christian}, booktitle = {Proceedings of the 2011 IEEE International Conference on Multimedia and Expo (ICME 2011)}, title = {NextShareTV: A Set-Top Box for Bittorrent-based Live Streaming}, year = {2011}, address = {Los Alamitos, CA, USA}, editor = {Cheng, Irene and Fernandez, Gabriel and Wang, Haohong}, month = {jul}, pages = {1}, publisher = {IEEE}, abstract = {The distribution of audio-visual content over the Internet has become very popular in recent years. However, due to the bandwidth requirements of videos in high definition, a costefficient distribution is desirable. In this paper we present a low-cost consumer electronics set-top box for streaming live video content using cost-efficient P2P networks. The main features of the set-top box include content discovery, highquality playback, easy user management, and social interaction.}, language = {EN}, location = {Barcelona, Spain}, pdf = {https://www.itec.aau.at/bib/files/icme_nextsharetv_demo.pdf}, talkdate = {2011.07.12}, talktype = {registered} } @InProceedings{Sobe2011, author = {Sobe, Anita and Elmenreich, Wilfried and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the Ninth Workshop on intelligent solutions for embedded systems}, title = {Replication for Bio-inspired Delivery in Unstructured Peer-to-Peer Networks}, year = {2011}, address = {Los Alamitos, CA, USA}, editor = {Kucera, Markus and Waas, Thomas}, month = {jul}, pages = {6}, publisher = {IEEE}, language = {EN}, location = {Regensburg, Germany}, talkdate = {2011.07.08}, talktype = {registered} } @InProceedings{SchoeffmannMIPR11, author = {Schoeffmann, Klaus and Ahlström, David}, booktitle = {Proceedings of the Seventh {IEEE} International Workshop on Multimedia Information Processing and Retrieval (MIPR 2011)}, title = {Similarity-Based Visualization for Image Browsing Revisited}, year = {2011}, address = {Dana Point, California, USA}, editor = {Del Bimbo, Alberto and Park, Kwang-ro and Sheu, Phillip}, month = {dec}, pages = {422-427}, publisher = {IEEE}, language = {EN}, location = {Dana Point, CA, USA}, talkdate = {2011.12.5.}, talktype = {registered} } @InProceedings{SchoeffmannISM11, author = {Schoeffmann, Klaus and Ahlström, David and Beecks,Christian}, booktitle = {Proceedings of the Seventh {IEEE} International Symposium on Multimedia (ISM 2011)}, title = {3D Image Browsing on Mobile Devices}, year = {2011}, address = {Dana Point, California, USA}, editor = {Del Bimbo, Alberto and Park, Kwang-ro and Sheu, Phillip}, month = {dec}, pages = {335-336}, publisher = {IEEE}, language = {EN}, location = {Dana Point, CA, USA}, talkdate = {2011.12.7.}, talktype = {poster} } @InProceedings{SchoeffmannACMMM11, author = {Schoeffmann, Klaus and Del Fabro, Manfred}, booktitle = {Proceedings of the {ACM} International Conference on Multimedia}, title = {Hierarchical Video Browsing with a 3D Carousel}, year = {2011}, address = {Scottsdale, AZ, USA}, editor = {Candan, Selcuk and Panchanthan, Sethuraman and Prabhakaran, Balakrishnan Prabhakaran}, month = {dec}, pages = {1609-1612}, publisher = {ACM Pre}, language = {EN}, location = {Scottsdale, AZ, USA}, talkdate = {2011.11.30}, talktype = {poster} } @InProceedings{Schoeffmann:2011icmr, author = {Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 1st ACM International Conference on Multimedia Retrieval}, title = {Image and video browsing with a cylindrical 3D storyboard}, year = {2011}, address = {New York, NY, USA}, editor = {De Natale, Francesco and Del Bimbo, Alberto}, month = {apr}, pages = {63:1–63:2}, publisher = {ACM}, series = {ICMR ’11}, doi = {http://doi.acm.org/10.1145/1991996.1992059}, keywords = {image browsing, interactive search, video browsing}, language = {EN}, location = {Trento, Italy}, talkdate = {2011.4.18}, talktype = {poster}, url = {http://doi.acm.org/10.1145/1991996.1992059} } @InProceedings{Quaritsch2011b, author = {Quaritsch, Markus and Kuschnig, Robert and Hellwagner, Hermann and Rinner, Bernhard}, booktitle = {Proceedings of the 8th International Conference on Information Systems for Crisis Response and Management (ISCRAM 2011)}, title = {Fast Aerial Image Acquisition and Mosaicking for Emergency Response Operations by Collaborative UAVs}, year = {2011}, address = {Berlin, Heidelberg, New York}, editor = {Dugdale,Julie and Mendonça,David}, month = {may}, pages = {5}, publisher = {Springer}, language = {EN}, location = {Lisbon, Portugal}, pdf = {https://www.itec.aau.at/bib/files/Quaritsch_ISCRAM2011.pdf}, talktype = {none} } @InProceedings{Quaritsch2011a, author = {Quaritsch, Markus and Kuschnig, Robert and Wischounig-Strucl, Daniel and Yahyanejad, Saeed and Mersheeva, Vera and Yanmaz, Evsen and Friedrich, Gerhard and Hellwagner, Hermann and Bettstetter, Christian and Rinner, Bernhard}, booktitle = {Proceedings of the Austrian Robotics Workshop (ARW-11)}, title = {FAMUOS: A Multi-UAV System for Aerial Reconnaissance in Rescue Scenarios}, year = {2011}, address = {Hall in Tyrol, Austria}, editor = {Hofbaur, Michael and Husty, Manfred}, month = {may}, pages = {3 3 3}, publisher = {UMIT}, language = {EN}, location = {Hall in Tyrol, Austria}, pdf = {https://www.itec.aau.at/bib/files/Quaritsch_ARW2011.pdf}, talktype = {none} } @InProceedings{Quaritsch2011, author = {Quaritsch, Markus and Wischounig-Strucl, Daniel and Yahyanejad, Saeed and Mersheeva, Vera and Yanmaz, Evsen and Friedrich, Gerhard and Hellwagner, Hermann and Bettstetter, Christian and Rinner, Bernhard}, booktitle = {Proceedings of the International Workshop on Self-Organizing Systems (IWSOS 2011)}, title = {Collaborative Microdrones Research Questions \& Challenges}, year = {2011}, address = {Berlin, Heidelberg, New York}, editor = {Zitterbart, Martina and de Meer, Hermann}, month = {jan}, pages = {38}, publisher = {Springer}, language = {EN}, talktype = {none} } @InProceedings{Pletzer11b, author = {Pletzer, Felix and Tusch, Roland and Böszörmenyi, Laszlo and Rinner, Bernhard and Sidla, Oliver and Harrer, Manfred and Mariacher, Thomas}, booktitle = {Proc. of 14th IEEE International Conference on Intelligent Transportation Systems (ITSC)}, title = {Feature-based Level of Service Classification for Traffic Surveillance}, year = {2011}, address = {Washington D.C., USA}, editor = {Yi, Kyongsu}, month = {oct}, pages = {1015-1020}, publisher = {IEEE}, language = {EN}, location = {Washington D.C., USA}, talkdate = {2011.10.06}, talktype = {registered} } @InProceedings{Pletzer11a, author = {Pletzer, Felix and Tusch, Roland and Rinner, Bernhard and Böszörmenyi, Laszlo and Harrer, Manfred and Mariacher, Thomas}, booktitle = {Proceedings of 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS)}, title = {Level of Service Classification for Smart Cameras}, year = {2011}, address = {Klagenfurt, Austria}, editor = {Cavallaro, Andrea}, month = {sep}, pages = {543-544}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, language = {EN}, location = {Klagenfurt, Austria}, talkdate = {2011.09.02}, talktype = {poster} } @InProceedings{Petrocco2012, author = {Petrocco, Riccardo and Eberhard, Michael and Pouwelse, Johan and Epema, Dick}, booktitle = {Proceedings of the International Symposium on Multimedia 2011}, title = {Deftpack: A Robust Piece-Picking Algorithm for Scalable Video Coding in P2P Systems}, year = {2011}, address = {Los Alamitos, CA, U.S.A.}, editor = {Werner, Bob}, month = {dec}, pages = {285-292}, publisher = {IEEE}, abstract = {The volume of Internet video is growing, and is expected to exceed 57 percent of global consumer Internet traffic by 2014. Peer-to-Peer technology can help delivering this massive volume of traffic in a cost-efficient, scalable, and reliable manner. However, single bitrate streaming is not sufficient given today’s device and network connection diversity. A possible solution to this problem is provided by layered coding techniques, such as Scalable Video Coding, which allow addressing this diversity by providing content in various qualities within a single bitstream. In this paper we propose a new self-adapting piece-picking algorithm for downloading layered video streams, called Deftpack. Our algorithm significantly reduces the number of stalls, minimises the frequency of quality changes during playback, and maximizes the effective usage of the available bandwidth. Deftpack is the first algorithm that is specifically crafted to take all these three quality dimensions into account simultaneously, thus increasing the overall quality of experience. Additionally, Deftpack can be integrated into Bittorrent-based P2P systems and so has the chance of large-scale deployment. Our results from realistic swarm simulations show that Deftpack significantly outperforms previously proposed algorithms for retrieving layered content when all three quality dimensions are taken into account.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/06123359.pdf}, talktype = {none} } @InProceedings{Mueller2011_ACMMM, author = {Mueller, Christopher and Timmerer, Christian}, booktitle = {Proceedings of the 19th ACM international conference on Multimedia}, title = {A VLC media player plugin enabling dynamic adaptive streaming over HTTP}, year = {2011}, address = {New York, NY, USA}, editor = {Candan, Kasim Selcuk and Panchanathan, Sethuraman and Prabhakaran, Balakrishnan and Sundaram, Hari and Feng, Wu-Chi and Sebe, Nicu}, month = {nov}, pages = {723--726}, publisher = {ACM}, series = {MM}, abstract = {This paper describes the implementation of a VLC media player plugin enabling Dynamic Adaptive Streaming over HTTP (DASH). DASH is an emerging ISO/IEC MPEG and 3GPP standard for HTTP streaming. It aims to standardize formats enabling segmented progressive download by exploiting existing Internet infrastructure as such. Our implementation of these formats as described in this paper is based on the well-known VLC. Hence, it is fully integrated into the VLC structure and has been also submitted to the VLC development team for consideration in future releases of VLC. Therefore, it is licensed under the GNU Lesser General Public License (LGPL). The plugin provides a very flexible structure that could be easily extended with respect to different adaptation logics or profiles of the DASH standard. As a consequence, the plugin enables the integration of a variety of adaptation logics and comparison thereof, making it attractive for the research community.}, doi = {10.1145/2072298.2072429}, keywords = {3GPP, DASH, HTTP streaming, MPEG, dynamic adaptive streaming over HTTP, video}, language = {EN}, location = {Scottsdale, Arizona, USA}, pdf = {https://www.itec.aau.at/bib/files/p723-muller.pdf}, talkdate = {2011.11.29}, talktype = {registered} } @InProceedings{Mueller2011, author = {Mueller, Christopher and Timmerer, Christian}, booktitle = {Proceedings of the Second Annual {ACM SIGMM} Conference on Multimedia Systems ({MMSys})}, title = {A Test-Bed for the Dynamic Adaptive Streaming over {HTTP} featuring Session Mobility}, year = {2011}, address = {New York, NY, USA}, editor = {Mayer-Patel, Ketan and Begen, Ali}, month = {feb}, pages = {271--276}, publisher = {ACM}, abstract = {In this paper, we present a multimedia test-bed enabling session mobility in the context of the emerging ISO/IEC MPEG standard, Dynamic Adaptive Streaming over HTTP (DASH). In general, session mobility is defined as the transfer of a running streaming session from one device to another device where it may need to be consumed in an adaptive way. The two main challenges are: (1) taking into account the new context of the device (e.g., capabilities) to which the session is transferred and (2) performing the actual transfer in a seamless and interoperable way. Our system addresses both challenges supported by a prototype implementation integrated into VLC. In anticipation of the results we can conclude that interoperability is achieved adopting existing standards while the performance of the system does not depend on these standards. That is, the modules responsible for the performance are usually not defined within such standards and left out for competition. However, our system is designed in an extensible way and is able to accommodate this fact.}, language = {EN}, location = {San Jose, CA, USA}, pdf = {https://www.itec.aau.at/bib/files/mueller_A_Test_Bed_for_DASH_featuring_Session_Mobility.pdf}, talkdate = {2011.02.25}, talktype = {registered} } @InProceedings{Lux2011a, author = {Lux, Mathias}, booktitle = {MM '11 Proceedings of the 19th ACM international conference on Multimedia}, title = {Content based image retrieval with LIRe}, year = {2011}, address = {New York, USA}, editor = {Candan, KS and Panchanathan, S and Prabhakaran, B}, month = {jan}, pages = {735-738}, publisher = {ACM}, abstract = {LIRe (Lucene Image Retrieval) is an open source library for content based image retrieval. Besides providing multiple common and state of the art retrieval mechanisms it allows for easy use on multiple platforms. LIRe is actively used for research, teaching and commercial applications. Due to its modular nature it can be used on process level (e.g. index images and search) as well as on image feature level. Developers and researchers can easily extend and modify LIRe to adapt it to their needs.}, doi = {10.1145/2072298.2072432}, isbn10 = {978-1-4503-0616-4}, language = {EN}, location = {Scottsdale, Arizona, USA}, talkdate = {2011.11.29}, talktype = {registered} } @InProceedings{Lagger2011, author = {Lagger, Christoph and Lux, Mathias and Marques, Oge}, booktitle = {Workshop on Multimedia on the Web 2011, Proceedings of}, title = {Which video do you want to watch now?}, year = {2011}, address = {Los Alamitos, California, USA}, editor = {Böszörmenyi, Laszlo and Marques, Oge and Lux, Mathia and Klamma, Ralf}, month = {jan}, note = {to appear in IEEE}, pages = {45-48}, publisher = {IEE}, abstract = {Searching and retrieving videos in a meaningful way on the web is still an open problem. The integration of a user's context into search is one of the most promising approaches to enhance current search interfaces and algorithms. We performed two user studies investigating video search, video retrieval, and video sharing behavior. In this paper we present an overview on the findings most promising for enhancing user experience in video retrieval. We propose a software prototype that implements an adaptive video retrieval system, that utilizes the users' intentions to provide better search results in a user interface adapted to the intentions and needs of users.}, doi = {10.1109/MMWeb.2011.15}, isbn10 = {978-1-4577-2043-7}, language = {EN}, location = {Graz}, talkdate = {2011.09.08}, talktype = {registered} } @InProceedings{Kuschnig2011, author = {Kuschnig, Robert and Kofler, Ingo and Hellwagner, Hermann}, booktitle = {Proceedings of the Second Annual {ACM SIGMM} Conference on Multimedia Systems (MMSys)}, title = {Evaluation of {HTTP}-based request-response streams for internet video streaming}, year = {2011}, address = {New York, NY, USA}, editor = {Mayer-Patel, Ketan and Begen, Ali}, month = {feb}, pages = {245--256}, publisher = {ACM}, abstract = {Adaptive video streaming based on TCP/HTTP is becoming popular because of its ability to adapt to changing network conditions. We present an in-depth experimental analysis of the use of HTTP-based request-response streams for video streaming. In this scheme, video fragments are fetched by a client from the server, in smaller units called chunks, potentially via multiple parallel HTT P requests (TCP connections). A model for the achievable throughput is formulated.The model is validated by a broad range of streaming experiments, including an evaluation of TCP-friendliness. Our findings include that request-response streams are able to scale with the available bandwidth by increasing the chunk size or the number of concurrent streams. Several combinations of system parameters exhibiting TCP-friendliness are presented. We also evaluate the video streaming performance in terms of video quality in the presence of packet loss. Multiple request-response streams are able to maintain satisfactory performance, while a single TCP connection deteriorates rapidly with increasing packet loss. The results provide experimental evidence that HTTP-based request-response streams are a good alternative to classical TCP streaming}, doi = {10.1145/1943552.1943585}, language = {EN}, location = {San Jose, CA, USA}, pdf = {https://www.itec.aau.at/bib/files/mmsys11_kuschnig_preprint.pdf}, talkdate = {2011.02.25}, talktype = {registered} } @InProceedings{Kogler2011, author = {Kogler, Marian and Lux, Mathias}, booktitle = {Proceedings of the 2011 ACM workshop on Social and behavioural networked media access}, title = {Pursuing the holy grail by interrelating user intentions and bag of visual words to perform retrieval adaptation}, year = {2011}, address = {New York, NY, USA}, editor = {","}, month = {dec}, pages = {3--8}, publisher = {ACM}, language = {EN}, location = {Scottsdale, Arizona, USA}, talkdate = {2011.12.1}, talktype = {registered} } @InProceedings{Kofler2011a, author = {Kofler, Ingo and Kuschnig, Robert and Hellwagner, Hermann}, booktitle = {Proceedings of the 2011 IEEE International Conference on Multimedia and Expo (ICME 2011)}, title = {Evaluating the Networking Performance of Home Router Platforms for Multimedia Services}, year = {2011}, address = {Los Alamitos, CA, USA}, editor = {Cheng, Irene and Fernandez, Gabriel and Wang, Haohong}, month = {jul}, pages = {6}, publisher = {IEEE}, series = {ICME}, abstract = {Wireless router platforms based on the Linux operating system are becoming popular in consumers' home networks. The transmission of multimedia data or their use as media-aware network elements imposes high traffic and computational loads on these devices. Thus, it is interesting to evaluate the networking and processing capabilities of such home router platforms in order to assess their usefulness for improved multimedia services such as in-network H.264/SVC video stream adaptation. This paper presents a performance evaluation of three home router platforms representative for low-end, mid-range, and high-end devices. The scope of the evaluation is the performance of the Linux networking stack on these routers; results for both application-layer (TCP and UDP) transmission and kernel-level (UDP) traffic routing are given. The results show that both TCP and UDP throughputs are significantly below (less than half of) the outgoing (wired) links' nominal capacities and depend very much on the sizes of the transmitted data blocks. This clearly indicates that the networking performance is limited by the platforms' processing capabilities and the lack of mechanisms that offload networking tasks from the CPUs. This behaviour cannot be observed on today's PC systems and has to be considered when deploying multimedia services on these network devices. Furthermore, a detailed analysis of the Linux networking stack reveals that the performance is heavily impacted by the netfilter code, even when no packet filtering or network address translation is being performed. Considerable performance gains can be achieved when this netfilter code is bypassed.}, doi = {10.1109/ICME.2011.6012189}, language = {EN}, location = {Barcelona, Spain}, pdf = {https://www.itec.aau.at/bib/files/platformeval_preprint.pdf}, talkdate = {2011.07.11}, talktype = {registered} } @InProceedings{Kofler2011, author = {Kofler, Ingo and Kuschnig, Robert and Hellwagner, Hermann}, booktitle = {Proceedings of the 21st International Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV 2011)}, title = {In-Network Adaptation of H.264/SVC for HD Video Streaming Over 802.11g Networks}, year = {2011}, address = {New York, NY, USA}, editor = {Krasic, Charles and Li, Kang}, month = {jun}, pages = {9-14}, publisher = {ACM}, series = {NOSSDAV}, abstract = {In this paper, we present an approach for in-network adaptation of H.264/SVC in the context of 802.11 wireless networks. It builds upon our previous work on an adaptive RTSP/RTP proxy which allows to adapt video streams on Linux-based home router platforms. The proposed approach tackles the throughput variations that occur as a consequence of the physical rate adaptation in 802.11 equipment caused by the mobility of clients. By combining monitoring information available exclusively on the wireless router with the ability to adapt scalable video streams on-the-fly, the proposed in-network adaptation approach allows to quickly adjust the video bit rate to the current link conditions. Instead of reacting on packet loss, our approach uses an increase in queueing delay at the router to detect phases of throughput degradation. This allows a higher responsiveness compared to traditional end-to-end approaches that rely solely on RTCP feedback. The behavior of our novel approach was evaluated in several mobility scenarios in an experimental test bed. The results obtained by streaming and adapting high-definition content clearly demonstrate the feasibility and benefits of this approach.}, doi = {10.1145/1989240.1989245}, language = {EN}, location = {Vancouver, Canada}, pdf = {https://www.itec.aau.at/bib/files/NOSSDAV2011_Preprint.pdf}, talkdate = {2011.06.02}, talktype = {registered} } @InProceedings{Grafl2011_WoWMoM, author = {Grafl, Michael}, booktitle = {Proceedings of the 12th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)}, title = {SVC Tunneling for Media-Aware Content Delivery: Impact on Video Quality}, year = {2011}, address = {Los Alamitos, CA, USA}, editor = {Gerla, Mario and Mingozzi, Enzo and Chatterjee, Mainak and Passarella, Andrea}, month = {jun}, pages = {3}, publisher = {IEEE}, abstract = {Today's omnipresent demand for access to multimedia content via diverse devices places new challenges on efficient content delivery. This work introduces the concept of Scalable Video Coding (SVC) tunneling developed in the EU FP7 ALICANTE project and shows that the quality impact of the transcoding steps for a transcoding chain from MPEG-2 to SVC and back to MPEG-2 accumulates to a PSNR reduction of up to 2.1 dB for transcoding at fixed target bitrate points. We also discuss research challenges and open issues in SVC tunneling.}, doi = {10.1109/WoWMoM.2011.5986152}, keywords = {Content-aware networking; scalable video coding; SVC tunneling; transcoding; multimedia distribution}, language = {EN}, location = {Lucca, Italy}, pdf = {https://www.itec.aau.at/bib/files/WoWMoM2011_mgrafl.pdf}, talkdate = {2011.06.22}, talktype = {poster} } @InProceedings{Grafl2011_WoMAN, author = {Grafl, Michael and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the 2011 IEEE International Conference on Multimedia and Expo (ICME 2011)}, title = {Quality Impact of Scalable Video Coding Tunneling for Media-Aware Content Delivery}, year = {2011}, address = {Los Alamitos, CA, USA}, editor = {Cheng, Irene and Fernandez, Gabriel and Wang, Haohong}, month = {jul}, pages = {4}, publisher = {IEEE}, series = {ICME}, abstract = {Today's omnipresent demand for access to multimedia content via diverse devices places new challenges on efficient content delivery. While the Scalable Video Coding (SVC) extension of Advanced Video Coding (AVC) has proven to be a useful tool for the advanced delivery of video content, it has not yet found major adoption in practice. This paper introduces the concept of SVC tunneling developed in the EU FP7 ALICANTE project, which attempts to provide device-independent access to media resources at reduced network load. For SVC tunneling, video transcoding is performed at the ingress/egress points of the network, which may impact the video quality. We show that the quality impact of these transcoding steps for a transcoding chain from MPEG-2 to SVC and back to MPEG-2 accumulates to a PSNR reduction of up to 2.1 dB for transcoding at fixed target bitrates. We also discuss research challenges and open issues in SVC tunneling.}, doi = {10.1109/ICME.2011.6012239}, keywords = {Content-aware networking; scalable video coding; quality of service; SVC tunneling; transcoding; multimedia distribution}, language = {EN}, location = {Barcelona, Spain}, pdf = {https://www.itec.aau.at/bib/files/WoMAN2011_paper_209.pdf}, talkdate = {2011.07.11}, talktype = {registered} } @InProceedings{Eberhard2011b, author = {Eberhard, Michael and Hellwagner, Hermann and Timmerer, Christian and Szkaliczki, Tibor and Szobonya, Laszlo}, booktitle = {Proceedings of the 2011 {IEEE} International Conference on Multimedia and Expo (ICME 2011)}, title = {An evaluation of piece-picking algorithms for layered content in Bittorrent-based peer-to-peer systems}, year = {2011}, address = {Los Alamitos, CA, USA}, editor = {Cheng, Irene and Fernandez, Gabriel and Wang, Haohong}, month = {jul}, pages = {1-6}, publisher = {IEEE}, series = {ICME}, language = {EN}, location = {Barcelona, Spain}, pdf = {https://www.itec.aau.at/bib/files/icme2011_piece-picking.pdf}, talkdate = {2011.07.11}, talktype = {registered} } @InProceedings{DelFabro2011, author = {Del Fabro, Manfred and Böszörmenyi, Laszlo}, booktitle = {ACM CHI 2011 Workshop – Data Collection By The People For The People}, title = {The Vision of Crowds: Social Event Summarization Based on User- Generated Multimedia Content}, year = {2011}, address = {http://databythepeople.com/ (May 2011)}, editor = {Robson, Christine and Kandel, Sean and Heer, Jeff and Pierce, Jeff}, month = {may}, pages = {1--5}, publisher = {published on workshop homepage}, abstract = {In this position paper we introduce the idea of generating a superior view of a large social event, based on user-generated -- crowdsourced -- content. Instead of just collecting and making them available in a raw form (as social platforms like YouTube), we automatically generate semantically coherent summarizations of the entire event. The individual consuming user gets thus a compact view generated by a large number of producing users. We call this idea the "Vision of Crowds". A case study has been conducted at a social event where we used user-generated content to automatically generate live reports about that event. Furthermore, we have implemented a GUI that allows users to interactively compose personalized video summaries, based on the user-generated data collected at the case study.}, language = {EN}, location = {Vancouver, BC, Canada}, pdf = {https://www.itec.aau.at/bib/files/The Vision of Crowds - Social Event Summarization Based on User-Generated Multimedia Content.pdf}, talkdate = {2011.05.08}, talktype = {registered} } @InProceedings{Beecks2011, author = {Beecks, Christian and Skopal, Thomas and Schoeffmann, Klaus and Seidl, Thomas}, booktitle = {Proceedings of the 5th International Workshop on Ranking in Databases (DBRank 2011)}, title = {Towards Large-Scale Multimedia Exploration}, year = {2011}, address = {Seattle, WA, USA}, editor = {Das, Gautam and Hsristidis, Vagelis and Ilyas, Ihab}, month = {aug}, pages = {31-33}, publisher = {VLDB}, abstract = {With the advent of the information age and the increasing size and complexity of multimedia databases, the question of how to support users in getting access and insight into those large databases has become immensely important. While traditional content-based retrieval approaches provide query-driven access under the assumption that the users' information needs are clearly specified, modern content-based exploration approaches support users in browsing and navigating through multimedia databases in the case of imprecise or even unknown information needs. By means of interactive graphical user interfaces, exploration approaches offer a convenient and intuitive access to unknown multimedia databases which becomes even more important with the arrival of powerful mobile devices. In this paper, we formulate challenges of user-centric multimedia exploration with a particular focus on large-scale multimedia databases. We claim that adaptability and scalability should be researched on both conceptual as well as technical level in order to model multimedia exploration approaches which are able to cope with millions of multimedia objects in near-realtime.}, language = {EN}, location = {Seattle, WA, USA}, pdf = {https://www.itec.aau.at/bib/files/Towards LargeScale_2011_KSch.pdf}, talkdate = {2011.08.29}, talktype = {registered} } @InProceedings{5992204, author = {Esterle, Lukas and Lux, Mathias}, booktitle = {Multimedia and Ubiquitous Engineering (MUE), 2011 5th FTRA International Conference on}, title = {Indexing Digital Images Based on Overlap}, year = {2011}, address = {Piscataway, USA}, editor = {Min, Geyong and Yeo, Sang Soo}, month = {june}, pages = {134 -137}, publisher = {IEEE}, abstract = {Image retrieval currently relies heavily on metadata and present search engines do not exploit spatial relations between images. Therefore searching for images of a certain location manually is a time consuming task. Typically there are pair wise spatial relations in an unsorted set of photos taken at the same location from different angles and different viewpoints. By identifying and indexing spatial relations of different photos an image search engine can provide additional results based on these relationships. This paper presents a novel approach to identify pair wise spatial relations between images and a method to index and search through the identified spatial relations. We further describe an application, which implements this robust and surprisingly simple technique.}, doi = {10.1109/MUE.2011.35}, isbn13 = {978-1-4577-1228-9}, keywords = {digital image indexing;image retrieval;image search engine;metadata;pair wise spatial relations;database indexing;image retrieval;meta data;search engines;visual databases;}, language = {EN}, talktype = {none} } @InProceedings{schoeffmann_mmsys2010, author = {Schoeffmann, Klaus and Taschwer, Mario and Böszörmenyi, Laszlo}, booktitle = {MMSys ’10: Proceedings of the first annual ACM SIGMM conference on Multimedia systems}, title = {The video explorer: a tool for navigation and searching within a single video based on fast content analysis}, year = {2010}, address = {New York, NY, USA}, editor = {Feng, Wu-chi and Mayer-Patel, Ketan}, month = {feb}, pages = {247–258}, publisher = {ACM}, doi = {http://doi.acm.org/10.1145/1730836.1730867}, language = {EN}, location = {Phoenix, Arizona, USA}, talkdate = {2010.2.23}, talktype = {registered} } @InProceedings{schoeffmann2010mmm, author = {Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Advances in Multimedia Modeling}, title = {Enhancing Seeker-Bars of Video Players with Dominant Color Rivers}, year = {2010}, address = {Chongqing, China}, editor = {Chen, Yi-Ping Phoebe and Zhang, Zili and Boll, Susanne and Tian, Qi and Zhang, Lei}, month = {jan}, pages = {–}, publisher = {Springer}, language = {EN}, location = {Chongqing, China}, talkdate = {2010.1.7.}, talktype = {poster} } @InProceedings{schoeffmann2010mm, title = {Facilitating Interactive Search and Navigation in Videos}, author = {Schoeffmann, Klaus}, booktitle = {Proceedings of the {ACM} International Conference on Multimedia}, year = {2010}, address = {Firenze, Italy}, editor = {Del Bimbo, Alberto and Chang, Shih-Fu and Smeulders,Arnold}, month = {oct}, pages = {1609-1612}, publisher = {ACM Press}, language = {EN}, location = {Firenze, Italy}, talkdate = {2010.10.27}, talktype = {poster} } @InProceedings{Wieser2011a, author = {Wieser, Stefan and Böszörmenyi, Laszlo}, booktitle = {The Second International Conferences on Advances in Multimedia (MMEDIA 2010)}, title = {Flocks: Interest-Based Construction of Overlay Networks}, year = {2010}, address = {Washington, USA}, editor = {Benoit, Huet and Alan, Smeaton and Ketan, Mayer-Patel and Yannis, Avrithis}, month = {jun}, pages = {119-124}, publisher = {IEEE}, abstract = {Self-organizing overlay networks have received a lot of attention in the recent years. However, despite the popularity of content-aware and topology-aware overlay networks, surprisingly little research has been done to combine both approaches. In this paper, we create robust and flexible overlay networks that we call “Flocks”, which can be content-aware, topology-aware, or a combination of both. We model affinity with interests and properties and show the resulting overlay networks work in a decentralized, self-organizing way, and stabilize quickly.}, doi = {10.1109/MMEDIA.2010.22}, journal = {2010 Second International Conferences on Advances in Multimedia (MMEDIA)}, language = {EN}, location = {Athens, Greece}, talkdate = {2010.06.14}, talktype = {registered} } @InProceedings{Waltl2010_WIAMIS_SensoryEffects, author = {Waltl, Markus and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the 11th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS'10)}, title = {Increasing the User Experience of Multimedia Presentations with Sensory Effects}, year = {2010}, address = {Los Alamitos, CA, USA}, editor = {Leonardi, Riccardo and Migliorati, Pierangelo and Cavallaro, Andrea}, month = {apr}, pages = {1-4}, publisher = {IEEE}, abstract = {The term Universal Multimedia Experience (UME) has gained momentum and is well recognized within the research community. As this approach puts the user into the center stage, additional complexity is added to the overall quality assessment problem which calls for a scientific framework to capture, measure, quantify, judge, and explain the user experience. In previous work we have proposed the annotation of multimedia content with sensory effect metadata that can be used to stimulate also other senses than vision or audition. In this paper we report first results obtained from subjective tests in the area of sensory effects attached to traditional multimedia presentations such as movies that shall lead to an enhanced, unique, and worthwhile user experience.}, isbn13 = {9781424478484}, keywords = {Sensory Information, MPEG-V}, language = {EN}, location = {Desenzano del Garda, Italy}, pdf = {https://www.itec.aau.at/bib/files/wiamis2010_mwcthh.pdf}, talkdate = {2010.04.13}, talktype = {poster} } @InProceedings{Waltl2010_QoMEX2010_SensoryEffects, author = {Waltl, Markus and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the 2nd International Workshop on Quality of Multimedia Experience (QoMEX'10)}, title = {Improving the Quality of Multimedia Experience through Sensory Effects}, year = {2010}, address = {Los Alamitos, CA, USA}, editor = {Perkis, Andrew and Möller, Sebastian and Svensson, Peter and Reibman, Amy}, month = {jun}, pages = {124-129}, publisher = {IEEE}, abstract = {In previous and related work sensory effects are presented as a tool for increasing the user experience of multimedia presentations by stimulating also other senses than vision or audition. In this paper we primarily investigated the relationship of the Quality of Experience (QoE) due to various video bit-rates of multimedia contents annotated with sensory effects (e.g., wind, vibration, light). Therefore, we defined a subjective quality assessment methodology based on standardized methods. The paper describes the test environment, its setup, and conditions in detail. Furthermore, we experimented with a novel voting device that allows for continuous voting feedback during a sequence in addition to the overall quality voting at the end of each sequence. The results obtained from the subjective quality assessment are presented and discussed thoroughly. In anticipation of the results we can report an improvement of the quality of the multimedia experience thanks to the sensory effects.}, doi = {10.1109/QOMEX.2009.5246962}, isbn13 = {9781424469581}, keywords = {Sensory Information, MPEG-V}, language = {EN}, location = {Trondheim, Norway}, pdf = {https://www.itec.aau.at/bib/files/qomex2010_mwcthh.pdf}, talkdate = {2010.06.21}, talktype = {poster}, url = {http://www.qomex2010.org} } @InProceedings{Waltl2010_IMOF2010_SensoryEffects, author = {Waltl, Markus and Raffelsberger, Christian and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings CD of the 2nd International ICST Conference on User Centric Future Media Internet}, title = {Metadata-based Content Management and Sharing System for Improved User Experience}, year = {2010}, address = {Berlin, Heidelberg, New York}, editor = {Alvarez, Federico and Costa, Cristina}, month = {sep}, pages = {1-9}, publisher = {Springer Verlag GmbH}, abstract = {In the past years the amount of multimedia content on the Internet or in home networks has been drastically increasing. Instead of buying traditional media (such as CDs or DVDs) users tend to buy online media. This leads to the difficulty of managing the content (e.g., movies, images). A vast amount of tools for content management exists but they are mainly focusing on one type of content (e.g., only images). Furthermore, most of the available tools are not configurable to the user’s preferences and cannot be accessed by different devices (e.g., TV, computer, mobile phone) in the home network. In this paper we present a UPnP A/V-based system for managing and sharing audio/visual content in home environments which is configurable to the user’s preferences. Furthermore, the paper depicts how this system can be used to improve the user experience by using MPEG-V.}, isbn13 = {9789639995000}, keywords = {Sensory Information, MPEG-V}, language = {EN}, location = {Palma de Mallorca, Spain}, pdf = {https://www.itec.aau.at/bib/files/ucmedia2010_mwcrcthh.pdf}, talkdate = {2010.09.01}, talktype = {registered} } @InProceedings{Tusch2010, author = {Tusch, Roland and Fuchs, Armin and Gutmann, Horst and Kogler, Marian and Köpke, Julius and Böszörmenyi, Laszlo and Harrer, Manfred and Mariacher, Thomas}, booktitle = {Proceedings of the Lakeside Conference 2010: Data and Mobility – Transforming Information into Intelligent Traffic and Transportation Services}, title = {A Multimedia-centric Quality Assurance System for Traffic Messages}, year = {2010}, address = {Villach, Austria}, editor = {Düh, Julia and Hufnagl, Hartwig and Juritsch, Erhard and Pfliegl, Reinhard and Schimany, Helmut-Klaus and Schönegger, Hans}, month = {oct}, pages = {1-14}, publisher = {Springer-Verlag}, language = {EN}, location = {Villach, Austria}, talkdate = {2010.10.08}, talktype = {registered} } @InProceedings{Timmerer2010_WISMA_SensoryEffects, author = {Timmerer, Christian and Waltl, Markus and Hellwagner, Hermann}, booktitle = {Proceedings of the Workshop on Interoperable Social Multimedia Applications (WISMA 2010)}, title = {Are Sensory Effects Ready for the World Wide Web?}, year = {2010}, address = {Aachen, Germany}, editor = {Carreras, Anna and Delgado, Jaime and Maroñas, Xavier and Rodríguez, Víctor}, month = {may}, pages = {57-60}, publisher = {CEUR Workshop Proceedings (CEUR-WS.org)}, abstract = {The World Wide Web (WWW) is one of the main entry points to access and consume Internet content in various forms. In particular, the Web browser is used to access different types of media (i.e., text, image, audio, and video) and on some platforms is the only way to access the vast amount of information on the Web. Recently, it has been proposed to stimulate also other senses than vision or audition while consuming multimedia content through so- called sensory effects, with the aim to increase the user’s Quality of Experience (QoE). The effects are represented as Sensory Effects Metadata (SEM) which is associated to traditional multimedia content and is rendered (synchronized with the media) on sensory devices like fans, vibration chairs, lamps, etc. In this paper we provide a principal investigation of whether the sensory effects are ready for the WWW and, in anticipation of the result, we propose how to embed sensory effect metadata within Web content and the synchronized rendering thereof.}, keywords = {MPEG-V}, language = {EN}, location = {Barcelona, Spain}, pdf = {https://www.itec.aau.at/bib/files/MPEG-V_v2.1.pdf}, talkdate = {2010.05.19}, talktype = {registered} } @InProceedings{Timmerer2010_WISMA_Metadata, author = {Timmerer, Christian and Eberhard, Michael and Grafl, Michael and Mitchell, Keith and Dutton, Sam and Hellwagner, Hermann}, booktitle = {Proceedings of the Workshop on Interoperable Social Multimedia Applications (WISMA 2010)}, title = {A Metadata Model for Peer-to-Peer Media Distribution}, year = {2010}, address = {Aachen, Germany}, editor = {Carreras, Anna and Delgado, Jaime and Maroñas, Xavier and Rodríguez, Víctor}, month = {may}, pages = {8}, publisher = {CEUR Workshop Proceedings (CEUR-WS.org)}, abstract = {In this paper we describe a metadata solution for a Peer-to-Peer (P2P) content distribution system termed NextShare. We outline the key motivating factors for our approach, detail the overall generic architecture we have developed and present the workflow for delivering metadata through Peer-to-Peer based content distribution. The paper also presents the metadata model we have developed and we describe in detail how all the content can be packetized and distributed using NextShare. Finally, a description of the core and optional metadata attributes which may be utilized within the system is provided.}, keywords = {Metadata, peer-to-peer streaming, social networks, payment and cashing, advertisements, MPEG-21 Digital Item, API.}, language = {EN}, location = {Barcelona, Spain}, pdf = {https://www.itec.aau.at/bib/files/P2P-Metadata_v2.0.pdf}, talkdate = {2010.05.19}, talktype = {registered}, url = {http://www.multimedia-metadata.info/Members/ralf/callforpapers.2010-02-01.6353762208} } @InProceedings{Timmerer2010_STDay_HTTPStreaming, author = {Timmerer, Christian and Mueller, Christopher}, booktitle = {Proceedings of STreaming Day 2010}, title = {HTTP Streaming of {MPEG} Media}, year = {2010}, address = {Agrate B.za, Italy}, editor = {Bernardini, Riccardo and Rovati, Fabrizio}, month = {oct}, pages = {4}, publisher = {Rovati, Fabrizio}, abstract = {MPEG has developed various technologies for multimedia transport, such as MPEG-2 Transport Stream (TS) and ISO Media Base File Format. These technologies have been widely accepted and heavily used by various industries and applications, such as digital broadcasting, audio and video transport over the Internet, mobile phones, etc. In recent years, the Internet has become an important channel for the delivery of multimedia. As HTTP is widely used on the Internet, it has recently been used extensively for the delivery of multimedia content. However, there is no standard for HTTP- based streaming of MPEG media. MPEG intends to standardize a solution that addresses this need. This paper provides an overview of the recent Call of Proposals (CfP) for HTTP Streaming of MPEG Media, a new work item within ISO/IEC MPEG. In particular, it will provide an overview of existing systems and the outcome of the evaluation of the aforementioned CfP which has been conducted during the 93rd MPEG meeting in July 2010.}, keywords = {HTTP Streaming}, language = {EN}, location = {Udine, Italy}, pdf = {https://www.itec.aau.at/bib/files/STDay-2010-v1.1.pdf}, talkdate = {2010.09.17}, talktype = {registered} } @InProceedings{Timmerer2010_ITWDC, author = {Timmerer, Christian and Grafl, Michael and Hellwagner, Hermann and Negru, Daniel and Borcoci, Eugen and Renzi, Daniel and Mevel, Anne-Lore and Chernilov, Alex}, booktitle = {Proceedings of the International Tyrrhenian Workshop on Digital Communications (ITWDC)}, title = {Scalable Video Coding in Content-Aware Networks: Research Challenges and Open Issues}, year = {2010}, address = {New York, NY, USA}, editor = {Blefari-Melazzi, Nicola}, month = {sep}, pages = {11}, publisher = {Springer}, abstract = {The demand for access to advanced, distributed media resources is nowadays omnipresent due to the availability of Internet connectivity almost anywhere, anytime, and with a huge amount of different devices. This calls for rethinking of the current Internet architecture by making the network aware of which content is actually transported. This paper introduces Scalable Video Coding (SVC) as a tool for Content-Aware Networks (CANs) which is currently researched as part of the EU FP7 ALICANTE project. The architecture of ALICANTE with respect to SVC and CAN is reviewed, use cases are described, and, finally, research challenges and open issues are discussed.}, language = {EN}, location = {Island of Ponza, Italy}, pdf = {https://www.itec.aau.at/bib/files/SVC4CAN_v1.0.pdf}, talkdate = {2010.09.08}, talktype = {registered} } @InProceedings{Timmerer2010_INTL-DPIF, author = {Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the 1st International Digital Preservation Interoperability Framework Symposium}, title = {MPEG-21 digital items in research and practice}, year = {2010}, address = {New York, NY, USA}, editor = {Chang, Wo}, month = {apr}, pages = {8:1-8:8}, publisher = {ACM}, series = {INTL-DPIF}, abstract = {The aim of the MPEG‐21 standard, the so‐called Multimedia Framework, is to enable transparent and augmented use of multimedia resources across a wide range of networks, devices, user preferences, and communities, notably for trading (of bits). As such, it provides an important step in MPEG's standards evolution, i.e., the transaction of Digital Items among Users. This paper provides an overview of applications making use specifically of MPEG‐21 Digital Items and a more in‐depth presentation of a few selected applications in research and practice.}, doi = {10.1145/2039263.2039271}, keywords = {DANAE, ENTHRONE, MPEG-21, P2P-Next, UPnP, application, digital item, digital library, usage}, language = {EN}, location = {Dresden, Germany}, pdf = {https://www.itec.aau.at/bib/files/a8-timmerer.pdf}, slides = {https://www.itec.aau.at/bib/files/DPIF2010_v1.0.pdf}, talkdate = {2010.04.22}, talktype = {registered} } @InProceedings{Timmerer2010_ACMMM_SensoryExperience, author = {Timmerer, Christian and Müller, Karsten}, booktitle = {Proceedings of the International Conference on Multimedia (MM '10)}, title = {Immersive Future Media Technologies: From 3D Video to Sensory Experiences}, year = {2010}, address = {New York, NY, USA}, editor = {del Bimbo, Alberto and Chang, Shih-Fu and Smeulders, Arnold}, month = {oct}, pages = {1781--1782}, publisher = {ACM}, abstract = {In this tutorial we present immersive future media technologies ranging from 3D video to sensory experiences. The former targets stereo and multi-view video technologies whereas the latter aims at stimulating other senses than vision or audition enabling an advanced user experiences through sensory effects.}, doi = {10.1145/1873951.1874369}, keywords = {Measurement, Experimentation, Human Factors, Standardization, Immersive Media, 3D Video, Stereo Video, Multi-view Video, Sensory Effects, MPEG-V, Quality of Experience}, language = {EN}, location = {Florence, Italy}, pdf = {https://www.itec.aau.at/bib/files/tut08x-timmerer.pdf}, talkdate = {2010.10.25}, talktype = {registered}, url = {http://doi.acm.org/10.1145/1873951.1874369} } @InProceedings{Sobe2010a, author = {Sobe, Anita and Elmenreich, Wilfried and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 18th International Conference on Multimedea 2010}, title = {{Towards a self-organizing replication model for non-sequential media access}}, year = {2010}, address = {New York}, editor = {Del Bimbo, Alberto and Chang, Shih-Fu and Smeulders, Arnold}, month = {jan}, pages = {3--8}, publisher = {ACM}, isbn10 = {978-1-60558-933-6}, keywords = {non-sequential, replication, self-organization, video delivery}, language = {EN}, location = {Florence, Italy}, talkdate = {2010.10.29}, talktype = {registered} } @InProceedings{Sablatschan2010a, author = {Sablatschan, Michael and Ortiz Murillo, Jordi and Ransburg, Michael and Hellwagner, Hermann}, booktitle = {Proceedings of the Workshop SVCVision, in conjunction with the 6th International Mobile Multimedia Communications Conference (MobiMedia 2010)}, title = {Efficient SVC-to-AVC Conversion at a Media Aware Network Element}, year = {2010}, address = {Berlin, Heidelberg, New York}, editor = {Rodriguez, Jonathan and Tafazolli, Rahim and Verikoukis, Christos}, month = {sep}, pages = {7}, publisher = {Springer}, abstract = {H.264/SVC, the Scalable Video Coding extension of the H.264/AVC video coding standard, features spatial, quality and temporal scalability. Backwards compatibility with legacy decoding devices is maintained through an H.264/AVC compliant base layer, which represents the lowest quality of an H.264/SVC bit-stream. However, it is often desireable to also provide the higher quality layers to legacy H.264/AVC devices. This is achieved by a process commonly known as "bit-stream rewriting", which allows for an efficient H.264/SVC to H.264/AVC conversion by exploiting the similarities of the two codecs. This paper describes a demonstrator showing the advantages of including an improved version of the bit-stream rewriting tool from the existing JSVM H.264/SVC reference software in an H.264/SVC-based multimedia delivery system, by integrating it into a Media Aware Network Element.}, keywords = {Multimedia Adaptation, H.264/SVC, SVC-to-AVC rewriting}, language = {EN}, talktype = {none} } @InProceedings{Sablatschan2010, author = {Sablatschan, Michael and Ransburg, Michael and Hellwagner, Hermann}, booktitle = {Proceedings of the Second International Conferences on Advances in Multimedia (MMEDIA 2010)}, title = {Towards an Improved SVC-to-AVC Rewriter}, year = {2010}, address = {Los Alamitos, CA, USA}, editor = {Böszörmenyi, Laszlo and Burdescu, Dumitru and Davis, Philip and Stanchev, Peter}, month = {jun}, pages = {18-21}, publisher = {IEEE}, abstract = {The Scalable Video Coding (SVC) extension of the H.264/AVC (AVC) video coding standard features spatial, quality and temporal scalability. Backwards compatibility with legacy decoding devices is maintained through an H.264/AVC compliant base layer, which represents the lowest quality of an SVC bit-stream. However, it is often desirable to also provide the higher quality layers to legacy H.264/AVC devices. This is achieved by a process commonly known as “bit-stream rewriting”, which allows for an efficient SVC to AVC conversion by exploiting the similarities of the two codecs. This paper introduces an improved version of the existing JSVM reference software rewriter (JSVM-rewriter). The improvements include a better run-time performance through parallel processing, as well as applicability in streaming scenarios. A detailed evaluation provides performance measurements for the improved rewriter and compares it to the existing JSVM-rewriter. The evaluation shows that notable performance improvements can be achieved using the presented approach. The paper concludes on how the rewriter could be further improved.}, doi = {10.1109/MMEDIA.2010.27}, language = {EN}, location = {Athens, Greece}, pdf = {https://www.itec.aau.at/bib/files/Towards_an_Improved_SVC2AVCRewriter_MMEDIA2010_Sablatschan.pdf}, talkdate = {2010.06.14}, talktype = {registered}, url = {http://www.iaria.org/conferences2010/MMEDIA10.html} } @InProceedings{Ransburg2010a, author = {Ransburg, Michael and Martínez Graciá, Eduardo and Sutinen, Tiia and Ortíz Murillo, Jordi and Sablatschan, Michael and Hellwagner, Hermann}, booktitle = {Proceedings of the Workshop SVCVision, in conjunction with the 6th International Mobile Multimedia Communications Conference (MobiMedia 2010)}, title = {Scalable Video Coding Impact on Networks}, year = {2010}, address = {Berlin, Heidelberg, New York}, editor = {Rodriguez, Jonathan and Tafazolli, Rahim and Verikoukis, Christos}, month = {sep}, pages = {571-581}, publisher = {Springer}, abstract = {This paper describes the CELTIC project on "Scalable Video Coding Impact on Networks" with the focus of designing a streaming system based on the Scalable Video Coding extension of the H.264/AVC standard. The system is designed to cope with streaming scenarios that can be classified in four use cases: session handover, network congestion, receiver heterogeneity and user driven adaptation. A complete overview of the architecture of the system is given. Two demonstration scenarios are described in detail, which point out the advantages of scalable video coding compared to single layer approaches in multimedia transmission and adaptation scenarios. A concluding section summarizes the work and provides an outlook to future work items.}, isbn13 = {SBN 978-3-642-35155-6}, keywords = {Scalable Video Coding, H.264/SVC, streaming, architecture, video adaptation}, language = {EN}, talktype = {none} } @InProceedings{Ransburg2010, author = {Ransburg, Michael and Jonke, Mario and Hellwagner, Hermann}, booktitle = {Proceedings of the First Workshop on Mobile Multimedia Networking (IWMMN 2010)}, title = {An Evaluation of Mobile End Devices in Multimedia Streaming Scenarios}, year = {2010}, address = {Heidelberg/Berlin, Germany}, editor = {Wang, Honggang and Xia, Jinchun}, month = {jun}, pages = {14}, publisher = {Springer}, abstract = {This paper compares handhelds based on the iPhone and Android operating systems in multimedia streaming scenarios. We simulate typical Internet network impairments, i.e. packet delay and packet loss, and evaluate their effects on the end devices. Additional evaluations include bandwidth overhead in icted by the different streaming approaches and traffic shape and fairness when both handhelds consume media simultaneously. Based on the quantitative evaluation, both approaches show weaknesses and strengths. A final qualitative discussion points out additional advantages for the streaming approach implemented in the iPhone operating system.}, doi = {10.1007/978-3-642-17758-3_31}, language = {EN}, location = {Chicago, IL, USA}, pdf = {https://www.itec.aau.at/bib/files/Ransburg_IWMMN10.pdf}, talkdate = {2010.06.30}, talktype = {registered}, url = {http://www.mobilware.org/2010/} } @InProceedings{OrtizMurillo2010, author = {Ortiz Murillo, Jordi and Ransburg, Michael and Martínez Graciá, Eduardo and Sablatschan, Michael and Gómez Skarmeta, Antonio and Hellwagner, Hermann}, booktitle = {Proceedings of the Workshop on Quality of Experience for Multimedia Content Sharing (QoEMCS 2010)}, title = {Towards User-driven Adaptation of H.264/SVC Streams}, year = {2010}, address = {Tampere, Finland}, editor = {Buchinger, Shelley and Lopes, Rui Jorge and Jumisko-Pyykkö, Satu and Zepernick, Hans-Jürgen}, month = {jun}, pages = {4}, publisher = {Tampere University of Technology}, abstract = {H.264/SVC enables runtime-efficient scalability in the spatial, temporal and fidelity dimension. Existing adaptation mechanisms facilitate this to automatically adapt the H.264/ SVC stream to the current usage environment without any user interaction. This paper argues that the Quality of Experience (QoE) of the end user can be enhanced by enabling him to manually adjust the adaptation if he wishes to do so. An approach which enables this is presented and evaluated. It is shown that by facilitating this approach an increased QoE is provided compared to automatic adaptation approaches. Finally, future work indicates the next steps in order to implement this approach.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Towards User-driven Adaptation of H.264-SVC Streams.pdf}, talktype = {none}, url = {http://dcti.iscte.pt/events/qoemcs/} } @InProceedings{MLux_2010, author = {Chatzchristofis, Sawas and Boutalis, Yiannis and Lux, Mathias}, booktitle = {Agents and Artificial Intelligence}, title = {Combining Color and Spatial Color Distribution Information in a Fuzzy Rule Based Compact Composite Descriptor}, year = {2010}, address = {Heidelberg, Germany}, editor = {Filipe, Joaquim and Fred, Ana and Sharp, Bernadette}, month = {jan}, pages = {pp. 49-60}, publisher = {Springer}, abstract = {In this paper, a novel low level feature for content based image retrieval is presented. The proposed feature structure combines color and spatial color distribution information. The combination of these two features in one vector classifies the proposed descriptor to the family of Composite Descriptors. In order to extract the color information, a fuzzy system is being used, which is mapping the number of colors that are included in the image into a custom palette of 8 colors. The way by which the vector of the proposed descriptor is being formed, describes the color spatial information contained in images. To be applicable in the design of large image databases, the proposed descriptor is compact, requiring only 48 bytes per image. Experiments presented in this paper demonstrate the effectiveness of the proposed technique especially for Hand-Drawn Sketches.}, doi = {10.1007/978-3-642-19890-8_4}, edition = {129}, isbn10 = {978-3-642-19889-2}, isbn13 = {978-3-642-19890-8}, language = {EN}, subtitle = {Communications in Computer and Information Science}, talktype = {none} } @InProceedings{Lux2010e, author = {Lux, Mathias and Schoeffmann, Klaus and del Fabro, Manfred and Kogler, Marian and Taschwer, Mario}, booktitle = {TRECVID 2010 Participant Notebook Papers}, title = {ITEC-UNIKLU Known-Item Search Submission}, year = {2010}, address = {Gaithersburg, USA}, editor = {Over, Paul and Awad, George and Fiscus, Jonathan and Michel, Martial and Kraaij, Wessel and Smeaton, Alan and Quénot, Georges}, month = {jan}, pages = {9}, publisher = {National Institute of Standards and Technology (NIST)}, language = {EN}, talktype = {none}, url = {http://www-nlpir.nist.gov/projects/tvpubs/tv.pubs.org.html} } @InProceedings{Lux2010c, author = {Lux, Mathias and Kogler, Marian and del Fabro, Manfred}, booktitle = {Proceedings of the 2010 ACM workshop on Social, adaptive and personalized multimedia interaction and access}, title = {Why did you take this photo: a study on user intentions in digital photo productions}, year = {2010}, address = {New York, NY, USA}, editor = {Vallet, David and Ramzan, Naeem and Halvey, Martin and Patrikakis, Charalampos}, month = {jan}, pages = {41–44}, publisher = {ACM}, series = {SAPMIA '10}, abstract = {Why do people take pictures? While substantial work has been done on the intentions of people producing photos in specific domains (e.g. Flickr users or mobile phone cameras) the general case - arbitrary users taking photos with arbitrary devices - has not yet been investigated in detail. In this short paper, we present an exploratory study on the intentions and goals of people taking digital photos. 40 different specific photo taking situations of 10 people where investigated. We classified the situations and reflected them into context of existing work to investigate the applicability and usefulness of classifications existing for specific domains. Our findings show that applicability of existing models for small domains is limited and they indicate the need of a generalized taxonomy. We further identify hypotheses and research questions for future work in this area.}, doi = {http://doi.acm.org/10.1145/1878061.1878075}, keywords = {camera usage, digital photos, user intentions}, language = {EN}, talktype = {none}, url = {http://doi.acm.org/10.1145/1878061.1878075} } @InProceedings{Lux2010a, author = {Lux, Mathias and Pitman, Arthur and Marques, Oge}, booktitle = {Proceedings of the 11th International Workshop of the Multimedia Metadata Community (WISMA 2010)}, title = {Callisto: Tag Recommendations by Image Content}, year = {2010}, address = {Barcelona, Spain}, editor = {Carreras, Anna and Delgado, Jaime and Maroñas, Xavier and Rodríguez, Victor}, month = {May}, pages = {87-88}, publisher = {ceur.ws}, language = {EN}, talktype = {none} } @InProceedings{Lux2010, author = {Lux, Mathias and Kofler, Christopher and Marques, Oge}, booktitle = {CHI EA '10 CHI '10 Extended Abstracts on Human Factors in Computing Systems}, title = {A Classification Scheme for User Intentions in Image Search}, year = {2010}, address = {Atlanta, GA, USA}, editor = {Fitzpatrick, Geraldine and Hudson, Scott and Edwards, Keith and Rodden, Tom}, month = {April}, pages = {3913-3918}, publisher = {ACM}, abstract = {Searching for images on the web is still an open problem. While multiple approaches have been presented, there has been surprisingly little work on the actual goals and intentions of users. In this poster we present our classification scheme for user goals in image search and describe our ongoing work focusing on identification and classification of user intentions during image search tasks.}, language = {EN}, talktype = {none} } @InProceedings{Kuschnig2010a, author = {Kuschnig, Robert and Kofler, Ingo and Hellwagner, Hermann}, booktitle = {Proceedings of the First Annual ACM SIGMM Conference on Multimedia Systems (MMSys)}, title = {An Evaluation of TCP-based Rate-control Algorithms for Adaptive Internet Streaming of H.264/SVC}, year = {2010}, address = {New York, NY, USA}, editor = {Feng, Wu-chi and Mayer-Patel, Ketan}, month = {feb}, pages = {157-168}, publisher = {ACM}, abstract = {Recent work in TCP video streaming indicates that multimedia streaming via TCP provides satisfactory performance when the achievable TCP throughput is approximately twice the media bit rate. However, these conditions may not be achievable on the Internet, e.g., when the delivery path offers insufficient bandwidth or becomes congested due to competing traffic. Therefore, adaptive streaming for videos over TCP is required and a number of rate-control algorithms for video streaming have been proposed and evaluated in the literature. In this paper, we evaluate and compare three existing rate-control algorithms for TCP streaming in terms of the (PSNR) quality of the delivered video and in terms of the timeliness of delivery. The contribution of the paper is that, to the best of our knowledge, this is the first evaluation of TCP-based streaming in an Internet-like setting making use of the scalability features of the H.264/SVC video codec. Two simple bandwidth estimation algorithms and a priority-/deadline-driven approach are described to adapt the bit rates of, and transmit, the H.264/SVC video in a rate-distortion optimal manner. The results indicate that the three algorithms perform robustly in terms of video quality and timely delivery, both on under-provisioned links and in case of competing TCP flows. The priority-/deadline-driven technique is even more stable in terms of packet delays and jitter; thus, client buffers can be dimensioned more easily.}, doi = {10.1145/1730836.1730856}, language = {EN}, location = {Scottsdale, AZ, USA}, pdf = {https://www.itec.aau.at/bib/files/MMSYS10_Kuschnig_Evaluation_TCP_based_Rate_Control.pdf}, talkdate = {2010.02.23}, talktype = {registered}, url = {http://www.mmsys.org} } @InProceedings{Kuschnig2010, author = {Kuschnig, Robert and Kofler, Ingo and Hellwagner, Hermann}, booktitle = {Proceedings of the 7th IEEE Consumer Communications and Networking Conference (CCNC)}, title = {Improving Internet Video Streaming Performance by Parallel TCP-Based Request-Response Streams}, year = {2010}, address = {Los Alamitos, CA, USA}, editor = {Balandin, Sergey and Matuszewksi, Marcin and Ott, Jörg}, month = {jan}, pages = {5}, publisher = {IEEE}, abstract = {TCP-based video streaming encounters difficulties in unreliable networks with unanticipated packet loss. In combination with high round trip times, the effective throughput deteriorates rapidly and TCP connection resets or stalls may occur. In this paper, we propose a client-driven video transmission scheme which utilizes multiple HTTP/TCP streams. The scheme is largely insensitive to unanticipated packet loss and thereby reduces throughput fluctuations. Since it is based on HTTP, the scheme can easily be deployed in existing network infrastructures. It fosters scalability on the server side by shifting complexity from the server to the clients. Certain features of request-response schemes allow maintaining fairness, despite of using multiple HTTP streams. Making use of TCP, the scheme inherently adapts to congested network links.}, doi = {10.1145/1730836.1730856}, language = {EN}, location = {Las Vegas, NV, USA}, pdf = {https://www.itec.aau.at/bib/files/CCNC10_Kuschnig_Request_Response_Streams.pdf}, talkdate = {2010.01.10}, talktype = {registered}, url = {http://www.ieee-ccnc.org/2010} } @InProceedings{Kogler:2010:BVW:1814245.1814248, author = {Kogler, Marian and Lux, Mathias}, booktitle = {Proceedings of the Tenth International Workshop on Multimedia Data Mining}, title = {Bag of visual words revisited: an exploratory study on robust image retrieval exploiting fuzzy codebooks}, year = {2010}, address = {New York, NY, USA}, editor = {","}, month = {jul}, pages = {3:1--3:6}, publisher = {ACM}, language = {EN}, talktype = {none} } @InProceedings{Eberhard2010, author = {Eberhard, Michael and Szkaliczki, Tibor and Hellwagner, Hermann and Szobonya, László and Timmerer, Christian}, booktitle = {Proceedings of the 2010 ACM Workshop on Advanced Video Streaming Techniques for Peer-to-Peer Networks and Social Networking}, title = {Knapsack Problem-based Piece-Picking Algorithms for Layered Content in Peer-to-Peer Networks}, year = {2010}, address = {New York, NY, USA}, editor = {Olmo, Gabriella and Timmerer, Christian and Frossard, Pascal and Mitchell, Keith}, month = {oct}, pages = {71--76}, publisher = {ACM}, series = {AVSTP2P}, abstract = {The distribution of layered content over peer-to-peer networks becomes more important today as the users are consuming the content on terminals with various display capabilities and different network connections. For single-layer content distribution, the piece-picking algorithm only needs to ensure that content pieces are downloaded in time for display. When layered content is distributed over a peer-to-peer network, the piece-picking algorithm needs to be modified to ensure that the best possible quality is displayed while all desired pieces still have to be received before their deadline expires. In this paper, the piece-picking problem for layered content is analyzed and a number of piece-picking algorithms for layered content based on the solutions for the knapsack problem are presented. Furthermore, an evaluation of these algorithms is performed and possible applications are discussed.}, doi = {10.1145/1877891.1877908}, isbn13 = {978-1-4503-0169-5}, keywords = {knapsack problem, layered/scalable content, piece utility calculation, piece-picking}, language = {EN}, location = {Firenze, Italy}, pdf = {https://www.itec.aau.at/bib/files/avst1524-eberhard.pdf}, talkdate = {2010.10.29}, talktype = {poster}, url = {http://www.p2pstreaming.eu} } @InProceedings{DelFabro2010a, author = {Del Fabro, Manfred and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Proceedings of HCI in Work and Learning, Life and Leisure 6th Symposium of the Workgroup Human-Computer Interaction and Usability Engineering}, title = {Instant Video Browsing: A Tool for Fast Non-sequential Hierarchical Video Browsing}, year = {2010}, address = {Berlin, Heidelberg, New York}, editor = {Leitner, Gerhard and Hitz, Martin and Holzinger, Andreas}, month = {nov}, pages = {443-446}, publisher = {Springer Verlag GmbH}, abstract = {We introduce an easy-to-use video browsing tool which assists users in getting a quick overview of videos as well as in finding segments of interest. It provides a parallel and a tree-based view for browsing the content of videos -- or even video collections -- in a hierarchical, non-sequential manner. The tool has a plug-in architecture and can be extended both by further presentation methods and by video analysis algorithms.}, doi = {10.1007/978-3-642-16607-5_30}, language = {EN}, location = {Klagenfurt, Austria}, pdf = {https://www.itec.aau.at/bib/files/Instant Video Browsing - A Tool for Fast Non-Sequential Hierarchical Video Browsing.pdf}, talkdate = {2010.11.05}, talktype = {registered} } @InProceedings{DelFabro2010, author = {Del Fabro, Manfred and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the Second International Conference on Advances in Multimedia (MMEDIA 2010)}, title = {Video Scene Detection Based on Recurring Motion Patterns}, year = {2010}, address = {Washington (DC)}, editor = {Böszörmenyi, Laszlo and Burdescu, Dumitru and Davies, Philip and Newell, David}, month = {jun}, pages = {113--118}, publisher = {IEEE}, abstract = {We present an algorithm for video scene detection based on the identification of recurring motion sequences within a video stream. The motion information is extracted in the compressed domain of H.264/AVC videos, no full decoding of the video stream is needed. Based on the motion information our algorithm identifies sequences of adjacent frames with similar motion. Throughout all identified motion sequences we are searching for recurring patterns of similar ones. The most recurring pattern is used for the segmentation of the video stream into scenes. The evaluation shows promising results.}, doi = {10.1109/MMEDIA.2010.26}, language = {EN}, location = {Athens, Greece}, pdf = {https://www.itec.aau.at/bib/files/4068a113.pdf}, talkdate = {2010.06.15}, talktype = {registered} } @InProceedings{Capovilla2010, author = {Capovilla, Nicola and Eberhard, Michael and Mignanti, Silvano and Petrocco, Riccardo and Vehkaperä, Janne}, booktitle = {Proceedings of the Second International Conferences on Advances in Multimedia (MMEDIA 2010)}, title = {An Architecture for Distributing Scalable Content over Peer-to-Peer Networks}, year = {2010}, address = {Los Alamitos, CA, USA}, editor = {Böszörmenyi, Laszlo and Burdescu, Dumitru and Davis, Philip and Stanchev, Peter}, month = {jun}, pages = {1-6}, publisher = {IEEE}, abstract = {Peer-to-Peer systems are nowadays a very popular solution for multimedia distribution, as they provide significant cost benefits compared with traditional server-client distribution. Additionally, the distribution of scalable content enables the consumption of the content in a quality suited for the available bandwidth and the capabilities of the end-user devices. Thus, the distribution of scalable content over Peer-to-Peer networks is a very actual research topic. This paper presents an architecture for the distribution of scalable content in a fully distributed Peer-to-Peer network. The architectural description includes how the scalable layers of the content are mapped to the pieces distributed in the Peer-to-Peer system and detailed descriptions of the producer- and consumer-site architecture of the system. The presented system is to our knowledge the first open-source Peer-to-Peer network with full Scalable Video Coding support.}, doi = {10.1109/MMEDIA.2010.17}, keywords = {P2P networks;consumer-site architecture;distributed peer-to-peer network;multimedia distribution;open-source peer-to-peer network;scalable video coding;server-client distribution;image coding;multimedia computing;peer-to-peer computing;}, language = {EN}, location = {Athens, Greece}, pdf = {https://www.itec.aau.at/bib/files/MMEDIA'10_Eberhard.pdf}, talkdate = {2010.06.14}, talktype = {registered}, url = {http://www.iaria.org/conferences2010/MMEDIA10.html} } @InProceedings{Borcoci2010, author = {Borcoci, Eugen and Negru, Daniel and Timmerer, Christian}, booktitle = {Proceedings of the 3rd International Conference on Communication Theory, Reliability, and Quality of Service (CTRQ 2010)}, title = {A Novel Architecture for Multimedia Distribution based on Content-Aware Networking}, year = {2010}, address = {Los Alamitos, CA, USA}, editor = {Ata, Shingo and Borcoci, Eugen and Del Ser Lorente, Javier and Diaz, Michel and Pioro, Michal and Rodrigues, Joel and Segall, Zary}, month = {jun}, pages = {162--168}, publisher = {IEEE}, abstract = {This paper proposes a novel virtual Content-Aware Network (CAN) layer as a part of a full layered architecture, focused, but not limited to, on multimedia distribution with Quality of Services (QoS) assurance. The overall system is based on a flexible cooperation between providers, operators and end-users, enabling users to access the offered multimedia services in various contexts and also to become private content providers. The paper introduces the main concepts and architecture for the main virtual network layer (i.e., CAN), exposing its role and interfaces among overall system layers. This work is a part of the starting effort inside of a new European FP7 ICT research project, ALICANTE.}, doi = {10.1109/CTRQ.2010.35}, keywords = {content-aware networking, network aware applications, quality of services, multimedia distribution, Future Internet}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/05532769.pdf}, talktype = {none}, url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5532769&isnumber=5532402} } @InProceedings{Waltl2009, author = {Waltl, Markus and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the First International Workshop on Quality of Multimedia Experience (QoMEX 2009)}, title = {A Test-Bed for Quality of Multimedia Experience Evaluation of Sensory Effects}, year = {2009}, address = {Los Alamitos, CA, USA}, editor = {Ebrahim, Touradj and El-Maleh, Khaled and Dane, Gokce and Karam, Lina}, month = {jul}, pages = {145-150}, publisher = {IEEE}, abstract = {This paper introduces a prototype test-bed for triggering sensory effects like light, wind, or vibration when presenting audiovisual resources, e.g., a video, to users. The ISO/IEC MPEG is currently standardizing the Sensory Effect Description Language (SEDL) for describing such effects. This language is briefly described in the paper and the testbed that is destined to evaluate the quality of the multimedia experience of users is presented. It consists of a video annotation tool for sensory effects, a corresponding simulation tool, and a real test system. Initial experiments and results on determining the color of light effects from the video content are reported.}, doi = {10.1109/QOMEX.2009.5246962}, isbn13 = {978-1-4244-4370-3}, issn = {978-1-4244-43}, keywords = {Sensory Information, MPEG-V}, language = {EN}, location = {San Diego, CA}, pdf = {https://www.itec.aau.at/bib/files/qomex2009_mwcthh.pdf}, talkdate = {2009.07.31}, talktype = {registered}, url = {http://www.qomex2009.org} } @InProceedings{Timmerer2009a, author = {Timmerer, Christian and Gelissen, Jean and Waltl, Markus and Hellwagner, Hermann}, booktitle = {Proceedings of the 2009 NEM Summit}, title = {Interfacing with Virtual Worlds}, year = {2009}, address = {Heidelberg}, editor = {Hrasnica, Halid}, month = sep, pages = {118-123}, publisher = {Eurescom – the European Institute for Research and Strategic Studies in Telecommunications – GmbH}, abstract = {Virtual worlds (often referred to as 3D3C for 3D visualization & navigation and the 3C’s of Community, Creation and Commerce) integrate existing and emerging (media) technologies (e.g. instant messaging, video, 3D, VR, AI, chat, voice, etc.) that allow for the support of existing and the development of new kinds of networked services. The emergence of virtual worlds as platforms for networked services is recognized by businesses as an important enabler as it offers the power to reshape the way companies interact with their environments (markets, customers, suppliers, creators, stakeholders, etc.) in a fashion comparable to the Internet and to allow for the development of new (breakthrough) business models, services, applications and devices. Each virtual world however has a different culture and audience making use of these specific worlds for a variety of reasons. These differences in existing Metaverses permit users to have unique experiences. In order to bridge these differences in existing and emerging Metaverses a standardized framework is required, i.e., MPEG-V Media Context and Control (ISO/IEC 23005), that will provide a lower entry level to (multiple) virtual worlds both for the provider of goods and services as well as the user. The aim of this paper is to provide an overview of MPEG-V and its intended standardization areas. Additionally, a review about MPEG-V’s most advanced part – Sensory Information – is given.}, issn = {9783000289538}, keywords = {MPEG-V}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/nem2009_ctjgmwhh.pdf}, talktype = {none}, url = {http://www.nem-summit.eu} } @InProceedings{Timmerer2009, author = {Timmerer, Christian and Jaborning, Johannes and Hellwagner, Hermann}, booktitle = {Proceedings of the 9th Workshop on Multimedia Metadata (WMM'09)}, title = {A Comparison and Mapping Model}, year = {2009}, address = {Aachen, Germany}, editor = {Klamma, Ralf and Grigoras, Romulus and Charvillat, Vincent and Kosch, Harald}, month = mar, pages = {18}, publisher = {http://ceur-ws.org}, abstract = {Nowadays, mobile devices have implemented several transmission technologies which enable access to the Internet and increase the bit rate for data exchange. Despite modern mobile processors and high-resolution displays, mobile devices will never reach the stage of a powerful notebook or desktop system (for example, due to the fact of battery powered CPUs or just concerning the smallsized displays). Due to these limitations, the deliverable content for these devices should be adapted based on their capabilities including a variety of aspects (e.g., from terminal to network characteristics). These capabilities should be described in an interoperable way. In practice, however, there are many standards available and a common mapping model between these standards is not in place. Therefore, in this paper we describe such a mapping model and its implementation aspects. In particular, we focus on the whole delivery context (i.e., terminal capabilities, network characteristics, user preferences, etc.) and investigated the two most prominent state-of-the-art description schemes, namely User Agent Profile (UAProf) and Usage Environment Description (UED).}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/DC-paper-v.2.pdf}, talktype = {none}, url = {http://ceur-ws.org/Vol-441/pxx.pdf} } @InProceedings{Sobe2009b, author = {Sobe, Anita and Böszörmenyi, Laszlo}, booktitle = {2009 First International Conference on Advances in Multimedia}, title = {{Non-sequential Multimedia Caching}}, year = {2009}, address = {Los Alamitos, CA, USA}, editor = {Burdescu, Dan and Dini, Petre}, month = jul, pages = {158--161}, publisher = {IEEE}, series = {MMedia'2009}, doi = {10.1109/MMEDIA.2009.36}, language = {EN}, location = {Colmar, France}, talkdate = {2009.07.25}, talktype = {registered} } @InProceedings{Schoeffmann2009e, author = {Schoeffmann, Klaus and Lux, Mathias and Taschwer, Mario and Böszörmenyi, Laszlo}, booktitle = {ICME'09 Proceedings of the 2009 IEEE international Conference on Multimedia and Expo}, title = {Visualization of Video Motion in Context of Video Browsing}, year = {2009}, address = {Los Alamitos, CA, USA}, editor = {Lin, CY and Cox, I}, month = jul, pages = {658-661}, publisher = {IEEE}, abstract = {We present a new approach for video browsing using visualization of motion direction and motion intensity statistics by color and brightness variations. Statistics are collected from motion vectors of H.264/AVC encoded video streams, so full video decoding is not required. By interpreting visualized motion patterns of video segments, users are able to quickly identify scenes similar to a prototype scene or identify potential scenes of interest. We give some examples of motion patterns with different semantic value, including camera zooms, hill jumps of ski-jumpers, and the repeated appearance of a news speaker. In a user study we show that certain scenes of interest can be found significantly faster using our video browsing tool than using a video player with VCR-like controls.}, issn = {9781424442911}, language = {EN}, talktype = {none}, url = {http://dl.acm.org/citation.cfm?id=1698924.1699086} } @InProceedings{Schoeffmann2009d, author = {Schoeffmann, Klaus and Taschwer, Mario and Böszörmenyi, Laszlo}, booktitle = {Proceedings oft the International Conference on Multimedia and Expo 2009}, title = {Video Browsing Using Motion Visualization}, year = {2009}, address = {Los Alamitos, CA, USA}, editor = {Lin, CY and Cox, I}, month = jul, pages = {1835-1836}, publisher = {IEEE}, abstract = {We present a video browsing tool that uses a novel and powerful visualization technique of video motion. The tool provides an interactive navigation index that allows users to quickly and easily recognize content semantics like scenes with fast/slow motion (in general or according to a specific direction), scenes showing still/moving objects in front of a still/moving background, camera pans, or camera zooms. Moreover, the visualization facilitates identification of similar segments in a video. A first user study has shown encouraging results.}, issn = {1945-788X}, language = {EN}, talktype = {none} } @InProceedings{Schoeffmann2009c, author = {Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Content-Based Multimedia Indexing, 2009. CBMI '09}, title = {Video Browsing Using Interactive Navigation Summaries}, year = {2009}, address = {Los Alamitos, CA, USA}, editor = {Avrithis, Yannis and Kollias, Stefanos}, month = jul, pages = {243-248}, publisher = {IEEE}, abstract = {A new approach for interactive video browsing is described. The novelty of the proposed approach is the flexible concept of interactive navigation summaries. Similar to time sliders, commonly used with standard soft video players, navigation summaries allow random access to a video. In addition, they also provide abstract visualizations of the content at a user-defined level of detail and, thus, quickly communicate content characteristics to the user. Navigation summaries can provide visual information about both low-level features but even high-level features. The concept fully integrates the user, who knows best which navigation summary at which level of detail could be most beneficial for his/her current video browsing task, and provide him/her a flexible set of navigation means. A first user study has shown that our approach can significantly outperform standard soft video players - the state-of-the art “poor man’s” video browsing tool.}, doi = {10.1109/CBMI.2009.40}, issn = {9780769536620}, language = {EN}, location = {Chania, Crete}, talkdate = {2009.06.04}, talktype = {registered} } @InProceedings{Schoeffmann2009b, author = {Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Advance in Semantic Media Adaptation and Personalization}, title = {Interactive Video Browsing of H.264 Content Based on Just-in-Time Analysis}, year = {2009}, address = {Boca Raton, FL, USA}, editor = {Angelides, Marios C and Mylonas, Phivos}, month = feb, pages = {159-179}, publisher = {Auerbach Publications}, isbn10 = {1420076647}, isbn13 = {978-1420076646}, language = {EN}, talktype = {none} } @InProceedings{Schoeffmann2009, author = {Schoeffmann, Klaus and Lux, Mathias and Böszörmenyi, Laszlo}, booktitle = {Advances in Multimedia Modeling}, title = {A Novel Approach for Fast and Accurate Commercial Detection in H.264/AVC Bit Streams Based on Logo Identification}, year = {2009}, address = {Berlin, Heidelberg, New York}, editor = {Huet, Benoit and Smeaton, Alan and Mayer-Patel, Ketan and Avrithis, Yannis}, month = jan, pages = {119-127}, publisher = {Springer}, series = {Lecture Notes in Computer Sciences}, abstract = {Commercial blocks provide no extra value for video indexing, retrieval, archiving, or summarization of TV broadcasts. Therefore, automatic detection of commercial blocks is an important topic in the domain of multimedia information systems. We present a commercial detection approach which is based on logo detection performed in the compressed domain. The novelty of our approach is that by taking advantage of advanced features of the H.264/AVC coding, it is both significantly faster and more exact than existing approaches working directly on compressed data. Our approach enables removal of commercials in a fraction of real-time while achieving an average recall of 97.33% with an average precision of 99.31%. Moreover, due to its run-time performance, our approach can also be employed on low performance devices, for instance DVB recorders.}, doi = {10.1007/978-3-540-92892-8_13}, isbn10 = {978-3-540-92891-1}, language = {EN}, talktype = {none}, url = {http://www.springer.com/computer/information+systems/book/978-3-540-92891-1} } @InProceedings{Reiterer2009b, author = {Reiterer, Bernhard and Concolato, Cyril and Hellwagner, Hermann}, booktitle = {Proceedings of 1st International ICST Conference on User Centric Media - UCMedia 2009}, title = {Natural-Language-based Conversion of Images to Mobile Multimedia Experiences}, year = {2009}, address = {Berlin, Heidelberg, New York}, editor = {Daras, Patros and Chlamtac, Imrich}, month = dec, pages = {4 - CD}, publisher = {Springer}, series = {LNICST - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering}, abstract = {We describe an approach for viewing any large, detail-rich picture on a small display by generating a video from the image, as taken by a virtual camera moving across it at varying distance. Our main innovation is the ability to build the virtual camera's motion from a textual description of a picture, e.g., a museum caption, so that relevance and ordering of image regions are determined by co-analyzing image annotations and natural language text. Furthermore, our system arranges the resulting presentation such that it is synchronized with an audio track generated from the text by use of a text-to-speech system.}, issn = {9789639799844}, keywords = {image adaptation - text analysis - image annotation - digital cultural heritage - computer animation}, language = {EN}, talktype = {none}, url = {http://www.usercentricmedia.org/index.shtml} } @InProceedings{Reiterer2009a, author = {Reiterer, Bernhard and Hellwagner, Hermann}, booktitle = {Proceedings International InterMedia Summer School 2009}, title = {Animated Picture Presentation Steered by Natural Language}, year = {2009}, address = {Geneva}, editor = {Nadia, Magnenat-Thalmann and Seunghyun, Han and Dimitris, Potopsaltou}, month = jun, pages = {24-32}, publisher = {MIRALab at University of Geneva}, series = {International InterMedia Summer School}, abstract = {In this paper, we present an approach for presenting large, feature-rich pictures on small displays by generating an animation and subsequently a video from the image, as it could be taken by a virtual camera moving across the image. Our main innovation is the ability to build the virtual camera's motion upon a textual description of a picture, as from a museum caption, so that relevance and ordering of image regions is determined by co-analyzing image annotations and text. Furthermore, our system can arrange the resulting presentation in a way that it is synchronized with an audio track generated from the text by use of a text-to-speech system.}, keywords = {image adaptation, text parsing, image annotation, digital cultural heritage, computer animation}, language = {EN}, talktype = {none}, url = {http://intermediaschool.miralab.unige.ch/} } @InProceedings{Reiterer2009, author = {Reiterer, Bernhard and Lachner, Janine and Lorenz, Andreas and Zimmermann, Andreas and Hellwagner, Hermann}, booktitle = {Advances in Semantic Media Adaptation and Personalization}, title = {Research Directions Toward User-centric Multimedia}, year = {2009}, address = {Boca Raton (Florida)}, editor = {Angelides, Marios C and Mylonas, Phivos and Wallace, Manolis}, month = mar, pages = {21-42}, publisher = {Auerbach Publications}, abstract = {Currently, much research aims at coping with the shortcomings in multimedia consumption that may exist in a user's current context, e.g., due to the absence of appropriate devices at many locations, a lack of capabilities of mobile devices, restricted access to content, or non-personalized user interfaces. Recently, solutions to specific problems have been emerging, e.g., wireless access to multimedia repositories over standardized interfaces; however, due to usability restrictions the user has to spend much effort to or is even incapable of fulfilling his/her demands. The vision of user-centric multimedia places the user in the center of multimedia services to support his/her multimedia consumption intelligently, dealing with the aforementioned issues while minimizing required work. Essential features of such a vision are comprehensive context awareness, personalized user interfaces, and multimedia content adaptation. These aspects are addressed in this paper as major challenges toward a user-centric multimedia framework.}, doi = {10.1201/9781420076653-c2}, edition = {2}, isbn10 = {1420076647}, isbn13 = {978-1420076646}, issn = {9781420076646}, language = {EN}, talktype = {none}, url = {http://www.crcpress.com/product/isbn/9781420076646} } @InProceedings{Lux2009b, author = {Lux, Mathias}, booktitle = {Multimedia, 2009. ISM '09. 11th IEEE International Symposium on}, title = {An Evaluation of Metrics for Retrieval of MPEG-7 Semantic Descriptions}, year = {2009}, address = {Los Alamitos, CA, USA}, editor = {Tsai, Jeffrey and Jain, Ramesh}, month = dec, pages = {546-551}, publisher = {IEEE}, abstract = {MPEG-7 is an extensive multimedia metadata standard covering a huge number of aspects of metadata. However, as with most metadata standards details of usage and application of the standards are – at least partially – open to interpretation. In case of MPEG-7storage and transmission of high level metadata on concept level are defined but retrieval methods are not proposed. So if for instance a user annotates photos using the MPEG-7 semantic description scheme, there are no standardized ways to retrieve the photos based on the annotation. In this paper we propose metrics for retrieval based on the MPEG-7 semantic description scheme and evaluate them in a digital photo retrieval scenario.}, doi = {10.1109/ISM.2009.104}, isbn10 = {978-1-4244-5231-6}, language = {EN}, talktype = {none} } @InProceedings{Lux2009, author = {Lux, Mathias and Schoeffmann, Klaus and Marques, Oge and Böszörmenyi, Laszlo}, booktitle = {9th Workshop on Multimedia Metadata (WMM'09)}, title = {A Novel Tool for Quick Video Summarization using Keyframe Extraction Techniques}, year = {2009}, address = {Aachen, Germany}, editor = {Grigoras, Romulus and Charvillat, Vincent and Klamma, Ralf and Kosch, Harald}, month = mar, pages = {62-76}, publisher = {http://ceur-ws.org}, abstract = {The increasing availability of short, unstructured video clips on the Web has generated an unprecedented need to organize, index, annotate and retrieve video contents to make them useful to potential viewers. This paper presents a novel, simple, and easy-to-use tool to benchmark different low level features for video summarization based on keyframe extraction. Moreover, it shows the usefulness of the benchmarking tool by developing hypothesis for a chosen domain through an exploratory study. It discusses the results of exploratory studies involving users and their judgment of what makes the summary generated by the tool a good one.}, language = {EN}, talktype = {none}, url = {http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-441/p04.pdf} } @InProceedings{Kogler2009, author = {Kogler, Marian and Del Fabro, Manfred and Lux, Mathias and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 10th International Workshop of the Multimedia Metadata Community on Semantic Multimedia Database Technologies (SeMuDaTe'09) in conjunction with the 4th International Conference on Semantic and Digital Media Technologies (SAMT 2009)}, title = {Global vs. Local Feature in Video Summarization: Experimental Results}, year = {2009}, address = {Aachen, Germany}, editor = {Ralf, Klamma and Harald, Kosch and Lux, Mathias and Florian, Stegmaier}, month = dec, pages = {6}, publisher = {http://ceur-ws.org}, language = {EN}, talktype = {none}, url = {http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-539/} } @InProceedings{Kofler2009c, author = {Kofler, Christoph and Lux, Mathias}, booktitle = {MM '09 Proceedings of the 17th ACM international conference on Multimedia}, title = {Dynamic presentation adaptation based on user intent classification.}, year = {2009}, address = {NA}, editor = {Gao, Wen and Tui, Yong and Hanjalic, Alan}, month = oct, pages = {1117-1118}, publisher = {NA}, abstract = {Results of internet searches are typically presented as lists. When searching for digital photos different search result presentations however offer different benefits. If users are primarily interested in the visual content of images a thumbnail grid may be more appropriate than a list. For people searching photos taken at a specific place image metadata in the result presentation is of interest too. In this paper we present an application which monitors a user's behavior while searching for digital photos and classifies the user's intention. Based on the intention, the result is adapted to support the user in an optimal way.}, doi = {10.1145/1631272.1631526}, language = {EN}, talktype = {none}, url = {http://dl.acm.org/citation.cfm?id=1631526} } @InProceedings{Kofler2009b, author = {Kofler, Christoph and Lux, Mathias}, booktitle = {Proceedings of I-KNOW ’09 and I-SEMANTICS ’09}, title = {An Exploratory Study on the Explicitness of User Intentions in Digital Photo Retrieval.}, year = {2009}, address = {Graz, Austria}, editor = {Tochtermann, Klaus and Maurer, Hermann}, month = sep, pages = {208-214}, publisher = {TU Graz \& Know Center}, abstract = {Search queries are typically interpreted as specification of information need of a user. Typically the search query is either interpreted as is or based on the context of a user, being for instance a user profile, his/her previously undertaken searches or any other background information. The actual intent of the user – the goal s/he wants to achieve with information retrieval – is an important part of a user’s context. In this paper we present the results of an exploratory study on the interplay between the goals of users and their search behavior in multimedia retrieval.}, language = {EN}, talktype = {none}, url = {http://www.i-know.tugraz.at/2009/papers/an_exploratory_study_explicitness_user_intentions.pdf} } @InProceedings{Kofler2009a, author = {Kofler, Ingo and Kuschnig, Robert and Hellwagner, Hermann}, booktitle = {Proceedings of the IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)}, title = {Improving IPTV Services by H.264/SVC Adaptation and Traffic Control}, year = {2009}, address = {Los Alamitos, CA, USA}, editor = {Angueira, Pablo and Reimers, Ulrich}, month = may, pages = {1-6}, publisher = {IEEE}, series = {BMSB}, abstract = {This paper presents a novel approach that combines both in-network, application-layer adaptation and network-layer traffic control of scalable video streams based on the H.264/SVC standard. In the IPTV/VoD scenario considered, an intercepting RTSP/RTP proxy performs admission control of the requested video, based on the signaled scalability information, and decides whether the content can be streamed without changes or in an adapted version. The proxy configures the network layer appropriately in order to separate the video stream from besteffort traffic on the same link. Rather than performing fixed bandwidth allocation, our proxy approach uses the Hierarchical Token Bucket (HTB) queuing discipline to allow for borrowing bandwidth between traffic classes. In that setting, two different allocation policies are introduced. The Hard Reservation Policy (HRP) performs admission control and adaptation on the video streams and does not modify video bandwidth allocation after admission. In contrast, the Flexible Borrowing Policy (FBP) restricts the admission control to the base layer of the SVC stream. The packets carrying MGS enhancement layer data are marked with priorities by the proxy and are handled at the network layer by a priority-based queuing mechanism. Both a qualitative comparison and an experimental evaluation of the two policies are given.}, doi = {10.1109/ISBMSB.2009.5133771}, isbn13 = {9781424425907}, language = {EN}, location = {Bilbao, Spain}, talkdate = {2009.05.14}, talktype = {registered}, url = {https://www.itec.aau.at/publications/mmc/BMSB09_Kofler_Improving_IPTV_Services_Preprint.pdf} } @InProceedings{Kofler2009, author = {Kofler, Ingo and Kuschnig, Robert and Hellwagner, Hermann}, booktitle = {Proceedings of the 6th IEEE Consumer Communications and Networking Conference (CCNC)}, title = {In-Network Real-Time Adaptation of Scalable Video Content on a WiFi-ne Router}, year = {2009}, address = {Los Alamitos, CA, USA}, editor = {Gibbs, Simon and Messer, Alan}, month = jan, pages = {2}, publisher = {IEEE}, series = {CCNC}, abstract = {One of the most active research topics in the field of video signal processing is scalable video coding (SVC). The recently published extension of the H.264/AVC video coding standard introduces scalability features by employing a layered encoding of the video stream. In our work we investigated the usage of this scalable extension of H.264/AVC for in-network multimedia adaptation. We developed an RTSP/RTP-based proxy which exploits the layered encoding of the video and can perform real-time video adaptation on an inexpensive off-the-shelf WiFi router. This is achieved by applying a stateful, packet-based adaptation approach that keeps the computational costs at a minimum. With that approach it is possible to simultaneously adapt multiple video streams to varying network conditions or to the capabilities of the consumers' end-devices. In our demonstration we show the streaming of two scalable video streams from a server to a client and the in-network adaptation of the video at the WiFi router. The adaptation can be controlled interactively in the temporal, spatial and SNR domains.}, doi = {10.1109/CCNC.2009.4785005}, isbn13 = {9781424423088}, language = {EN}, location = {Las Vegas, NV, USA}, pdf = {https://www.itec.aau.at/bib/files/CCNC09_SVC_Adaptation_Router_preprint.pdf}, talkdate = {2009.01.11}, talktype = {poster} } @InProceedings{Ferscha2009, author = {Ferscha, Alois and Hellwagner, Hermann and Neuper, Christa and Pree, Wolfgang}, booktitle = {Informatik macht Zukunft - Zukunft macht Informatik}, title = {Zukunft der Informatik}, year = {2009}, address = {Wien}, editor = {Chroust, Gerhard and Moessenboeck, Hans-Peter}, month = dec, pages = {48-51}, publisher = {Oesterreichische Computer Gesellschaft}, isbn10 = {9783854032588}, language = {DE}, talktype = {none} } @InProceedings{Eberhard2009, author = {Eberhard, Michael and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {STreaming Day ’09 Proceedings}, title = {A Layered Piece-Picking Algorithm for Peer-to-Peer Networks}, year = {2009}, address = {NA}, editor = {Raggio, Marko and Rovati, Fabrizio}, month = sep, pages = {n.a.}, publisher = {NA}, abstract = {The streaming of multimedia content over Peer-to-Peer (P2P) networks is nowadays a well appreciated concept, as it helps distributing content to a great number of users and additionally reduces the server costs for providing the content. As the users of P2P networks often have different bandwidth connections and terminals, the same content is usually provided in different qualities. Although such a provision of the same content in different qualities helps to satisfy all users, it makes the sharing process less efficient. Users that are interested in the content in a specific quality can only exchange pieces with those users that are interested in the same content and the same quality. Thus, layered video coding, which provides different qualities within one bitstream, is especially well suited for P2P distribution. If the layered content is provided once in the best quality, all peers interested in this content can at least exchange the base layer, plus the enhancement layers they are interested in with those peers that have them available.}, issn = {9781616236212}, language = {EN}, location = {Genova, Italy}, talkdate = {2009.09.21}, talktype = {registered} } @InProceedings{Chatzichristofis2009a, author = {Chatzichristofis, Savvas A and Boutalis, Yiannis and Lux, Mathias}, booktitle = {SISAP '09 Proceedings of the 2009 Second International Workshop on Similarity Search and Applications}, title = {An Interactive Content Based Image Retrieval System}, year = {2009}, address = {Los Alamitos, CA, USA}, editor = {Skopal, Thomas and Zezula, Pavel}, month = aug, pages = {151-153}, publisher = {IEEE}, abstract = {This paper presents an image retrieval suite called img(Rummager) which brings into effect a number of new as well as state of the art descriptors. The application can execute an image search based on a query image, either from XML-based index files, or directly from a folder containing image files, extracting the comparison features in real time. In addition the img(Rummager) application can execute a hybrid search of images from the application server, combining keyword information and visual similarity. Also img(Rummager) supports easy retrieval evaluation based on the normalized modified retrieval rank (NMRR) and average precision (AP).}, isbn10 = {978-0-7695-3765-8}, language = {EN}, talktype = {none}, url = {http://www.computer.org/portal/web/csdl/doi/10.1109/SISAP.2009.16} } @InProceedings{Chatzichristofis2009, author = {Chatzichristofis, Savvas A and Boutalis, YS and Lux, Mathias}, booktitle = {Signal Processing, Pattern Recognition and Applications (SPPRA 2009)}, title = {Selection of the proper compact composite descriptor for improving content based image retrieval}, year = {2009}, address = {Calgary, Canada}, editor = {Zagar, B}, month = feb, pages = {00-00}, publisher = {ACTA Press}, abstract = {Compact Composite Descriptors (CCD) are global image features capturing both, color and texture characteristics, at the same time in a very compact representation. In this paper we propose a combination of two recently introduced CCDs (CEDD and FCTH) into a Joint Composite Descriptor (JCD). We further present a method for descriptor selection to approach the best ANMRR that would result from CEDD and FCTH. With our approach the most appropriate descriptor in terms of maximization of information content can be found on a per image basis without knowledge of the data set as a whole. Experiments conducted on three known benchmarking image databases demonstrate the effectiveness of the proposed technique.}, language = {EN}, talktype = {none}, url = {http://www.actapress.com/PaperInfo.aspx?PaperID=34669&reason=500} } @InProceedings{Boeszoermenyi2009a, author = {Böszörmenyi, Laszlo}, booktitle = {Informatik macht Zukunft - Zukunft macht Informatik}, title = {Das Ideal der Ausführbarkeit in der Informatik und Gesellschaft}, year = {2009}, address = {Vienna, Austria}, editor = {Chroust, Gerhard and Mössenböck, Hans-Peter}, month = dec, pages = {117-122}, publisher = {OCG}, issn = {9783854032588}, language = {DE}, talktype = {none}, url = {http://www.siabshop.com/ocgbookshop/product_info.php/info/p50_Informatik-macht-Zukunft---Zukunftsmacht-Informatik.html/XTCsid/612c1725ded1d040d0098ae0fe5612a4} } @InProceedings{Boeszoermenyi2009, author = {Böszörmenyi, Laszlo}, booktitle = {Zeit erinnern}, title = {Können sich Computer erinnern?}, year = {2009}, address = {Klagenfurt, Austria}, editor = {Antonitsch, Peter and Scherbantin, Annette and Theuermann, Anneliese and Wakounig, Vladimir}, month = oct, pages = {205-215}, publisher = {Drava Verlag}, series = {Drava Diskurs}, issn = {9783854356004}, language = {DE}, talktype = {none}, url = {http://ifeb.uni-klu.ac.at/index.php?id=120&tx_ttnews[tt_news]=34&tx_ttnews[backPid]=22&cHash=bb0520ffc9} } @InProceedings{Timmerer2008h, author = {Timmerer, Christian and Ransburg, Michael and Kofler, Ingo and Hellwagner, Hermann and Souto, Pedro and Andrade, Maria and Carvalho, Pedro and Castro, Helder and Sidibe, Mamadou and Mehaoua, Ahmed and Fang, Li and Lindsay, Adam and Mackay, Michael and Lugmayr, Artur and Feiten, Bernhard}, booktitle = {Proceedings of the 2nd European Symposium on Mobile Media Delivery (EUMOB)}, title = {An Integrated Management Supervisor for End-to-End Management of Heterogeneous Contents, Networks, and Terminals enabling Quality of Service}, year = {2008}, address = {New York, NY, USA}, editor = {Frantti, Tapio and Huusko, Jyrki}, month = jul, pages = {6}, publisher = {ACM}, series = {EUMOB}, abstract = {End-to-end support for Quality of Service (QoS) has been broadly discussed in the literature. Many technologies have been proposed, each focusing on specific aspects for providing QoS guarantees to the end user. However, the integrated management of the end-to-end chain preserving QoS in heterogeneous environments is still a significant issue and insufficiently addressed to date. In this paper we propose an integrated management supervisor that takes into account the requirements from all stakeholders along the multimedia content delivery chain and provides an end-to-end management solution enabling QoS to the end user. This architecture and the subsystems that can be distributed along the end-to-end chain are detailed in this paper.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/eumob2008enthrone.pdf}, talktype = {none} } @InProceedings{Timmerer2008f, author = {Timmerer, Christian and Andrade, Maria Teresa and Carvalho, Pedro and Rogai, Davide and Cordara, Giovanni}, booktitle = {Proceedings of ACM Multimedia 2008 2nd International Workshop on the Many Faces of Multimedia Semantics}, title = {The Semantics of MPEG-21 Digital Items Revisited}, year = {2008}, address = {New York, USA}, editor = {Fotouhi, Farshad and Grosky, William I and Stanchev, Peter}, month = oct, pages = {17-23}, publisher = {ACM}, abstract = {The MPEG-21 standard forms a comprehensive multimedia framework covering the entire multimedia distribution chain. In particular, it provides a flexible approach to represent, process, and transact complex multimedia objects which are referred to as Digital Items (DIs). DIs can be quite generic, independent of the application domain, and can encompass a diversity of media resources and metadata. This flexibility has an impact on the level of interoperability between systems and applications, since not all the functionality needs to be implemented. Furthermore, additional semantic rules may be implemented through the processing of the Digital Item which is possibly driven by proprietary metadata. This jeopardizes interoperability and consequently raises barriers to the successful achievement of augmented and transparent use of multimedia resources. In this context, we have investigated and evaluated the interoperability at the semantic level of Digital Items throughout the automated production, delivery and consumption of complex multimedia resources in heterogeneous environments. This paper describes the studies conducted, the experiments performed, and the conclusions reached towards that goal.}, doi = {http://dx.doi.org/10.1145/1460676.1460681}, isbn13 = {978-1-60558-316-7}, keywords = {MPEG-21, Digital Items, Semantics, Evaluation, Metadata.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/ms41754-timmerer-pre.pdf}, talktype = {none} } @InProceedings{Szkaliczki2008, author = {Szkaliczki, Tibor and Karpati, Peter and Böszörmenyi, Laszlo}, booktitle = {Communication Systems and Networks 2008}, title = {Algorithms for Placement of Storage Components and Videos in Distributed Multimedia Servers}, year = {2008}, address = {Calgary, Canada}, editor = {Salvador, CP}, month = jun, pages = {43-48}, publisher = {ACTA Press}, abstract = {We plan to setup a VoD service built on an innovative multimedia server architecture which enables dynamic adaptation to the changing circumstances. The adaptation happens by replicating the server components and the stored videos based on real-time host and network monitoring and resource constraint analysis. In addition, the terminal capabilities and client preferences are considered. The paper focuses on the challenge of the optimal placement of storage components and the videos in the network. We compare three implemented optimisation algorithms (so called simple, incremental and complex incremental); the latter one can be calibrated against different preferences. We examine the effect of changing weights of the algorithm onto the recommendation.}, issn = {9780889867581}, language = {EN}, talktype = {none}, url = {http://www.iasted.org/conferences/pastinfo-629.html} } @InProceedings{Strohmaier2008a, author = {Strohmaier, Markus and Prettenhofer, Peter and Lux, Mathias}, booktitle = {Proceedings of the Workshop on Common Sense Knowledge and Goal-Oriented Interfaces}, title = {Different Degrees of Explicitness in Intentional Artifacts: Studying User Goals in a Large Search Query Log}, year = {2008}, address = {Aachen, Germany}, editor = {Gordon, Andrew and Havasi, Catherine and Lux, Mathias and Strohmaier, Markus}, month = jan, pages = {10}, publisher = {http://ceur-ws.org}, series = {CEUR Workshop Proceedings}, abstract = {On the web, search engines represent a primary instrument through which users exercise their intent. Understanding the specific goals users express in search queries could improve our theoretical knowledge about strategies for search goal formulation and search behavior, and could equip search engine providers with better descriptions of users’ information needs. However, the degree to which goals are explicitly expressed in search queries can be suspected to exhibit considerable variety, which poses a series of challenges for researchers and search engine providers. This paper introduces a novel perspective on analyzing user goals in search query logs by proposing to study different degrees of intentional explicitness. To explore the implications of this perspective, we studied two different degrees of explicitness of user goals in the AOL search query log containing more than 20 million queries. Our results suggest that different degrees of intentional explicitness represent an orthogonal dimension to existing search query categories and that understanding these different degrees is essential for effective search. The overall contribution of this paper is the elaboration of a set of theoretical arguments and empirical evidence that makes a strong case for further studies of different degrees of intentional explicitness in search query logs.}, language = {EN}, talktype = {none}, url = {http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-323/paper04.pdf} } @InProceedings{Strohmaier2008, author = {Strohmaier, Markus and Prettenhofer, Peter and Lux, Mathias}, booktitle = {Workshop on Common Sense Knowledge and Goal-Oriented Interfaces (CSKGOI 08)}, title = {Different Degrees of Explicitness in Intentional Artifacts}, year = {2008}, address = {Klagenfurt, Austria}, editor = {Gordon, Andrew and Havasi, Catherine and Lux, Mathias and Strohmaier, Markus}, month = jan, pages = {10}, publisher = {Klagenfurt University}, abstract = {On the web, search engines represent a primary instrument through which users exercise their intent. Understanding the specific goals users express in search queries could improve our theoretical knowledge about strategies for search goal formulation and search behavior, and could equip search engine providers with better descriptions of users’ information needs. However, the degree to which goals are explicitly expressed in search queries can be suspected to exhibit considerable variety, which poses a series of challenges for researchers and search engine providers. This paper introduces a novel perspective on analyzing user goals in search query logs by proposing to study different degrees of intentional explicitness. To explore the implications of this perspective, we studied two different degrees of explicitness of user goals in the AOL search query log containing more than 20 million queries. Our results suggest that different degrees of intentional explicitness represent an orthogonal dimension to existing search query categories and that understanding these different degrees is essential for effective search. The overall contribution of this paper is the elaboration of a set of theoretical arguments and empirical evidence that makes a strong case for further studies of different degrees of intentional explicitness in search query logs.}, language = {EN}, talktype = {none} } @InProceedings{Schoeffmann2008a, author = {Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 18th International Workshop on Network and Operating Systems Support for Digital Audio and Video}, title = {Fast and Flexible Video Content Browsing based on H.264/AVC Features}, year = {2008}, address = {New York, NY, USA}, editor = {Griwodz, Carsten and Wolf, Lars}, month = may, pages = {115-116}, publisher = {ACM Press}, abstract = {We present a video content browsing tool which is supposed to be used for two purposes: (1) efficiently searching a certain scene within a long video sequence and (2) quickly identifying videos out of interest. Instead of a complex user interface with many features we rather use a simple but flexible player-like interface which can, however, support the user on taking advantage of his/her knowledge about the content semantics. The content analysis is based on some simple features which can be extracted from compressed data of H264/AVC and, thus, allow very fast analysis. An early user study has shown encouraging results.}, doi = {10.1145/1496046.1496075}, isbn10 = {978-1-60558-157-6}, language = {EN}, talktype = {none}, url = {http://www.nossdav.org/2008/} } @InProceedings{Schoeffmann2008, author = {Schoeffmann, Klaus and Böszörmenyi, Laszlo}, booktitle = {Advances in Multimedia Modeling}, title = {Fast Segmentation of H.264/AVC Bitstreams for On-Demand Video Summarization}, year = {2008}, address = {Berlin, Heidelberg, New York}, editor = {Satoh, Shin’ichi and Nack, Frank and Etoh, Minoru}, month = jan, pages = {265-276}, publisher = {Springer}, series = {LNCS 4903}, abstract = {Video summarization methods need fast segmentation of a video into smaller units as a first step, especially if used in an on-demand fashion. We propose an efficient segmentation algorithm for H.264/AVC bitstreams that is able to segment a video in appr. 10% of the time required to decode the video. This is possible because our approach uses features available after entropy-decoding (which is the very first stage of the decoding process) only. More precisely, we use a combination of two features, especially appropriate to H.264/AVC, with different characteristics in order to decide if a new segment starts or not: (1) L1-Distance based partition histograms and (2) ratio of intra-coded macroblocks on a per-frame basis. Our results show that this approach performs well and works for several different encoders used in practice today.}, issn = {0302-9743}, language = {EN}, talktype = {none}, url = {http://www.springerlink.com/content/bv13746227j58713/} } @InProceedings{Ransburg2008a, author = {Ransburg, Michael and Gressl, Hubert and Hellwagner, Hermann}, booktitle = {2008 Ninth International Workshop on Image Analysis for Multimedia Interactive Services}, title = {Efficient Transformation of MPEG-21 Metadata for Codec-agnostic Adaptation in Real-time Streaming Scenarios}, year = {2008}, address = {Los Alamitos, CA, USA}, editor = {Hellwagner, Hermann and Timmerer, Christian}, month = apr, pages = {143-146}, publisher = {IEEE}, abstract = {Scalable media contents, such as the new MPEG-4 Scalable Video Codec enable to easily retrieve different qualities of the media content by simply disregarding certain media segments. The MPEG-21-based codec-agnostic adaptation approach supports this concept by introducing an XMLbased Bitstream Syntax Description (BSD) which describes the different segments of a media content. Based on this BSD, an adaptation node can intelligently adapt any scalable media (i.e., remove specific media segments) without the need for codec-specific knowledge. The adaptation approach consists of 1) transforming this BSD and 2) adapting the media based on the transformed BSD. In this paper, we focus on the BSD transformation step and evaluate different mechanisms w.r.t. their transformation efficiency given several application scenarios. In particular, we compare the traditional stylesheet-based mechanisms with a novel mechanism based on regular expressions. We discuss both mechanisms in terms of their expressiveness, and propose how to actually employ regular expressions for codec-agnostic adaptation. Finally, we quantitatively evaluate these mechanisms in different adaptation scenarios, which vary in the size and number of required BSD units}, isbn13 = {9780769531304}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Efficient Transformation of MPEG-21 Metadata for Codec-agnostic Adaptation.pdf}, talktype = {none}, url = {http://www2.computer.org/portal/web/csdl/abs/proceedings/wiamis/2008/3130/00/3130toc.htm} } @InProceedings{Ransburg2008, author = {Ransburg, Michael and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Multimedia Semantics: The role of Metadata}, title = {Dynamic and Distributed Multimedia Content Adaptation based on the MPEG-21 Multimedia Framework}, year = {2008}, address = {Berlin, Heidelberg, New York}, editor = {Lux, Mathias and Granitzer, Michael and Spaniol, Marc}, month = feb, pages = {3-24}, publisher = {Springer}, abstract = {Today, there are many technologies in place to establish an infrastructure for the delivery and consumption of multimedia content. In practice, however, several elements of such an infrastructure are often stand-alone systems and a big picture of how these elements relate to each other or even fit together is not available. Therefore, MPEG-21 aims to provide an open framework for interoperable multimedia delivery and consumption. This requirement for interoperability results in a great diversity of XML-based metadata, which describes the media data on semantic or syntactic levels, in order to make it more accessible to the user. This metadata can be of considerable size, which leads to problems in streaming scenarios. Other than media data, XML metadata has no concept of samples, thus inhibiting streamed (and timed) processing, which is natural for media data. In order to address the challenges and requirements resulting from this situation, the concept of streaming instructions is introduced. These streaming instructions facilitate the fragmentation of content-related metadata, the association of media and metadata fragments with each other, and the synchronized streaming and processing of those fragments. Based on these capabilities, a dynamic and distributed multimedia content adaptation framework can be built.}, doi = {10.1007/978-3-540-77473-0_1}, isbn10 = {3540774726}, isbn13 = {978-3540774723}, language = {EN}, talktype = {none} } @InProceedings{Quaritsch2008, author = {Quaritsch, Markus and Stojanovski, Emil and Bettstetter, Christian and Friedrich, Gerhard and Hellwagner, Hermann and Rinner, Bernhard and Hofbaur, Michael and Shah, Mubarak}, booktitle = {Proceedings of the Second International Conference on Autonomic Computing and Communication Systems}, title = {Collaborative Microdrones: Applications and Research Challenges}, year = {2008}, address = {New York, NY, USA}, editor = {ACM,}, month = jul, pages = {7}, publisher = {ACM Press}, abstract = {Microdrones are small-scale unmanned aerial vehicles (UAVs) carrying payloads such as cameras and sensors. Such microdrones enable us to obtain a bird's eye view of the environment which is helpful in many applications such as environmental monitoring, surveillance or disaster management. This position paper reports on our recently launched project \collaborative microdrones" where we are developing a system for aerial imaging based on cooperating, wireless networked microdrones that can be used in disaster management applications. Several microdrones will y in formation over the area of interest and deliver sensor data which is fused, analyzed and delivered to the user in real-time. In this paper we brie y discuss applications for UAVs, present related projects, introduce our research focus and report on preliminary results.}, keywords = {microdrones, networked autonomous systems, mission planning, aerial imaging, formation flight}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Collaborative Microdrones.pdf}, talktype = {none}, url = {http://www.pervasive.uni-klu.ac.at/publications/pdf/Quaritsch_Autonomics2008.pdf} } @InProceedings{Prangl2008a, author = {Prangl, Martin and Kofler, Ingo and Hellwagner, Hermann}, booktitle = {Proceedings of the 4th International Conference on Networking and Services (ICNS)}, title = {Towards QoS Improvements of TCP-based Media Delivery}, year = {2008}, address = {Los Alamitos, CA, USA}, editor = {Bi, Jun and Chin, Kim and Dini, Cosmin and Lehmann, Leo and Pheanis, David C}, month = mar, pages = {188-193}, publisher = {IEEE}, series = {ICNS}, abstract = {The amount of audiovisual data available on the Internet and thus of multimedia communication over today's networks is increasing at a rapid pace. Despite the availability of specific media transport protocols like RTP, most content providers make use of the well-established and reliable TCP protocol to deliver audiovisual content over the Internet. The reason is that TCP-based data delivery in general is much less complicated for the clients to be served and over today's networks traversed (including proxies and firewalls), than making use of UDP-based RTP connections. However, in case of network bandwidth fluctuations and packet losses, TCP-based media delivery may lead to annoying jerky playback at the client side, due to retransmissions and late arrival of media data. This papers deals with TCP-based perceptual QoS improvement mechanisms for increasing the media experience for the consumer under unstable network conditions. Our approach is based on media content adaptation (transcoding) to fit the actual network bandwidth continuously monitored by the sender. The proposed mechanisms are applied at the application level at the server side, leaving the existing TCP implementation untouched and therefore enabling transparent use of existing media players. An evaluation of a realistic use case is presented which underlines the efficency of our approach.}, doi = {10.1109/ICNS.2008.10}, isbn13 = {978-0-7695-3094-9}, language = {EN}, location = {Gosier, Guadaloupe}, pdf = {https://www.itec.aau.at/bib/files/prangl-tQosTcpMediaDelivery.pdf}, talkdate = {2008.03.19}, talktype = {registered} } @InProceedings{Prangl2008, author = {Prangl, Martin and Kofler, Ingo and Hellwagner, Hermann}, booktitle = {Proceedings of the 1st International Conference on Ambient Media and Systems (Ambi-sys)}, title = {An MPEG-21-driven Utility-based Multimedia Adaptation Decision Taking Web Service}, year = {2008}, address = {Brussels, Belgium}, editor = {Whitaker, Roger M and Liang, Ben}, month = feb, pages = {8}, publisher = {ICST}, series = {Ambi-sys}, abstract = {Supporting transparent delivery and convenient use of multimedia content across a wide range of networks and devices is still a challenging task within the multimedia research community; Universal Multimedia Access (UMA) is a vision that has been pursued for quite some time. In multimedia frameworks, content adaptation is the core concept to make progress toward this goal. Most media adaptation engines targeting UMA scale the content w.r.t. terminal capabilities and network resource constraints and do not sufficiently consider end user preferences or even the utility of the adapted content for the user. Based on our previous work and the support of the MPEG-21 framework, we present a transparent solution to provide a content utility-aware adaptation decision for such utility-unaware multimedia frameworks. The idea is to outsource the challenging utility-aware adaptation decision taking task, which takes many factors into consideration and leads to a complex optimization problem. A realistic use case is adopted to show how related external multimedia frameworks can easily integrate and use our proposed adaptation decision taking Web Service.}, isbn13 = {978-963-9799-16-5}, language = {EN}, location = {Quebec, Canada}, pdf = {https://www.itec.aau.at/bib/files/ADTService-final.pdf}, talkdate = {2008.02.12}, talktype = {registered} } @InProceedings{Marques2008, author = {Marques, Oge and Lux, Mathias}, booktitle = {Proceeding of the 2nd ACM workshop on Multimedia semantics}, title = {An exploratory study on joint analysis of visual classification in narrow domains and the discriminative power of tags}, year = {2008}, address = {New York, NY, USA}, editor = {Fotouhi, Farshad and Grosky, William and Stanchev, Peter}, month = nov, pages = {40-47}, publisher = {ACM Press}, language = {EN}, talktype = {none}, url = {http://portal.acm.org/citation.cfm?doid=1460676.1460685} } @InProceedings{Mackay2008, author = {Mackay, Michael and Hutchison, David and Ransburg, Michael and Hellwagner, Hermann}, booktitle = {2008 Ninth International Workshop on Image Analysis for Multimedia Interactive Services}, title = {Combined Adaptation and Caching of MPEG-4 SVC in Streaming Scenarios}, year = {2008}, address = {Los Alamitos, CA, USA}, editor = {Hellwagner, Hermann and Timmerer, Christian}, month = apr, pages = {101-104}, publisher = {IEEE}, abstract = {A key objective of the ENTHRONE II Project is the ability to optimise the delivery of multimedia content to a wide group of heterogeneous users. One example of this is in the cooperative deployment of adaptation and caching functionality in the edge network. This hybrid approach makes it possible not only to store content locally, thus minimising the cost incurred through subsequent requests, but also to better serve heterogeneous groups of users by dynamically adapting the content to suit a wide range of terminal devices. In this paper, we describe and evaluate how the cooperative deployment of MPEG-21-based adaptation and caching of MPEG-4 SVC can result in improvements both in the quality of the content received at the user terminal and the resources consumed during the delivery}, isbn13 = {9780769531304}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Combined Adaptation and Caching of MPEG-4 SVC in Streaming Scenarios.pdf}, talktype = {none}, url = {http://www2.computer.org/portal/web/csdl/abs/proceedings/wiamis/2008/3130/00/3130toc.htm} } @InProceedings{Lux2008d, author = {Lux, Mathias and Granitzer, Gisela and Beham, Günter}, booktitle = {Multimedia Semantics. The Role of Metadata}, title = {User-Centered Multimedia Retrieval Evaluation based on Empirical Research}, year = {2008}, address = {Berlin, Heidelberg, New York}, editor = {Lux, Mathias and Spaniol, Marc}, month = dec, pages = {175-194}, publisher = {Springer}, series = {Studies in Computational Intelligence}, issn = {9783540774723}, language = {EN}, talktype = {none}, url = {http://www.springer.com/engineering/book/978-3-540-77472-3} } @InProceedings{Lux2008c, author = {Lux, Mathias and Marques, Oge and Pitman, Arthur}, booktitle = {Proceedings of the I-KNOW´08 and I-MEDIA´08}, title = {Using Visual Features to Improve Tag Suggesions in Image Sharing Sites}, year = {2008}, address = {Graz, Austria}, editor = {Tochtermann, Klaus and Maurer, Hermann}, month = aug, pages = {425-429}, publisher = {TU Graz \& Know Center}, issn = {0948695x}, language = {EN}, talktype = {none}, url = {http://www.jucs.org} } @InProceedings{Lux2008b, author = {Lux, Mathias}, booktitle = {2008 Ninth International Workshop on Image Analysis for Multimedia Interactive Services}, title = {Revisiting the Vector Retrieval Model in Context of the MPEG-7 Semantic Description Scheme}, year = {2008}, address = {Los Alamitos, CA, USA}, editor = {Hellwagner, Hermann and Timmerer, Christian}, month = apr, pages = {134-138}, publisher = {IEEE}, isbn10 = {978-0-7695-3130-4}, language = {EN}, talktype = {none}, url = {http://www2.computer.org/portal/web/csdl/abs/proceedings/wiamis/2008/3130/00/3130toc.htm} } @InProceedings{Lux2008a, author = {Lux, Mathias and Russ, Christian}, booktitle = {Information Systems and e-Business Technologies, 2nd International United Information Systems Conference}, title = {A Model of Self-Organized Criticality in Emergent Web Systems}, year = {2008}, address = {Berlin, Heidelberg, New York}, editor = {Kaschek, Roland and Kop, Christian and Steinberger, Claudia and Fliedl, Günther}, month = apr, pages = {496-507}, publisher = {Springer}, series = {Lecture Notes in Business Information Processing}, abstract = {Self-organized criticality (SOC) is a measure to identify if complex systems have the potential to build out emergent behavior. This phenomenon is known in many different areas of physics, biology, ecology, economy and social systems. Its core assertion is that an over critical energy input can lead to spontaneous, self-enforcing and unpredictable self-organization. In such a process new structures and orders emerge. “Online Crowds” are masses of internet users who behave and act collectively on the web. They tend to follow specific online trends and can generate tremendous online traffic and attention (cp. Social software like YouTube.com, MySpace.com, Friendster.com, etc.). “Online Crowds” are observed rarely, are hard to predict and even harder to generate artificially. So it is essential for online business ideas to foster and facilitate these “Online Crowds” to reach a critical mass of online users to grow continuously and to produce profit. The paper in hand introduces the “Online Crowds” model (OCM) in context of web information systems employing the concepts of self organization theory and self organization criticality. Furthermore a statistical approach for detection of indicators of self organized criticality is presented along with experiments and preliminary results showing the applicability of the approach.}, issn = {9783540789413}, language = {EN}, talktype = {none}, url = {http://www.springerlink.com/content/m6133627426456v6/} } @InProceedings{Lopez2008, author = {López, Fernando and Jannach, Dietmar and Martínez, José M and Timmerer, Christian and Hellwagner, Hermann and García, Narciso}, booktitle = {2008 Ninth International Workshop on Image Analysis for Multimedia Interactive Services}, title = {Multimedia Adaptation Decisions Modelled as Non-deterministic Operations}, year = {2008}, address = {Los Alamitos, CA, USA}, editor = {Hellwagner, Hermann and Timmerer, Christian}, month = apr, pages = {46-49}, publisher = {IEEE}, abstract = {This paper describes how a multimedia adaptation framework can automatically decide the sequence of operations to be executed in order to adapt an MPEG-21 Digital Item to the MPEG-21 description of the usage environment in which it will be consumed. The main innovation of this work with respect to previous multimedia adaptation decision models is that in the proposed approach decisions can be made without knowing the exact behaviour of the operations that are going to be executed.}, isbn13 = {9780769531304}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Multimedia Adaptation Decisions Modelled as Non-Deterministic Operations.pdf}, talktype = {none}, url = {http://www2.computer.org/portal/web/csdl/abs/proceedings/wiamis/2008/3130/00/3130toc.htm} } @InProceedings{Lachner2008, author = {Lachner, Janine and Hellwagner, Hermann}, booktitle = {Information Systems and e-Business Technologies (Proc. 2nd International United Information Systems Conference, UNISCON 2008}, title = {Information and Communication Systems for Mobile Emergency Response}, year = {2008}, address = {Berlin, Heidelberg, New York}, editor = {Kaschek, Roland and Kop, Christian and Steinberger, Claudia and Fliedl, Günther}, month = apr, pages = {213-224}, publisher = {Springer}, series = {LNBIP 5}, abstract = {This discussion paper attempts to propose emergency response and disaster management as worthwhile areas of applied research for the informa-tion system community. The typical requirements, entities and activities in-volved in specifically mobile emergency response operations are summarized. Recent research contributions in this area are exemplarily reviewed in order to give a deeper insight into the role and use of mobile information and communi-cation systems. Finally, the major challenges and research needs regarding in-formation systems are summarized, with a view to draw the attention of infor-mation systems researchers to this interesting and important field.}, edition = {1}, isbn10 = {3540789413}, isbn13 = {978-3540789413}, keywords = {Emergency response, disaster management, information systems, mobile information and communication technology}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Information and Communication Systems for Mobile Emergency Response.pdf}, talktype = {none} } @InProceedings{Kofler2008, author = {Kofler, Ingo and Prangl, Martin and Kuschnig, Robert and Hellwagner, Hermann}, booktitle = {Proceedings of the 18th International Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV)}, title = {An H.264/SVC-based Adaptation Proxy on a WiFi Router}, year = {2008}, address = {New York, NY, USA}, editor = {Wolf, Lars and Griwodz, Carsten}, month = may, pages = {63-68}, publisher = {ACM}, series = {NOSSDAV}, abstract = {Recent advances in video coding technology like the scalable extension of the MPEG-4 AVC/H.264 video coding standard pave the way for computationally cheap adaptation of video content. In this paper we present our work on a lightweight RTSP/RTP proxy that enables in-network stream processing. Based on an off-the-shelf wireless router that runs a Linux-based firmware we demonstrate that the video adaptation can be performed on-the-fly directly on a network device. The paper covers design and implementation details of the proxy as well as a discussion about the actual adaptation of the SVC stream. Based on experimental evaluations we show that our approach can handle a reasonable number of concurrent sessions for a typical home deployment scenario. Furthermore, the paper covers possible applications in which adaptation on the network device can be beneficial.}, doi = {10.1145/1496046.1496061}, keywords = {Multimedia adaptation, in-network adaptation, RTSP, RTP, H.264, scalable video coding}, language = {EN}, location = {Braunschweig, Germany}, pdf = {https://www.itec.aau.at/bib/files/NOSSDAV08_AdaptationProxyRouter-preprint.pdf}, talkdate = {2009.05.29}, talktype = {registered} } @InProceedings{Koepke2008, author = {Köpke, Julius and Tusch, Roland and Hellwagner, Hermann and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the International Conference on Signal Processing and Multimedia Applications}, title = {Context-aware hoarding of Multimedia Content in a large-scale Tour Guide Scenario}, year = {2008}, address = {Setubal}, editor = {Assunção, Pedro and Faria, Sérgio}, month = jul, pages = {15-23}, publisher = {INSTICC Press}, issn = {9789898111609}, language = {EN}, talktype = {none}, url = {http://www.sigmap.org} } @InProceedings{Karpati2008a, author = {Karpati, Peter and Szkaliczki, Tibor and Böszörmenyi, Laszlo}, booktitle = {13th International Telecommunications Network Strategy and Planning Symposium}, title = {Modeling and Simulation of the Performance of Distributed Video Services}, year = {2008}, address = {Los Alamitos, CA, USA}, editor = {Sallai, G}, month = sep, pages = {10}, publisher = {IEEE}, issn = {9789638111685}, language = {EN}, talktype = {none}, url = {http://www.networks2008.org} } @InProceedings{Karpati2008, author = {Karpati, Peter and Szkaliczki, Tibor and Böszörmenyi, Laszlo}, booktitle = {Internet and Multimedia Systems and Applications 2008}, title = {Comparing Static and Self-Organizing Behaviours for VoD Servers}, year = {2008}, address = {Calgary, Canada}, editor = {Mandal, M}, month = mar, pages = {44-49}, publisher = {ACTA Press}, issn = {9780889867512}, language = {EN}, talktype = {none}, url = {http://www.actapress.com/Abstract.aspx?paperId=33806} } @InProceedings{Hellwagner2008, author = {Hellwagner, Hermann}, booktitle = {Advances in Multiagent Systems, Robotics and Cybernetics: Theory and Practice (Volume II)}, title = {Challenges toward Adaptive Behavior of Distributed Multimedia Systems}, year = {2008}, address = {Tecumseh}, editor = {Lasker, George E and Pfalzgraf, Jochen}, month = jul, pages = {15-19}, publisher = {The International Institute for Advanced Studies in Systems Research and Cybernetics}, series = {Proceedings of the Symposium on Multiagent Systems, Robotocs and Cybernetics Inter-Symp-2007}, abstract = {The multimedia community is pursuing, among others, the vision of Universal Multimedia Access (UMA). UMA denotes the concept that any multimedia content should be available anywhere, anytime, on any device, tailored to the user's needs and preferences, accessible for the user in a transparent and convenient way. Key to achieving this vision is to realize collaborative adaptive behavior of the involved distributed multi-media system components (server, media-aware net-work elements like proxies or gateways, and clients), based on intense metadata exchange and multimedia content negotiation, adaptation, or personalization. This paper outlines the key challenges and the state of the art in achieving such adaptive behavior. The major challenges have been tackled recently and many of the building blocks of UMA have become or are becoming available from standardization groups, which are instrumental in this area to ensure interop-erable use of the media and metadata items. However, making use of these standards in practical multimedia systems raises additional issues, both of conceptual nature and in terms of implementation. Based on years of contributions to ISO/IEC MPEG standardization efforts and of research work into adaptive multimedia systems, we will give an overview of these challenges, discuss the state of the art, and introduce an emerging principled solution for format-independent multimedia content adaptation.}, edition = {Vol. II}, isbn13 = {9781897233610}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/InterSymp_2007_HH_Adaptive_Behavior_DMS.pdf}, talktype = {none} } @InProceedings{Eberhard2008c, author = {Eberhard, Michael and Celetto, Luca and Timmerer, Christian and Quacchio, Emanuele and Hellwagner, Hermann}, booktitle = {STreaming Day'08 Proceedings}, title = {An Interoperable Streaming Framework for Scalable Video Coding based on MPEG-21}, year = {2008}, address = {Parma}, editor = {Fanucci, Luca and Rovati, Fabrizio and Timmerer, Christian}, month = {sep}, pages = {4}, publisher = {University of Parma}, abstract = {In this paper, an interoperable streaming framework for the adaptation and streaming of scalable multimedia content is presented. The streaming framework’s architecture for Video on Demand (VoD) as well as multicast streaming is presented. The VoD test-bed allows each client to set up a separate streaming session and receive the bitstreams in a quality tailored to the clients requirements, while the multicast test-bed provides a layered scalable multicast to all clients and every client needs to decide which layers to subscribe to. After the description of the architectures, a comparison in terms of performance of the MPEG-21 DIA metadata-based adaptation approach to an SVC-specific adaptation approach is presented. Furthermore, optimizations for both adaptation approaches are presented and the performance improvements due to the optimizations are discussed.}, issn = {9781607029373}, language = {EN}, location = {Parma, Italy}, pdf = {https://www.itec.aau.at/bib/files/Streaming Day'08_Eberhard_StreamingFramework_Paper.pdf}, talkdate = {2008.09.02}, talktype = {registered} } @InProceedings{Eberhard2008b, author = {Eberhard, Michael and Celetto, Luca and Timmerer, Christian and Quacchio, Emanuele and Hellwagner, Hermann and Rovati, Fabrizio S}, booktitle = {Proceedings of the 5th IET Visual Information Engineering Conference Conference (VIE’08)}, title = {An Interoperable Streaming Framework for Scalable Video Coding based on MPEG-21}, year = {2008}, address = {London}, editor = {Izquierdo, Ebroul and Liu, Guizhong}, month = {jul}, pages = {723-728}, publisher = {IET}, abstract = {This paper presents an interoperable framework for the streaming of scalable multimedia content such as Scalable Video Coding (SVC). In particular, the framework’s architecture for both, Video on Demand (VoD) and multicast streaming, is presented. The architecture includes a detailed description of the adaptation engine – conforming to MPEG-21 Digital Item Adaptation – as well as the integration of the adaptation engine into VideoLAN’s VLC media player, which provides the streaming server and client for the framework. Following the description of the architecture, a comparison in terms of performance of the generic MPEG-21 DIA-based adaptation approach, which is utilized by the described demo, versus an SVC-specific adaptation approach is presented and possible further improvements for both approaches are investigated.}, isbn13 = {978-0-86341-914-0}, issn = {0537-9989}, keywords = {Adaptation, MPEG-21 Digital Item Adaptation, Multicasting, Scalable Video Coding, Video on Demand}, language = {EN}, location = {Xi'an, China}, pdf = {https://www.itec.aau.at/bib/files/VIE08_Eberhard.pdf}, talkdate = {2008.07.29}, talktype = {registered} } @InProceedings{Eberhard2008a, author = {Eberhard, Michael and Celetto, Luca and Timmerer, Christian and Quacchio, Emanuele and Hellwagner, Hermann and Rovati, Fabrizio S}, booktitle = {Proceedings of the IEEE International Conference on Multimedia and Expo 2008 (ICME’08)}, title = {An Interoperable Multimedia Delivery Framework for Scalable Video Coding based on MPEG-21 Digital Item Adaptation}, year = {2008}, address = {Los Alamitos, CA, USA}, editor = {Ostermann, Jörn and Ebrahimi, Touradj}, month = {jun}, pages = {1607-1608}, publisher = {IEEE}, abstract = {In this paper we present an interoperable multimedia delivery framework for scalable video coding based on MPEG-21 Digital Item Adaptation (DIA). In can be used to transmit scalable video contents within heterogeneous usage environments where the properties of the usage environment (e.g., terminal/network capabilities) may change dynamically during the streaming session. The usage environment is signaled by interoperable description formats provided by the DIA standard. Additionally, the adaptation itself is done by exploiting the standard's generic adaptation approach, i.e., independent of the actual coding format. Thus, the overall framework is also applicable for other scalable coding formats.}, issn = {9781424425709}, language = {EN}, location = {Hannover, Germany}, pdf = {https://www.itec.aau.at/bib/files/ICME08_Eberhard.pdf}, talkdate = {2008.06.25}, talktype = {poster} } @InProceedings{Eberhard2008, author = {Eberhard, Michael and Celetto, Luca and Timmerer, Christian and Quacchio, Emanuele and Hellwagner, Hermann}, booktitle = {2008 Ninth International Workshop on Image Analysis for Multimedia Interactive Services}, title = {Performance Analysis of Scalable Video Adaptation: Generic versus Specific Approach}, year = {2008}, address = {Los Alamitos, CA, USA}, editor = {Hellwagner, Hermann and Timmerer, Christian}, month = {may}, pages = {43-50}, publisher = {IEEE}, abstract = {This paper provides a performance analysis of adaptation approaches designed for scalable media resources. In particular, we investigate the streaming of media resources compliant to the Scalable Video Coding (SVC) extensions of Advanced Video Coding (AVC)within heterogeneous environments, i.e., terminals and networks with different capabilities. Therefore, we have developed a test-bed in order to analyze two different approaches for the adaptation of scalable media resources, namely a generic approach that is applicable independently of the actual scalable coding format used and a specific approach especially built for SVC.The results show that if adaptation is required the generic approach clearly outperforms the approach specifically built for SVC}, isbn10 = {076953130X}, isbn13 = {978-0769531304}, language = {EN}, location = {Klagenfurt, Austria}, pdf = {https://www.itec.aau.at/bib/files/wiamis08_eberhard.pdf}, talkdate = {2008.05.09}, talktype = {registered} } @InProceedings{Bolla2008, author = {Bolla, Raffaele and Repetto, Matteo and Chessa, Stefano and Furfari, Francecso and Zutter, Saar De and Walle, Rik Van de and Reiterer, Bernhard and Hellwagner, Hermann and Asbach, Mark and Wien, Mathias}, booktitle = {13th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA08)}, title = {A Context-Aware Architecture for QoS and Transcoding Management of Multimedia Streams in Smart Homes}, year = {2008}, address = {Los Alamitos, CA, USA}, editor = {IEEE, Industrial Electronics Society}, month = sep, pages = {1354-1361}, publisher = {IEEE}, abstract = {Current trends in smart homes suggest that several multimedia services will soon converge towards common standards and platforms. However this rapid evolution gives rise to several issues related to the management of a large number of multimedia streams in the home communication infrastructure. An issue of particular relevance is how a context acquisition system can be used to support the management of such a large number of streams with respect to the Quality of Service (QoS), to their adaptation to the available bandwidth or to the capacity of the involved devices, and to their migration and adaptation driven by the users' needs that are implicitly or explicitly notified to the system. Under this scenario this paper describes the experience of the INTERMEDIA project in the exploitation of context information to support QoS, migration, and adaptation of multimedia streams.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/04638575.pdf}, talktype = {none} } @InProceedings{Boeszoermenyi2008b, author = {Böszörmenyi, Laszlo}, booktitle = {Styles of Thinking in Science and Technology}, title = {Styles of thinking in informatics and how dogmatic is our science?}, year = {2008}, address = {Vienna, Austria}, editor = {Hunger, Hermann and Seebacher, Felicitas and Holzer, Gerhard}, month = sep, pages = {412-416}, publisher = {Verlag der Österreichischen Akademie der Wissenschaften}, issn = {9783700168461}, language = {EN}, talktype = {none} } @InProceedings{Boeszoermenyi2008, author = {Böszörmenyi, Laszlo}, booktitle = {Information Systems and e-Business Technologies}, title = {Public Adoption of Digital Multimedia- Why Is It Lagging behind Expectations?}, year = {2008}, address = {Berlin, Heidelberg, New York}, editor = {Kaschek, Rudolf and Kop, Christian and Steinberger, Claudia and Fliedl, Gerhard}, month = apr, pages = {52-58}, publisher = {Springer}, series = {LNBIP}, abstract = {The talk will address a number of problematic issues in current multimedia technology and try to give some positive answers. The term multimedia is used for a mixture of modalities, at least one of them being continuous. In the center of interest are “natural” videos, taken by cameras.}, issn = {18651348}, language = {EN}, location = {Klagenfurt, Austria}, talkdate = {2008.04.24}, talktype = {registered}, url = {http://www.uniscon.org} } @InProceedings{VanDeursen2007, author = {Deursen, Davy Van and Bruyne, Sarah De and Lancker, Wim Van and Neve, Wesley De and Schrijver, Davy De and Hellwagner, Hermann and Walle, Rik Van de}, booktitle = {IEEE International Symposium on Multimedia 2007 (ISM2007)}, title = {MuMiVA: A Multimedia Delivery Platform using Format-agnostic, XML-driven Content Adaptation}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {Bulterman, Dick and Mori, Kinji and Tsai, Jeffrey J P}, month = dec, pages = {131-138}, publisher = {IEEE}, abstract = {Due to the increasing heterogeneity in the current multimedia landscape, the delivery of multimedia content has become an important issue today. This heterogeneity is not only reflected by a plethora of different usage environments, but also by the presence of multiple (scalable) coding formats. Therefore, format-independent adaptation engines have to be used within a multimedia delivery platform, which are able to adapt the multimedia content according to a certain usage environment, independent of the underlying coding format of the content. By relying on automatically created textual descriptions of the highlevel syntax of binary media resources, a format-independent adaptation engine can be build. MPEG-21 generic Bitstream Syntax Schema (gBS Schema) is a tool that is part of the MPEG-21 Multimedia Framework. It enables the use of generic Bitstream Syntax Descriptions (gBSDs), i.e., textual descriptions in XML, to steer the adaptation of a binary media resource, using format-independent adaptation logic. In this paper, we address the design and performance evaluation of a multimedia delivery platform that relies on gBS Schema-driven adaptation engines. This platform is called MuMiVA; it is a fully integrated, extensible platform for multimedia delivery in heterogeneous usage environments, using streaming technologies. To demonstrate the flexibility of our multimedia delivery platform, we discuss the functioning of two different applications (i.e., exploitation of temporal scalability and shot selection) applied to two different coding formats (i.e., MPEG-4 Visual and H.264/AVC). Keywords— Content adaptation, Content delivery, MPEG-21 gBS Schema, XML transformations.}, isbn10 = {0769530583}, isbn13 = {978-0769530581}, keywords = {0769530583}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/MuMiVA.pdf}, talktype = {none}, url = {http://www.ism2007.ncu.edu.tw/} } @InProceedings{Szkaliczki2007, author = {Szkaliczki, Tibor and Karpati, Peter and Goldschmidt, Balazs}, booktitle = {Proceedings of the 5th Hungarian-Japanese Symposium on Discrete Mathematics and Its Applications}, title = {Two combinatorial optimisation problems in multimedia systems}, year = {2007}, address = {NA}, editor = {Tokuyama, T and Nishizeki, T and Recski, A and Shioura, A}, month = apr, pages = {211-218}, publisher = {NA}, language = {EN}, talktype = {none} } @InProceedings{Strohmaier2007, author = {Strohmaier, Markus and Lux, Mathias and Granitzer, Michael and Scheir, P and Liaskos, S and Yu, E}, booktitle = {WISE'07 Proceedings of the 2007 international conference on Web information systems engineering}, title = {How Do Users Express Goals on the Web? - An Exploration of Intentional Structures in Web Search}, year = {2007}, address = {Berlin, Heidelberg, New York}, editor = {Weske, M and Hacid, MS and Godart, C}, month = nov, pages = {67-78}, publisher = {Springer}, series = {LNCS 4832}, abstract = {Many activities on the web are driven by high-level goals of users, such as “plan a trip” or “buy some product”. In this paper, we are interested in exploring the role and structure of users’ goals in web search. We want to gain insights into how users express goals, and how their goals can be represented in a semi-formal way. This paper presents results from an exploratory study that focused on analyzing selected search sessions from a search engine log. In a detailed example, we demonstrate how goal-oriented search can be represented and understood as a traversal of goal graphs. Finally, we provide some ideas on how to construct large-scale goal graphs in a semi-algorithmic, collaborative way. We conclude with a description of a series of challenges that we consider to be important for future research.}, issn = {0302-974}, language = {EN}, talktype = {none}, url = {http://www.springerlink.com/content/w4067u12nu7375r4/?p=61bfd2d5edf24a6bbccfd9434ff4224f&pi=7} } @InProceedings{Spielvogel2007b, author = {Spielvogel, Christian and Böszörmenyi, Laszlo}, booktitle = {Second Interantional Workshop on Semantic Media Adaptation and Personalization}, title = {Quality-of-Service Based Video Replication}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {Mylonas, P and Wallace, M and Angelides, M}, month = dec, pages = {21-26}, publisher = {IEEE}, abstract = {An approach for quality-of-service based replica management in a proxy-to-proxy network is presented. Management decisions are based on a metrics called replication affinity. Replication affinity combines two other affinity metrics we call (1) placement affinity and (2) reallocation affinity. Placement affinity is used to find the best location to enable QoS based media delivery to future clients. Reallocation affinity is used to make media stream replacement decisions in case of insufficient storage space. Using our approach content replacements can be varied in the granularity. Granularity variations are possible for compressed videos by using multiple description coding (MDC). The effect of using replication affinity is evaluated by emulation experiments. For the experiments the network simulator NS-2 has been used.}, doi = {10.1109/SMAP.2007.17}, issn = {0-7695-3040-0}, language = {EN}, location = {Luxemburg}, talkdate = {2007.12.18}, talktype = {registered}, url = {http://ieeexplore.ieee.org/xpl/tocresult.jsp?sortType%3Dasc_p_Sequence%26filter%3DAND%28p_IS_Number%3A4414370%29&refinements=4293320131&pageNumber=1&resultAction=REFINE} } @InProceedings{Spielvogel2007, author = {Spielvogel, Christian and Böszörmenyi, Laszlo}, booktitle = {Parallel and Distributed Computing and Networks (PDCN 2007)}, title = {Active and Passive Replication of Multimedia Content in a ProXy-to-ProXy Network (X2X)}, year = {2007}, address = {Calgary, Canada}, editor = {Burkhart, H}, month = feb, pages = {303-308}, publisher = {ACTA Press}, abstract = {Active and passive replication are powerful techniques to improve the quality of multimedia streaming. Most systems follow either the active or the passive approach. A well known example for active replication are Content Distribution Networks [8] that replicate data to predefined static locations. In contrast to that, P2P file sharing networks [2, 1] use passive replication where identical content is usually provided by different peers. We suggest a system that combines both techniques using Proxy Affinity, Request Affinity and Replication Affinity considering user preferences, user behaviour, hardware resources and networks capabilities.}, issn = {978-0-88986-6}, language = {EN}, talktype = {none} } @InProceedings{Spaniol2007, author = {Spaniol, Marc and Klamma, Ralf and Lux, Mathias}, booktitle = {Proceedings of I-Media ´07 and I-Semantics ´07}, title = {Imagesemantics: User-Generated Metadata, Content Based Retrieval \& Beyond}, year = {2007}, address = {Graz, Austria}, editor = {Tochtermann, Klaus and Haas, Werner and Kappe, F and Scharl, A}, month = sep, pages = {41-48}, publisher = {TU Graz \& Know Center}, abstract = {With the advent of Web 2.0 technologies a new attitude towards processing contents in the Internet has emerged. Nowadays it is a lot easier to create, share and retrieve multimedia contents on the Web. However, with the increasing amount in contents retrieval becomes more challenging and often leads to inadequate search results. One main reason is that image clustering and retrieval approaches usually stick either solely to the images' low-level features or their user-generated tags (high-level features). However, this is frequently inappropriate since the "real" semantics of an image can only be derived from the combination of low-level and high-level features. Consequently, we investigated a more holistic view on image semantics based on a system called Imagesemantics. This system combines MPEG-7 descriptions for low-level content-based retrieval features and MPEG-7 keywords by a machine learning approach producing joined OWL rules. The rule base is used in Imagesemantics to improve retrieval results.}, doi = {10.3217/jucs-014-10-1792}, edition = {Volume 14, Issue 10}, issn = {0948-695x}, keywords = {MPEG-7, Web 2.0, social media platform, user-generated content}, language = {EN}, talktype = {none}, url = {http://www.jucs.org/jucs_14_10} } @InProceedings{Schoeffmann2007b, author = {Schoeffmann, Klaus}, booktitle = {Second Interantional Workshop on Semantic Media Adaptation and Personalization}, title = {Towards Interactive Video Browsing}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {Mylonas, Phivos and Wallace, Manolis and Angelides,Marios}, month = dec, pages = {237-240}, publisher = {IEEE}, issn = {0-7695-3040-0}, language = {EN}, talktype = {none}, url = {http://www.smap2007.org} } @InProceedings{Schoeffmann2007a, author = {Schoeffmann, Klaus and Fauster, Markus and Lampl, Oliver and Böszörmenyi, Laszlo}, booktitle = {Euro-Par 2007 Parallel Processing}, title = {An Evaluation of Parallelization Concepts for Baseline-Profile Compliant H.264/AVC Decoders}, year = {2007}, address = {Berlin, Heidelberg, New York}, editor = {Kermarrec, Anne-Marie and Bougé, Luc and Priol, Thierry}, month = aug, pages = {782-791}, publisher = {Springer}, series = {LNCS 4641}, abstract = {Due to the increasing performance requirements of decoding H.264/AVC in HDTV or larger resolutions, new approaches are necessary to enable real-time processing. According to the current trend to parallel computation in all performance classes, decoding of AVC must be mapped to these architectures even though this is complicated by the increased complexity and many data dependencies in the codec. We propose and evaluate different ways of using multithreading to speed-up our .NET implemented decoder. While slice based approaches scale best, this is not a flexible approach because of the reliance on specially encoded streams. Functional partitioning and macroblock pipelining prove to be a good alternative for almost all evaluated videos.}, issn = {0302-9743}, language = {EN}, location = {Rennes, France}, talkdate = {2007.08.30}, talktype = {registered}, url = {http://www.springerlink.com/content/q14w6788rp777r63/} } @InProceedings{Ransburg2007a, author = {Ransburg, Michael and Timmerer, Christian and Hellwagner, Hermann and Devillers, Sylvain}, booktitle = {WIAMIS 2007}, title = {Design and Evaluation of a Metadata-Driven Adaptation Node}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {Kompatsiaris, Yiannis and Avrithis, Yannis}, month = jun, pages = {4}, publisher = {IEEE}, abstract = {MPEG-21 Digital Item Adaptation (DIA) allows for a media codec agnostic multimedia adaptation approach which enables the implementation of generic adaptation engines. However, DIA is optimized for static, server-based adaptation. In this paper we introduce novel mechanisms to extend the DIA approach towards dynamic and distributed scenarios. This facilitates the placement of generic adaptation nodes which perform media codec agnostic and dynamic adaptation anywhere along the content delivery path. To validate our work we implemented such an adaptation node and evaluate its performance.}, issn = {0-7695-2818-X}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Design and Evaluation of a Metadata-Driven Adaptation Node.pdf}, talktype = {none}, url = {http://www.computer.org/proceedings/} } @InProceedings{Ransburg2007, author = {Ransburg, Michael and Devillers, Sylvain and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Datenbanksysteme in Business, Technologie und Web (BTW 2007)}, title = {Processing and Delivery of Multimedia Metadata for Multimedia Content Streaming}, year = {2007}, address = {Aachen}, editor = {Jarke, Matthias and Seidl, Thomas and Quix, Christoph and Kensche, David and Conrad, St and Rahm, E and Klamma, Ralf and Kosch, Harald and Granitzer, Michael and Apel, S and Rosenmüller, M and Saake, Gunter and Spinczyk, Olaf}, month = mar, pages = {117-138}, publisher = {Verlag Mainz}, abstract = {Today’s increasing variety of media data results in a great diversity of XMLbased metadata, which describes the media data on semantic or syntactic levels, in order to make it more accessible to the user. This metadata can be of considerable size, which leads to problems in streaming scenarios. Other than media data, XML metadata has no concept of “samples”, thus inhibiting streamed (and timed) processing, which is natural for media data. In order to address the challenges and requirements resulting from this situation, the concept of streaming instructions is introduced. In particular, streaming instructions address the problem of fragmenting metadata, associating media segments and metadata fragments, and streaming and processing them in a synchronized manner. This is achieved by enriching the metadata with additional attributes to describe media and XML properties. Alternatively, a style sheet approach provides the opportunity to dynamically set such streaming properties without actually modifying the XML description.}, issn = {3861309297}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Processing and Delivery of Multimedia Metadata for Multimedia Content Streaming.pdf}, talktype = {none} } @InProceedings{Prangl2007b, author = {Prangl, Martin and Bachlechner, Roland and Hellwagner, Hermann}, booktitle = {2007 IEEE International Conference on Multimedia and Expo (ICME 2007)}, title = {A hybrid recommender strategy for personalized utility-based cross-modal multimedia adaptation}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {Zhuang, Xinhua and Gao, Wen}, month = jul, pages = {1707-1710}, publisher = {IEEE}, abstract = {Enabling transparent and augmented use of multimedia content across a wide range of networks and devices is still a challenging task within the multimedia research community. Within multimedia frameworks, content adaptation is the core concept to overcome this issue. Most media adaptation engines targeting Universal Multimedia Access (UMA) scale the content w.r.t. terminal capabilities and network resource constraints and do not sufficiently consider user preferences. This paper focuses on a hybrid recommender technique for configuring a cross-modal utility model that guides adaptation of multimedia content. This approach additionally considers the user environment as well as demographic user data which leads to a personalized and increased multimedia experience. Based on a related adaptation decision technique we show how it is possible to offer a personalized adaptation for the individual user. We present a detailed evaluation of the approach based on results earned by subjective tests.}, issn = {1-4244-1017-7}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/A hybrid recommender strategy for personalized utility-based cross-modal multimedia adaptation.pdf}, talktype = {none} } @InProceedings{Prangl2007, author = {Prangl, Martin and Hellwagner, Hermann}, booktitle = {World of Wireless, Mobile and Multimedia Networks, 2007. WoWMoM 2007}, title = {A framework for personalized utility-aware IP-based multimedia consumption}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {Fleury, Eric and Karl, Holger}, month = {jan}, pages = {1-3}, publisher = {IEEE}, abstract = {Providing transparent and augmented use of multimedia content across a wide range of networks and devices is still a challenging task within the multimedia research community. Multimedia adaptation was figured out as a core concept to overcome this issue. Most multimedia adaptation engines for providing Universal Multimedia Access (UMA) scale the content under consideration of terminal capabilities and resource constraints but do not really consider individual user preferences. This paper introduces an adaptive multimedia framework which offers the user a personalized content variation for satisfying his/her individual utility preferences.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/A framework for personalized utility-aware ip-based multimedia consumption.pdf}, talktype = {none}, url = {http://www.tml.tkk.fi/IEEE-wowmom/index.html} } @InProceedings{Oberbichler2007b, author = {Oberbichler, Alexander and Böszörmenyi, Laszlo}, booktitle = {Proceedings of I-Know ´07 - 7th International Conference on Knowledge Management}, title = {Printf in 4D User Interfaces}, year = {2007}, address = {Graz, Austria}, editor = {Tochtermann, Klaus and Maurer, Hermann}, month = sep, pages = {377-383}, publisher = {TU Graz \& Know Center}, language = {EN}, talktype = {none} } @InProceedings{Lux2007b, author = {Lux, Mathias and Granitzer, Michael and Kern, Roman}, booktitle = {18th International Workshop on Database and Expert Systems Applications (DEXA 2007)}, title = {Aspects of Broad Folksonomies}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {Tjoa, A-Min and Wagner, R R}, month = sep, pages = {283-287}, publisher = {IEEE}, abstract = {Folksonomies, collaboratively created sets of metadata, are becoming more and more important for organising information and knowledge of communites in the Web. While for a single user the difference to keyword assignment is marginal, the power of folksonomies emerges from the collaborative aspects. Folksonomies are already issue of research.Within this publication we analyse underlying statistical properties of broad folksonomies aiming to identify laws and characteristics, which allow inferring properties for folksonomy based retrieval. The actual benefit of folksonomies for retrieval and the derived methods are concluded from experiments with aggregated data from del.icio.us1.}, doi = {10.1109/DEXA.2007.40}, isbn10 = {0-7695-2932-1}, issn = {1529-4188}, language = {EN}, talktype = {none} } @InProceedings{Lux2007, author = {Lux, Mathias and Dösinger, Gisela and Beham, Günter}, booktitle = {Datenbanksysteme in Business, Technologie und Web (BTW 2007)}, title = {Empirical Studies in Multimedia Retrieval Evaluation}, year = {2007}, address = {NA}, editor = {Jarke, Matthias and Seidl, Thomas and Quix, Christoph and Kensche,David and Conrad, Stefan and Rahm, Erhard and Klamma, Ralf and Kosch, Harald and Granitzer, Michael and Apel, Sven and Rosenm, Marko and Saake, Gunter and Spinczyk, Olaf}, month = mar, pages = {199-217}, publisher = {NA}, abstract = {The evaluation of retrieval mechanisms for inter-method comparison is necessary in academic as well as in applied research. A major issue in every evaluation is in which way and to what extent the actual perception of the user from the target user group is integrated. Within multimedia retrieval systems the impressions and perceptions of users vary much more than in text retrieval. Empirical studies are a common tool in social science and offer a way to research the correlation between the user perception and the computed similarity between pairs of multimedia documents or a query and the set of results. This approach can be used to complement and extend current evaluation approaches. Within this contribution we summarize general methods from social science and psychology for the interested reader in the area of computer science with some knowledge about statistics. Furthermore we give two examples of undertaken empirical experiments and their outcomes. Within the first one the perception of users is investigated and compared to factors like background and gender, while in the second study metrics are tested upon their ability to reflect the notion of similarity of users. Both experiments aim to give examples and insight on how empirical studies can be used in multimedia research in general and multimedia retrieval evaluation in special.}, issn = {3-86130-929-7}, language = {EN}, talktype = {none}, url = {http://pdf.aminer.org/000/069/740/empirical_studies_in_multimedia_retrieval_evaluation.pdf} } @InProceedings{Lang2007, author = {Lang, Margit and Kosch, Harald and Stars, S and Kettner, Cartsten and Lachner, Janine and Oborny, Doris}, booktitle = {Proceedings of the 8th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS 2007)}, title = {Recognition of Botanical Bloom Characteristics from Visual Features.}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {Kompatsiaris, Y and Avrithis, Y}, month = jun, pages = {27-27}, publisher = {IEEE}, abstract = {There is a number of image retrieval systems which allow a fast similarity search in large image databases. But to our knowledge there are no image retrieval systems which bring together information extraction from the image as well as object recognition and classification of the object analyzed. This paper introduces techniques to enable the extraction of botanical characteristics from visual features to support semi-automatic plant recognition. The identification of plants requires recognition and determination of plant species specific features such as bloom colour, inflorescences, shape of blooms, number of petals and shape of leaves. Our approach is to improve an existing medicinal plant database, called MedPhyt, by this basic requirement. We demonstrate the first steps towards a semiautomatic system for the identification of a plant species or at least plant families by the combination of both bloom colour and contour information under consideration of a specific content and knowledge domain using the features of MPEG-7.}, issn = {076952818X}, language = {EN}, talktype = {none} } @InProceedings{Lachner2007, author = {Lachner, Janine and Lorenz, Andreas and Reiterer, Bernhard and Zimmermann, Andreas and Hellwagner, Hermann}, booktitle = {Second International Workshop on Semantic Media Adaptation and Personalization (SMAP 2007)}, title = {Challenges toward User-centric Multimedia}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {Mylonas, Phivos and Wallace, Manolis and Angelides, Marios C}, month = sep, pages = {159-164}, publisher = {IEEE}, abstract = {Currently, much research aims at coping with the shortcomings in multimedia consumption that may exist in a user's current context, e.g., due to the absence of appropriate devices at many locations, a lack of capabilities of mobile devices, restricted access to content, or non-personalized user interfaces. Recently, solutions to specific problems have been emerging, e.g., wireless access to multimedia repositories over standardized interfaces; however, due to usability restrictions the user has to spend much effort to or is even incapable of fulfilling his/her demands. The vision of user-centric multimedia places the user in the center of multimedia services to support his/her multimedia consumption intelligently, dealing with the aforementioned issues while minimizing required work. Essential features of such a vision are comprehensive context awareness, personalized user interfaces, and multimedia content adaptation. These aspects are addressed in this paper as major challenges toward a user-centric multimedia framework.}, isbn10 = {0769430400}, isbn13 = {9780769530406}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Challenges toward User-centric Multimedia.pdf}, talktype = {none}, url = {http://www.smap2007.org/} } @InProceedings{Kropfberger2007, author = {Kropfberger, Michael and Tusch, Roland and Jakab, Michael and Köpke, Julius and Ofner, Michael and Hellwagner, Hermann and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 3rd International Conference on Web Information Systems and Technologies (WEBIST '07)}, title = {A Multimedia-Based Guidance System for various Consumer Devices}, year = {2007}, address = {Setubal, Portugal}, editor = {Filipe, Joaquim and Cordeiro, José}, month = mar, pages = {83-90}, publisher = {INSTICC Press}, abstract = {This paper introduces aWeb-based guidance system which supports optimized presentations of sights or exhibited objects on different types of available stationary and mobile consumer devices, possibly running different operating systems. This is accomplished by adapting both the objects’ content, as well as their presentation to the current usage context. Content thereby may be encoded in different presentation formats like video, audio, image, and marked-up text. The usage context embraces a set of properties describing the current usage environment of the guide. This includes, for example, the consumer device’s capabilities, its current location, and the user’s preferences. Both, the content adaptation and presentation services are based on standardWeb technologies for increased interoperability. Finally, the guidance system is augmented with a Web-based content management and a statistics module, which enable for remote content administration and usage evaluations, respectively.}, isbn13 = {978-3-540-68257-8}, keywords = {Multimedia-based guide for stationary and mobile devices, context-awareness, content adaptation, presentation adaptation, content management.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/A multimedia-based guidance system for various consumer devices.pdf}, talktype = {none}, url = {http://www.webist.org/} } @InProceedings{Kofler2007a, author = {Kofler, Ingo and Timmerer, Christian and Ahmed, Toufik and Hellwagner, Hermann}, booktitle = {Proceedings of the Second International Workshop on Semantic Media Adaptation and Personalization (SMAP)}, title = {Towards MPEG-21-based Cross-layer Multimedia Content Adaptation}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {Mylonas, Phivos and Wallace, Manolis and Angelides, Marios C}, month = dec, pages = {3-8}, publisher = {IEEE}, series = {SMAP}, abstract = {The adaptation of multimedia resources is a common method to enable the transport and consumption of audio-visual content in constrained environments. An important aspect in this field is adaptation decision-taking, which aims to find adaptation parameters that maximize the quality for the consumer while considering the constraints of the networks and terminals involved. In this paper we focus on improving the adaptation of audio-visual content by maximizing the perceived quality. This can be realized by using a multimedia quality model and content-related metadata. We present an approach to derive this content-related metadata from subjective tests and use it for adaptation decision-taking within the MPEG-21 multimedia framework.}, doi = {10.1109/SMAP.2007.34}, isbn10 = {0769530400}, isbn13 = {978-0769530406}, language = {EN}, location = {London, United Kingdom}, pdf = {https://www.itec.aau.at/bib/files/MPEG-21XL_SMAP2007.pdf}, talkdate = {2009.05.29}, talktype = {registered} } @InProceedings{Kofler2007, author = {Kofler, Ingo and Timmerer, Christian and Hutter, Andreas and Sanahuja, Francesc}, booktitle = {Proceedings of {SPIE-IS\&T} Electronic Imaging Multimedia Computing and Networking Conference ({MMCN})}, title = {Efficient MPEG-21-based Adaptation Decision-Taking for Scalable Multimedia Content}, year = {2007}, address = {Bellingham, Washington, USA}, editor = {Zimmermann, Roger and Griwodz, Carsten}, month = jan, pages = {65040J-1-65040J-8}, publisher = {SPIE}, series = {MMCN}, abstract = {The MPEG-21 standard defines a framework for the interoperable delivery and consumption of multimedia content. Within this framework the adaptation of content plays a vital role in order to support a variety of terminals and to overcome the limitations of the heterogeneous access networks. In most cases the multimedia content can be adapted by applying different adaptation operations that result in certain characteristics of the content. Therefore, an instance within the framework has to decide which adaptation operations have to be performed to achieve a satisfactory result. This process is known as adaptation decision-taking and makes extensive use of metadata describing the possible adaptation operations, the usage environment of the consumer, and constraints concerning the adaptation. Based on this metadata a mathematical optimization problem can be formulated and its solution yields the optimal parameters for the adaptation operations. However, the metadata is represented in XML resulting in a verbose and inefficient encoding. In this paper, an architecture for an Adaptation Decision-Taking Engine (ADTE) is introduced. The ADTE operates both on XML metadata and on metadata encoded with MPEG's Binary Format for Metadata (BiM) enabling an efficient metadata processing by separating the problem extraction from the actual optimization step. Furthermore, several optimization algorithms which are suitable for scalable multimedia formats are reviewed and extended where it was appropriate}, edition = {Volume 6504}, isbn13 = {9780819466174}, keywords = {Adaptation Decision-Taking, MPEG-21, Digital Item Adaptation, Binary Format for Metadata (BiM)}, language = {EN}, location = {San Jose, CA, USA}, pdf = {https://www.itec.aau.at/bib/files/MMCN2007EfficientMPEG21basedAdaptationDecisionTaking.pdf}, talkdate = {2007.02.01}, talktype = {registered} } @InProceedings{Jakab2007, author = {Jakab, Michael and Kropfberger, Michael and Ofner, Michael and Tusch, Roland and Hellwagner, Hermann and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 15th Euromicro Conference on Parallel, Distributed and Network-based Processing}, title = {Metadata Integration and Media Transcoding in Universal-Plug-and-Play (UPnP) Enabled Networks}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {D'Ambra, Pasqua and Guarracino, Mario R}, month = jan, pages = {363 - 369}, publisher = {IEEE}, abstract = {Universal Plug and Play (UPnP) is a widely accepted standard for automatically detecting devices and services in a local area network as well as for describing and controlling them. In order to deal with multimedia devices and especially content, in 2002 the UPnP-AV standard definition was released. It defines device and service descriptions for Media Servers and Renderers. Thereby, the Media Server’s Content Directory Service allows an easy management and the exchange of metadata about the provided media data. Media content became browsable by semantic meta information about it. There are still two major drawbacks of UPnP-AV, which make its usage in real world multimedia communication scenarios very difficult. First, searching for similar content on distributed Media Servers with a huge number of media files is not economically possible. Second, the media content must be consumed by Renderers as provided by the Servers, independently of their terminal capabilities and network connections. In order to deal with these two drawbacks, this work proposes a novel approach of metadata integration and media transcoding in UPnP networks. First, the Media Server is extended by a Control Point which offers discovery of other Media Servers and fetches metadata from their Content Directories. Furthermore, it integrates the gathered information in its own Content Directory. Control Points are then able to query this Integrating Media Server for a desired content, and get a network-complete search result. Second, terminal and network capabilities of the Render-ers are taken into account in order to transcode and transmit the content in a suitable way for the consuming device. These two approaches of metadata integration and media data adaptation enable searchable logical views on tailored multimedia content in UPnP-AV networks.}, issn = {1066-6192}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Universal-Plug-and-Play.pdf}, talktype = {none} } @InProceedings{Cobarzan2007, author = {Cobarzan, Claudiu and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 15th Euromicro Conference on Parallel, Distributed and Network-based Processing}, title = {Further Developments of a Dynamic Distributed Video Proxy-Cache System}, year = {2007}, address = {Los Alamitos, CA, USA}, editor = {Ambra, P D and Guarracino, M R}, month = jan, pages = {349-357}, publisher = {IEEE}, issn = {1066-6192}, language = {EN}, talktype = {none} } @InProceedings{Boeszoermenyi2007b, author = {Böszörmenyi, Laszlo}, booktitle = {Information und Gesellschaft - Technologien einer sozialen Beziehung}, title = {Die Henne, modernes Bewusstsein, das Ei moderne Technik?}, year = {2007}, address = {Wiesbaden, Germany}, editor = {Greif, Hajo and Mitrea, Oana and Werner, Matthias}, month = sep, pages = {41-46}, publisher = {Deutscher Universitäts-Verlag und der VS Verlag für Sozialwissenchaften}, issn = {9783835070073}, language = {DE}, talktype = {none}, url = {https://www.itec.aau.at/~laszlo/publications/Proceedings/LB_2008_Beitrag_Information_und_Gesellschaft_Kurzfassung.pdf} } @InProceedings{Zufferey2006, author = {Zufferey, Michael and Kosch, Harald}, booktitle = {Proceedings of the 48th International Symposium ELMAR-2006}, title = {Semantic Adaptation of Multimedia Content}, year = {2006}, address = {Zadar}, editor = {Grgic, M and Grgic, S}, month = jun, pages = {319-322}, publisher = {IEEE}, abstract = {The increasing diversity of devices and the heterogeneity of networks pose nowadays a challenge in the delivery and consumption of multimedia content. In this context, the Part 7 of the MPEG-21 standard formally named Digital Item Adaptation (DIA) targets the adaptation of multimedia content based on usage environment, such as network characteristics, terminal capabilities and user characteristics. But, MPEG-21 DIA does not take into account MPEG-7 semantics description tools, which provide means for a conceptual (semantic) description that is close to the human understanding of multimedia content. Therefore, to fill this gap, we proposed and implemented an interactive and user-centric framework called Semantic Adaptation Framework (SAF). The SAF provides facilities for the generation of all the required semantic metadata and enables an MPEG-21 adaptation engine to semantically adapt the multimedia content in order to provide the user with the best possible experience.}, issn = {13342630}, language = {EN}, talktype = {none} } @InProceedings{Timmerer2006, author = {Timmerer, Christian and DeMartini, Thomas and Hellwagner, Hermann}, booktitle = {D A CH Security 2006}, title = {The MPEG-21 Multimedia Framework: Conversions and Permissions}, year = {2006}, address = {Düsseldorf}, editor = {Horster, Patrick}, month = mar, pages = {225-235}, publisher = {IT Security \& IT Management}, abstract = {In the area of multimedia computing and communication, one of the major objectives currently being pursued is Universal Multimedia Access (UMA), i.e., enabling users to transparently access any kind of content from anywhere, anytime, with any device. In the course of the MPEG-21 (Multimedia Framework) activities, the ISO/IEC MPEG standardization group has created essential building blocks toward this goal, mainly metadata standards. Two of them are worth noting here: (1) the Digital Item Adaptation (DIA) specification, including normative vocabulary and formats to describe the multimedia consumption context (device, network, natural environment characteristics, user preferences) and to steer media adaptation operations required for UMA; (2) the Rights Expression Language (REL) and Rights Data Dictionary (RDD) specifications, providing terms and a language to express permissions on the usage of the media (who, how, what, under which conditions). In this paper, we describe a recent MPEG-21 DIA Amendment in this area, specifying description formats for: (1) multimedia conversion capabilities, which tool or service providers may use to normatively specify the media adaptation (conversion) capabilities of their tools or services, respectively; (2) permissions and conditions for multimedia conversions, which can be utilized by content providers to determine which adaptations (changes) are permitted on their contents under what conditions. The latter description format embeds media adaptation descriptions into rights expressions, filling a gap between DIA and REL/RDD. In the paper, a use case illustrating a complex UMA scenario justifies the need for these descriptions. Exemplary conversions and permissions descriptions that apply to this use case as well as detailed explanations will be given in the main portion of the paper.}, issn = {3-00-018166-0}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/The MPEG-21 multimedia framework.pdf}, talktype = {none} } @InProceedings{Spielvogel2006, author = {Spielvogel, Christian and Böszörmenyi, Laszlo and Schoeffmann, Klaus}, booktitle = {Minema Workshop Proceedings}, title = {An adaptive and self-organizing Proxy-to-Proxy Middleware}, year = {2006}, address = {Leuven}, editor = {Universität, Leuven}, month = feb, pages = {6}, publisher = {Eigenverlag Universität Leuven}, language = {EN}, talktype = {none} } @InProceedings{Schojer2006a, author = {Schojer, Peter and Böszörmenyi, Laszlo and Hellwagner, Hermann}, booktitle = {Multimedia Computing and Networking 2006}, title = {QBIX-G- A Transcoding Multimedia Proxy}, year = {2006}, address = {San Jose}, editor = {Chandra, Surendar and Griwodz, Carsten}, month = jan, pages = {60710C-1 - 60710C-16}, publisher = {SPIE}, abstract = {An adaptive multimedia proxy is presented which provides (1) caching, (2) filtering, and (3) media gateway functionalities. The proxy can perform media adaptation on its own, either relying on layered coding or using transcoding and transrating in the decompressed domain. A cost model is presented which incorporates (1) user requirements, (2) terminal capabilities, and (3) video variations in one formula. Based on this model, the proxy acts as a general broker of different user requirements and of different video variations. This is a first step towards “What You Need is What You Get” (WYNIWYG) video services, which deliver videos to users in exactly that quality they need and are willing to pay for. The MPEG-7 and MPEG-21 standards enable this in an interoperable way. A detailed evaluation based on a series of simulation runs is provided. Based on the simulation results, the algorithms were integrated into our “Quality Based Intelligent Proxy”, the evaluation of which is in progress.}, issn = {0-8194-6111-3}, language = {EN}, talktype = {none} } @InProceedings{Santner2006, author = {Santner, Martin and Tusch, Roland and Kropfberger, Michael and Böszörmenyi, Laszlo and Hellwagner, Hermann}, booktitle = {D•A•CH Mobility 2006}, title = {Ein Ortserkennungssystem für mobile Touristenführer}, year = {2006}, address = {Ottobrunn, München, Deutschland}, editor = {Horster, Patrick}, month = oct, pages = {84-98}, publisher = {IT Security \& IT Management}, abstract = {- Location-Based Services - Ortserkennungstechnologien - Ortserkennungsmiddleware - Integration in mobile Anwendung - Automatisiertes Führungssystem.}, issn = {3000196358}, language = {DE}, talktype = {none} } @InProceedings{Ransburg2006, author = {Ransburg, Michael and Cazoulat, Renaud and Pellan, Benoit and Concolato, Cyril and De Zutter, Saar and Poppe, Chris and Hutter, Andreas and Hellwagner, Hermann and Van de Walle, Rik}, booktitle = {Proc. of the European Symposium on Mobile Media Delivery (EuMob 2006)}, title = {Dynamic and Distributed Adaptation of Scalable Multimedia Content in a Context-Aware Environment}, year = {2006}, address = {Alghero, Italy}, editor = {EuMob, 2006}, month = sep, pages = {1-5}, publisher = {--}, abstract = {The seamless access to rich multimedia content on any device and over any network, usually known as Universal Multimedia Access, requires interoperable description tools and adaptation techniques to be developed. To address this, MPEG-21 introduces an adaptation framework, which provides several mechanisms for making adaptation decisions according to usage environment and adapting multimedia contents in a coding format independent way. This paper gives an overview of the European FP6 project DANAE which not only implements and extends the existing MPEG-21 adaptation mechanisms but also kicked off several new standardization activities in the area of dynamic and distributed adaptation and resource conversion. MPEG-21 DIP enables static stream selection which is a first step in a series of adaptations. The existing BSD-based adaptation mechanisms enable the efficient implementation of generic adaptation engines, which can be used for existing and future coding formats. These mechanisms were extended to enable dynamic and distributed adaptation. Alternatively to the BSD-based adaptation, resource conversion was investigated which does not rely on scalable media and allows adaptations at the scene level.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Dynamic and Distributed Adaptation of Scalable Multimedia Content in a Context-Aware Environment.pdf}, talktype = {none} } @InProceedings{Prangl2006d, author = {Prangl, Martin and Hellwagner, Hermann and Szkaliczki, Tibor}, booktitle = {Proceedings oft the IEEE International Conference on Multimedia and Expo (ICME)}, title = {Fast adaptation decision taking for cross-modal multimedia content adaptation}, year = {2006}, address = {Toronto, Canada}, editor = {Ling, Guan and Hong-Jiang, Zhang}, month = jul, pages = {137-140}, publisher = {IEEE Press}, abstract = {In order to enable transparent and convenient use of multimedia content across a wide range of networks and devices, content adaptation is an important issue within multimedia frameworks. The so called Digital Item Adaptation (DIA) standard is one of the core concepts of the MPEG-21 framework that will support the adaptation of multimedia resources according to device capabilities, underlying network characteristics, and user preferences. Most multimedia adaptation engines for providing Universal Multimedia Access (UMA) scale the content with respect to terminal capabilities and resource constraints. This paper focuses on the cross-modal adaptation decision taking process considering the user environment and terminal capabilities as well as resource limitations on the server, network, and client side. This approach represents a step toward increased Universal Multimedia Experience (UME). Based on four different algorithms for solving this optimization process, we present an evaluation of results gained by running their implementations on different test networks.}, issn = {1-4244-0367-7}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Fast adaptation decision taking for cross-modal multimedia content adaptation.pdf}, talktype = {none} } @InProceedings{Prangl2006c, author = {Prangl, Martin and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings ELMAR 2006}, title = {Real-time DVB based MPEG-21 Digital Item Adaptation for live Universal Multimedia Access}, year = {2006}, address = {Zadar}, editor = {Grgic, Mislav and Grgic, Sonja}, month = jun, pages = {297-300}, publisher = {Croatian Society Electronics in Marine - ELMAR, Zadar}, abstract = {In order to enable transparent and augmented use of multimedia content across a wide range of networks and devices, content adaptation is an important issue within multimedia frameworks. In this paper, we present a prototype application that receives Digital Video Broadcast (DVB) TV streams on a PC, transcodes the streams on the fly according to the individual User requirements and packs the adapted content together with available metadata into a standard compliant MPEG-21 Digital Item (DI). In this form, the framework enables the live Universal Multimedia Access (UMA) scenario where the DVB content can be transparently accessed by clients such as PCs and PDAs, anytime and anywhere.}, issn = {13342630}, keywords = {DVB, MEPG-2, MPEG-4, MPEG-7, MPEG-21, Digital Items, metadata}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Real-time DVB-based MPEG-21 Digital Item Adaptation.pdf}, talktype = {none} } @InProceedings{Prangl2006b, author = {Prangl, Martin and Hellwagner, Hermann and Szkaliczki, Tibor}, booktitle = {Proceedings of the 7th International Workshop on Image Analysis for Multimedia Services (WIAMIS)}, title = {A Semantic-based Multi-modal Utility Approach For Multimedia Adaptation}, year = {2006}, address = {Incheon, Korea}, editor = {Ebroul, Izquierdo and Hyoung Joon, Kim}, month = apr, pages = {67-70}, publisher = {WIAMIS Eigenverlag}, abstract = {Content adaptation is an important issue of multimedia frameworks in order to achieve Universal Multimedia Access (UMA), that is, to enable consumption of individual multimedia content independently of the given resource limitations, terminal capabilities and user preferences. The Digital Item Adaptation (DIA) standard, one of the core specifications of the MPEG-21 framework, supports content adaptation considering a wide range of networks, devices and user preferences. Most adaptive multimedia frameworks enabling this UMA do not consider utility aspects in their adaptation decisions. This paper focuses on a generic multi-modal utility model for DIA, enabling increased multimedia experience to the client. Our proposed model is able to take the semantic and the perceptual features of the content as well as the clients individual utility aspects into consideration. Based on a detailed analysis of these constraints we will show how the model reacts on individual input data. Finally we will discuss results of the multi-modal decision taking process according to a few use case scenarios as well.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/A Semantic-based Multi-modal Utility Approach For Multimedia Adaptation.pdf}, talktype = {none} } @InProceedings{Prangl2006a, author = {Prangl, Martin and Hellwagner, Hermann and Bischof, Horst and Szkaliczki, Tibor}, booktitle = {Proceedings of the SPIE Symposium on Medical Imaging 2006}, title = {Realtime automatic metal extraction of medical x-ray images for contrast improvement}, year = {2006}, address = {San Diego}, editor = {Reinhardt, Joseph M and Pluim, Josien P W}, month = mar, pages = {8}, publisher = {SPIE}, series = {Vol. 6144}, abstract = {This paper focuses on an approach for real-time metal extraction of x-ray images taken from modernx-ray machines like C-arms. Such machines are used for vessel diagnostics, surgical interventions, as well as cardiology, neurology and orthopedic examinations. They are very fast in taking images from different angles. For this reason, manual adjustment of contrast is infeasible and automatic adjustment algorithms have been applied to try to select the optimal radiation dose for contrast adjustment. Problems occur when metallic objects, e.g., a prosthesis or a screw, are in the absorption area of interest. In this case, the automatic adjustment mostly fails because the dark, metallic objects lead the algorithm to overdose the x-ray tube. This outshining effect results in overexposed images and bad contrast. To overcome this limitation, metallic objects have to be detected and extracted from images that are taken as input for the adjustment algorithm.In this paper, we present a real-time solution for extracting metallic objects of x-ray images. We will explore the characteristic features of metallic objects in x-ray images and their distinction from bone fragments which form the basis to find a successful way for object segmentation and classification. Subsequently, we will present our edge based real-time approach for successful and fast automatic segmentation and classification of metallic objects. Finally, experimental results on the effectiveness and performance of our approach based on a vast amount of input image data sets will be presented.}, isbn13 = {9780819464231}, keywords = {Pattern recognition, Segmentation, Medical imaging, X-Ray, Artefact-Segmentation}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Realtime automatic metal extraction of medical x-ray images for contrasst improvement.pdf}, talktype = {none} } @InProceedings{Lux2006c, author = {Lux, Mathias and Scheir, P and Granitzer, Michael and Lindstaedt, S}, booktitle = {6th International Conference on Knowledge Management}, title = {Special Track on Advanced Semantic Technologies - Introduction}, year = {2006}, address = {Graz}, editor = {Tochtermann, Klaus and Maurer, Hermann}, month = sep, pages = {249-251}, publisher = {Eigenverlag in Kooperation mit Springer Verlag}, issn = {0948695x}, language = {EN}, talktype = {none} } @InProceedings{Lux2006a, author = {Lux, Mathias and Meyer zu Eissen, Sven and Granitzer, Michael}, booktitle = {Proceedings of the Workshop on Text-Based Information Retrieval TIR 06}, title = {Graph Retrieval with the Suffix Tree Model}, year = {2006}, address = {Riva del Garda}, editor = {Stein, Benno and Kao, Odej}, month = aug, pages = {30-34}, publisher = {Università di Trento, Italy}, abstract = {The paper in hand presents an adoption of the suffix tree model for the retrieval of labeled graphs. The suffix tree model encodes path information of graphs in an efficient way and so reduces the size of the data structures compared to path index based approaches, while offering a better runtime performance than subgraph isomorphism based methods. Within a specific use case we evaluate the correlation of the developed method to human judgement and compare the correlation values to other methods. We show that in our use case, which is the retrieval of digital photos annotated with MPEG-7 using the MPEG-7 Semantic Description Scheme, the presented algorithm performs better than other methods.}, issn = {1613-0073}, language = {EN}, talktype = {none}, url = {http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS//Vol-205/} } @InProceedings{Lampl2006, author = {Lampl, Oliver and Stellnberger, Elmar and Böszörmenyi, Laszlo}, booktitle = {Modular Porgramming Languages}, title = {Programming Language Concepts for Multimedia Application Development}, year = {2006}, address = {Heidelberg, Germany}, editor = {Lightfoot, David and Szyperski, Clemens}, month = sep, pages = {23-37}, publisher = {Springer Verlag}, series = {Proceedings of 7th Joint Modular Languages Conference (JMLC)}, issn = {0302-9743}, language = {EN}, talktype = {none} } @InProceedings{Kofler2006a, author = {Kofler, Ingo and Hellwagner, Hermann}, booktitle = {Proceedings of the 2nd International Conference on Automated Production of Cross Media Content for Multi-channel Distribution ({AXMEDIS})}, title = {MPEG-21-based Cross-Resource Adaptation Decision-Taking}, year = {2006}, address = {Firenze, Italy}, editor = {Kia, Ng and Badii, Atta and Bellini, Pierfrancesco}, month = dec, pages = {207-214}, publisher = {Firenze University Press}, series = {AXMEDIS}, abstract = {The adaptation of multimedia resources is a common method to enable the transport and consumption of audio-visual content in constrained environments. An important aspect in this field is adaptation decision-taking, which aims to find adaptation parameters that maximize the quality for the consumer while considering the constraints of the networks and terminals involved. In this paper we focus on improving the adaptation of audio-visual content by maximizing the perceived quality. This can be realized by using a multimedia quality model and content-related metadata. We present an approach to derive this content-related metadata from subjective tests and use it for adaptation decision-taking within the MPEG-21 multimedia framework.}, language = {EN}, location = {Leeds, United Kingdom}, pdf = {https://www.itec.aau.at/bib/files/AXMEDIS2006MPEG21CrossResourceAdaptationDecisionTaking.pdf}, talkdate = {2006.12.13}, talktype = {registered} } @InProceedings{Karpati2006, author = {Karpati, Peter and Szkaliczki, Tibor and Böszörmenyi, Laszlo}, booktitle = {Methods and tools for development of semantic enabled systems and services for multimedia content, interoperability and reusability}, title = {Abstracting Characterizing Distributed VoD Servers}, year = {2006}, address = {Budapest, Ungarn}, editor = {Böszörmenyi, Laszlo and Simonics, Istvan and Pavlov, Radoslav}, month = aug, pages = {16-30}, publisher = {Eigenverlag Universität Klagenfurt/Projekt Hubuska}, language = {EN}, talktype = {none} } @InProceedings{GuenkovaLuy2006, author = {Guenkova-Luy, Teodore and Schorr, Andreas and Hauck, Franz and Gómez, Miguel and Timmerer, Christian and Wolf, Ingo and Kassler, Andreas}, booktitle = {Proceedings of IASTED International Conference onInternet and Multimedia Systems and Applications (EuroIMSA 2006)}, title = {Advanced Multimedia Management – Control Model and Content Adaptation}, year = {2006}, address = {Anaheim, CA, USA}, editor = {Boucouvalas, Anthony Christos}, month = apr, pages = {130-135}, publisher = {ACTA Press}, abstract = {The delivery and adaptation of multimedia content in dis tributed and heterogeneous environments requires flexible control and management mechanisms in terminals and in control entities inside the network. In the near future, it is important to reach interoperability between the IETF ap proaches on multimedia session establishment and control and the MPEG-21 efforts for multimedia streaming and adaptation to bring advanced multimedia service provi sioning and adaptation services towards the customer. MPEG-21 Digital Item Adaptation (DIA) provides norma tive descriptions for supporting adaptation of multimedia content, but does not define interactions with transport and control mechanisms. On the other hand, the IETF standardization efforts on multimedia session control pro vide the necessary transport (e.g. RTP) and control mechanisms (SDP/SDPng). We thus bridge the gap be tween those approaches by creating a converged XML model that enables the integration of session management and negotiation protocols (e.g. SIP or Megaco) inspired by the XML formats of MPEG-21 DIA and SDPng. We also present preliminary implementation results of the con verged model along with concepts and implementation of network-based content adaptation mechanisms through media gateways that enable flexible multimedia manage ment for heterogeneous consumer terminals.}, isbn10 = {0-88986-564-7}, keywords = {MPEG-21 DIA, SDP, SDPng, QoS, content adaptation, media gateways}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/516-048.pdf}, talktype = {none} } @InProceedings{Granitzer2006a, author = {Granitzer, Michael and Neidhart, T and Lux, Mathias}, booktitle = {Proceedings of the 17th International Conference on Database and Expert Systems Applications (DEXA'06)}, title = {Learning Term Spaces based on Visual Feedback}, year = {2006}, address = {Los Alamitos, CA, USA}, editor = {Tjoa, A Min and Wagner, R}, month = sep, pages = {176-180}, publisher = {IEEE Computer Society}, abstract = {Extracting and visualizing concepts and relationship between text documents strongly depends on the used similarity measure. In order to provide meaningful visualizations and to extract useful knowledge from document collections, user needs must be captured by the internal representation of documents, and the used similarity measure. In most applications the Vector Space Model and the Cosine similarity are used therefore and serve as good approximations. Nevertheless, influencing similarities between documents is rather hard, since parameter tuning relies heavily on expert knowledge of the underlying algorithms, and the influence of different weighting schemes and similarity measures is not known before. In this paper we present an approach on how to adapt the vector space representation of documents by giving visual feedback to the system. Our approach starts by clustering a corpus of text documents and visualizing the results using multi dimensional scaling techniques. Afterwards, a 2D landscape visualization is shown which can be manipulated by the user. Based on these manipulations the high dimensional representation of the documents is adapted to fit the users need more precisely. Our experiments show that iterating these steps results in an adapted representation of documents and similarities, generating layouts as intended by the user and furthermore increases clustering accuracy. While this paper only investigates the influence on clustering and visualization, the method itself may also be used for increasing classification and retrieval performance since it adapts to the users need of similarity.}, language = {EN}, talktype = {none} } @InProceedings{Granitzer2006, author = {Granitzer, Michael and Kosch, Harald and Lux, Mathias}, booktitle = {6th International Conference on Knowledge Management}, title = {5th Multimedia Metadata Community Workshop - Introduction}, year = {2006}, address = {Graz}, editor = {Tochtermann, Klaus and Maurer, Hermann}, month = sep, pages = {568-569}, publisher = {Eigenverlag in Kooperation mit Springer Verlag}, issn = {0948695x}, language = {EN}, talktype = {none} } @InProceedings{Zufferey2005, author = {Zufferey, Michael and Kosch, Harald}, booktitle = {n Proceedings of the 6th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS 2005)}, title = {Semantic Adaptation of Multimedia Content}, year = {2005}, address = {Montreux}, editor = {Dufaux, F and Ebrahimi, T and Strintzis, M}, month = apr, pages = {4}, publisher = {WIAMIS}, abstract = {The increasing diversity of devices and the heterogeneity of networks pose nowadays a challenge in the delivery and consumption of multimedia content. In this context, the Part 7 of the MPEG-21 standard formally named Digital Item Adaptation (DIA) targets the adaptation of multimedia content based on usage environment, such as network characteristics, terminal capabilities and user characteristics. But, MPEG-21 DIA does not take into account MPEG-7 semantics description tools, which provide means for a conceptual (semantic) description that is close to the human understanding of multimedia content. Therefore, to fill this gap, we propose an interactive and user-centric framework called Semantic Adaptation Framework (SAF). The SAF provides facilities for the generation of all the required semantic metadata and enables an MPEG-21 adaptation engine to semantically adapt the multimedia content in order to provide the user with the best possible experience.}, issn = {283990067X}, language = {EN}, talktype = {none} } @InProceedings{Timmerer2005e, author = {Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proc. of the First International Conference on Automated Production of Cross Media Content for Multi-channel Distribution (AXMEDIS 2005)}, title = {MPEG Standards enabling Universal Multimedia Access}, year = {2005}, address = {Florence, Italy}, editor = {Nesi, Paolo and Kia, Ng and Delgado, Jamie}, month = dec, pages = {187-196}, publisher = {Firenze University Press}, abstract = {Over the last decade, a wide spectrum of (multi­media) content has become available to an increasing number of users who desire to access it through various devices and over heterogeneous networks. Interoperability is the key for enabling transparent and augmented use of (multimedia) content across a wide range of networks and devices. Standardization efforts within the Moving Picture Experts Group (MPEG), in particular MPEG-7 and MPEG-21, aim to provide appropriate tools for achieving this goal of Universal Multimedia Access (UMA). This tutorial provides, in the first place, the concepts of UMA and corresponding MPEG-7 metadata tools built to support these concepts. Subsequently, the vision, an overview, and the state of the art of the emerging MPEG-21 Multimedia Framework are given. Finally, MPEG-21 Digital Item Adaptation (DIA) tools which implement the “Terminal and Networks Characteristics” key element within the whole framework are illustrated in detail. The goal of MPEG-21 DIA is to achieve interoperable transparent access to (distributed) advanced multimedia content by shielding users from network and terminal installation, configuration, management and implementation issues.}, issn = {88-8453-355-4}, language = {EN}, talktype = {none} } @InProceedings{Timmerer2005d, author = {Timmerer, Christian and Frank, Thomas and Hellwagner, Hermann and Heuer, Jörg and Hutter, Andreas}, booktitle = {Proc. SPIE}, title = {Efficient Processing of MPEG-21 Metadata in the Binary Domain}, year = {2005}, address = {Boston}, editor = {Vetro, Anthony and Wen Chen, Chang and Kuo, C-C Jay and Zhang, Tong and Tian, Qi and Smith, John R}, month = oct, pages = {32-43}, publisher = {Spie}, series = {Multimedia Systems and Applications VIII}, abstract = {XML-based metadata is widely adopted across the different communities and plenty of commercial and open source tools for processing and transforming are available on the market. However, all of these tools have one thing in common: they operate on plain text encoded metadata which may become a burden in constrained and streaming environments, i.e., when metadata needs to be processed together with multimedia content on the fly. In this paper we present an efficient approach for transforming such kind of metadata which are encoded using MPEG's Binary Format for Metadata (BiM) without additional en-/decoding overheads, i.e., within the binary domain. Therefore, we have developed an event-based push parser for BiM encoded metadata which transforms the metadata by a limited set of processing instructions – based on traditional XML transformation techniques - operating on bit patterns instead of cost-intensive string comparisons.}, keywords = {universal multimedia access, multimedia adaptation, compressed-domain metadata processing, bitstream adaptation in constrained and streaming environments, MPEG-21, Digital Item Adaptation, generic Bitstream Syntax Description}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Efficient Processing of MPEG-21 Metadata in the Binary Domain.pdf}, talktype = {none} } @InProceedings{Timmerer2005c, author = {Timmerer, Christian and Lederer, Peter and Kosch, Harald}, booktitle = {CBMI 2005 - Fourth International Workshop on Content-Based Multimedia Indexing}, title = {Transforming MPEG-21 generic Bitstream Syntax Descriptions within the Binary Domain}, year = {2005}, address = {Riga, Latvia}, editor = {Moncef, Gabbouj and Jaakko, Astola and Ferran, Marques}, month = jun, pages = {8}, publisher = {CBMI}, abstract = {XML-based metadata is widely adopted across the different communities and plenty of commercial and open source tools for processing and transforming are available on the market. However, all of these tools have the same requirement: they operate on plain text encoded metadata which may become a burden especially in constrained and streaming environments, e.g., when metadata needs to be processed together with multimedia content which is available in a highly efficient, binary representation format. In this paper we present techniques for transforming such kind of metadata which is encoded using the well known MPEG-7 Systems Binary Format for Metadata (BiM) without additional en-/decoding overheads, i.e., within the binary domain. As such it enables us to process both the multimedia data as well as the metadata within its compressed domain, e.g., for metadata-driven adaptation purposes within intermediary network nodes which are becoming increasingly popular in the multimedia community as well as in the XML community.}, issn = {952-15-1364-0}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/TR_TransformingMPEG-21genericBitstreamSyntaxDescriptionsWithinTheBinaryDomain_Jun2005.pdf}, talktype = {none} } @InProceedings{Timmerer2005a, author = {Timmerer, Christian and Kofler, Ingo and Liegl, Johannes and Hellwagner, Hermann}, booktitle = {Proceedings of the Seventh IEEE International Symposium on Multimedia (ISM)}, title = {An Evaluation of Existing Metadata Compression and Encoding Technologies for MPEG-21 Applications}, year = {2005}, address = {Washington, DC, USA}, editor = {Tsai, Jeffrey and Mühlhäuser, Max and Takizawa, Makoto}, month = dec, pages = {534-539}, publisher = {IEEE}, series = {ISM}, abstract = {XML-based metadata for digital media is becoming increasingly important, as a consequence also calling for efficient encoding and compression schemes for the storage and transport of this metadata. Moreover, support for streaming the XML metadata in conjunction with the media data is highly desirable. Such support is provided, for instance, by MPEG's Binary Format for Metadata (BiM) encoding approach, which facilitates fragmenting, delivering, and accessing the metadata in so- called Access Units (AUs). In this paper, we present a quantitative evaluation of existing XML metadata compression and encoding techniques, reaching from widely used state-of-the-art data compression algorithms to sophisticated XML-aware encoding schemes. The comparison is based on compressing MPEG-21 generic Bitstream Syntax Descriptions (gBSDs) which can grow to non-negligible sizes. The main conclusion from this investigation is that in terms of pure compression efficiency on XML files, the BiM approach (exemplified by the MPEG reference software as well as a commercial version thereof) is comparable – in terms of performance – with traditional data or specific XML compression tools. However, when XML metadata have to be fragmented, compressed, and streamed in such fragments, the results indicate that the BiM approach is superior to the other schemes.}, doi = {10.1109/ISM.2005.31}, language = {EN}, location = {Irvine, CA, USA}, pdf = {https://www.itec.aau.at/bib/files/An Evaluation of Existing Metadata Compression and Encoding Technologies for MPEG-21 Applications.pdf}, talkdate = {2005.12.12}, talktype = {registered} } @InProceedings{Timmerer2005, author = {Timmerer, Christian and Panis, Gabriel and Delfosse, Eric}, booktitle = {Proceedings of the 6th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS 2005)}, title = {Piece-wise Multimedia Content Adaptation in Streaming and Constrained Environments}, year = {2005}, address = {Montreux}, editor = {Dufaux, Frederic and Ebrahimi, Touradj and Strintzis, Michael}, month = {jan}, pages = {4}, publisher = {WIAMIS}, abstract = {Universal Multimedia Access (UMA) has become a driving concept behind a significant amount of research activities. One of MPEG’s (Moving Pictures Experts Group) responses to UMA is MPEG-21 Digital Item Adaptation (DIA). In this paper we present how tools as specified within DIA (i.e., normative XML-based description formats) are applied in streaming and constrained environments enabling piece-wise multimedia content adaptation including the adaptation decision- taking process and the actual resource adaptation in a coding format-independent way. Additionally, we demonstrate how the metadata overhead imposed by DIA tools can be reduced by means of appropriate metadata encoding tools.}, issn = {283990067X}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/TR_Piece-wiseMultimediaContentAdaptationInStreamingAndConstrainedEnvironments_Apr2005.pdf}, talktype = {none} } @InProceedings{Spielvogel2005, author = {Spielvogel, Christian and Böszörmenyi, Laszlo}, booktitle = {Proceedings of IASTED International Conference on Internet and Multimedia Systems and Applications (EuroIMSA 2005)}, title = {Measurement and Prediction of Network Characteristics}, year = {2005}, address = {Grindelwald}, editor = {Hamza, M H}, month = feb, pages = {227-233}, publisher = {ACTA Press}, abstract = {We present the extension of an adaptive distributed multimedia streaming server architecture (ADMS) towards a Quality of Service based network infrastructure. The key component of the extension is the distributed active network estimation and forecasting tool (DANEF). It is able to estimate, process and forecast bottleneck bandwidth, available bandwidth, delay, jitter and loss of a certain path between the streaming server and the requesting client. Using this information, the server node that offers the best QoS for a certain client is selected from a set of possible candidates. Active measurements are performed by sending ICMP [15] packet trains and forecasts are performed by applying fast algorithms that need only small initialization sets. The accuracy of the measurements is achieved by applying an efficient and innovative filtering mechanism, the correctness of the forecasts is achieved by dynamically selecting the best fitting forecast model and by considering the forecast error of previous samples. We have compared DANEF to other already existing measurement tools like BProbe, Cprobe, Pathload, Pathchar and Network Weather Service. As can be found in the evaluation part of this paper DANEF is much better suited for estimating QoS characteristics in the context of multimedia streaming than the other 5 tools it has been compared to.}, issn = {088986484}, language = {EN}, talktype = {none} } @InProceedings{Ransburg2005a, author = {Ransburg, Michael and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Proceedings of the First International Conference on Multimedia Services Access Networks (MSAN 2005)}, title = {Transport mechanisms for metadata-driven distributed multimedia adaptation}, year = {2005}, address = {Orlando, USA}, editor = {N,A}, month = jun, pages = {25-29}, publisher = {IEEE CS Press}, abstract = {The information revolution of the last decade has resulted in a phenomenal increase in the quantity of multimedia content available to an increasing number of different users with different preferences who access it through a plethora of devices and over heterogeneous networks. In order to address the amount of different content types, MPEG-21 Digital Item Adaptation (DIA) introduces interoperable description tools which enable coding format independent adaptation. Bandwidthefficient transport of the content to terminals with different capabilities and through a variety of access networks with various characteristics requires adaptation facilities not only on the server but also within the network. In this paper we present transport mechanisms for MPEG-21-based metadata enabling generic adaptation within the network. Three different transport mechanisms for delivering this metadata in conjunction with the corresponding multimedia content are evaluated and a payload format for the transport of this metadata is presented. Furthermore, we performed measurements which demonstrate the bandwidth benefits of our distributed adaptation approach compared to server-centric adaptation in a multicast scenario. Finally, we applied various encoding formats for the metadata which further reduces the metadata overhead.}, doi = {10.1109/MSAN.2005.1489936}, isbn10 = {0-7803-9319-8}, keywords = {MPEG-21 Digital Item Adaptation; distributed multimedia adaptation; metadata transport}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Transport Mechanisms for Metadata-driven Distributed Multimedia Adaptation.pdf}, talktype = {none} } @InProceedings{Ransburg2005, author = {Ransburg, Michael and Hellwagner, Hermann}, booktitle = {Proceedings of IASTED International Conference on Internet and Multimedia Systems and Applications (EuroIMSA 2005)}, title = {Generic Streaming of Multimedia Content}, year = {2005}, address = {Grindelwald}, editor = {Hamza, Mohamed H}, month = feb, pages = {324-330}, publisher = {ACTA Press}, abstract = {The growing demand for multimedia information by different types of users equipped with a large variety of devices and connecting through different kinds of networks results in an increasing amount of different multimedia formats. Research is currently concentrating on the adaptation of the contents in order to provide Universal Multimedia Access (UMA) for the content consumer. But this does not solve the problem of the content provider, who still has to signal this variety of different multimedia formats to the consumer. In this contribution, we show a way to stream any type of multimedia format based on generic hint information. This hint information is based on a generic bit stream syntax description (gBSD) which is used for format-independent content adaptation within the MPEG-21 Multimedia Framework. Ultimately, this can lead to a frame-work which allows generic streaming and generic adaptation anywhere in the network.}, keywords = {Streaming, Metadata, Multimedia, MPEG-21, XML andDigital Item Adaptation.}, language = {EN}, talktype = {none} } @InProceedings{Prangl2005, author = {Prangl, Martin and Timmerer, Christian and Leopold, Klaus and Hellwagner, Hermann}, booktitle = {ELMAR, 2005. 47th International Symposium}, title = {DVB-based MPEG-21 digital items for adaptive multimedia streaming}, year = {2005}, address = {Zadar}, editor = {Grgic, M and Grgic, S and Kos, T}, month = jun, pages = {135-138}, publisher = {IEEE Xplore}, abstract = {In this paper, we present a prototype application that receives Digital Video Broadcast (DVB) TV streams on a PC, extracts semantic and syntactic metadata from the MPEG-2 Transport Stream (TS), maps them to MPEG-7 compliant descriptors, and packs these metadata and the associated multimedia content into standard compliant MPEG-21 Digital Items (DIs). In this form, i.e., as DIs, the DVB content can be searched and accessed by clients such as PCs and PDAs, and can be transported over IP networks. The DVB server can be used as a live source of multimedia content to demonstrate multimedia streaming (e.g., via RTP) and adaptation to diverse devices.}, keywords = {DVB, metadata, MPEG-7, MPEG-21, Digital Items}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/DVB-based MPEG-21 Digital Items for Adaptive Multimedia Streaming.pdf}, talktype = {none} } @InProceedings{Mueller2005, author = {Müller, Armin and Kropfberger, Michael and Böszörmenyi, Laszlo}, booktitle = {Technology-enhanced Learning with Ubiquitous Applications of Integrated Web, Digital TV and Mobile Technologies}, title = {Annotation and presentation of content-variations in a web-based search environment for video}, year = {2005}, address = {Budapest}, editor = {Simonics, Istvan}, month = jul, pages = {67-74}, publisher = {Eigenverlag}, abstract = {In recent years there has been a big increase in the amount and usage of all different kinds of multimedia data. Ranging from digital video broadcasting over the Internet to sharing digital photos and videos from the last holidays with others, multimedia is around everywhere today. Multimedia metadata help us to manage and search for information in these data. They offer searching for keywords as well as semantic search for textual descriptions of complex activities in audio, video and image. Based upon the research and implementation of the DAHL project, we present an approach for the annotation and presentation of content-variations of videos. First we want to have a look at muvino, a tool for creating MPEG-7 metadata descriptions of videos. After that the presentation of search results, especially the variations of videos or video segments is highlighted}, issn = {963311361X}, language = {EN}, talktype = {none} } @InProceedings{Kropfberger2005, author = {Kropfberger, Michael and Hellwagner, Hermann}, booktitle = {Proc. of the IEEE International Workshop on Multimedia Signal Processing}, title = {Combining Stream Switching with Fine-grained Intra-stream Adaptation for Adaptive Video Streaming}, year = {2005}, address = {Shanghai}, editor = {Zhuang, Xinhua and Sorensen, J and Wu, Qiang and Qing, Shi Y and Ostermann, J and Man, H and Goldgof, D}, month = nov, pages = {373-376}, publisher = {IEEE Computer Society}, abstract = {Video streaming systems in best effort networks have to somehow cope with dynamically changing bandwidth. Various scalable video codecs allow intra-stream adaptation by use of temporal, spatial, or quality (SNR) scalability; optimizations for finer grained scalability are available as layered coding and FGS techniques. However, if there is no scalable video stream at hand, stream switching among pre-encoded stream versions of different bitrates and qualities allows at least coarse-grained adaptation. Those different approaches compete to be the most efficient solution for adaptive video streaming. However, this paper will show that the efficacy is significantly increased by combining those approaches. As will be discussed, the combination of coarse-grained stream switching and temporal intra-stream adaptation offers better visual results and more stable client buffer behavior than the denoted approaches used separately.}, doi = {10.1109/MMSP.2005.248654}, isbn10 = {0-7803-9288-4}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Combining stream switching with fine-grained intra-stream adaptation for adaptive video streaming.pdf}, talkdate = {IEE}, talktype = {none} } @InProceedings{Kosch2005b, author = {Kosch, Harald and Döller, Mario}, booktitle = {Multimedia and Expo, 2005. ICME 2005. IEEE International Conference on}, title = {Approximating the selectivity of multimedia range queries}, year = {2005}, address = {Amsterdam}, editor = {Smeulders, A}, month = jul, pages = {382-385}, publisher = {IEEE Computer Society}, abstract = {This paper introduces a new approach of approximating the selectivity of multimedia range queries. Estimating the selectivity of a range query is a pre-requisite to optimize a multimedia database query. We use the DBSCAN clustering technique for finding high density areas in the data set. Then, the selectivity is approximated with the help of a density function in combination with the volume of the query’s hypersphere. Our approach is fast and accurate which was evaluated on an image data set using the MPEG-7 Scalable Color Descriptor. The technique is integrated with the help of the extensible optimizer architecture in the Oracle multimedia database system.}, issn = {0-7803-9331-7}, language = {EN}, talktype = {none} } @InProceedings{Kosch2005, author = {Kosch, Harald and Arrich, Alexander}, booktitle = {Kommunikation in Verteilten Systemen (KiVS) 2005}, title = {Methodik und Software zur Erstellung und Konsum von MPEG-21 Digital Items}, year = {2005}, address = {Kaiserslautern}, editor = {Mueller, P and Gotzhein, R and Schmitt, J B}, month = feb, pages = {256-270}, publisher = {Springer Verlag}, series = {Informatik aktuell}, abstract = {Im MPEG-21 Multimedia Framework Standard spielt das Digital Item als fundamentale Transaktions- und Austauscheinheit eine zentrale Rolle. Dieser Artikel beschreibt eine Methodik und Software zur Erstellung und den Konsum von Digital Items. Das Softwarewerkzeug setzt sich aus zwei Teilen zusammen: Der DI Builder erlaubt es Benutzern MPEG-21 Digital Items zu erstellen, die mit dem DI Consumer konsumiert werden können. Der Konsum eines Digital Items umfasst das Abspielen von Mediendateien und die Betrachtung der Metadaten eines Digital Items. Die Software demonstriert Teile des MPEG-21 Standards, im speziellen Teil 2-Digital Item Declaration, Teil 3-Digital Item Identifcation, Teil 5-Rights Expression Language, Teil 6-Rights Data Dictionary und Teil 7-Digital Item Adaptation.}, issn = {3-540-24473-5}, language = {DE}, talktype = {none} } @InProceedings{KoflerVogt2005, author = {Kofler Vogt, Andrea and Kosch, Harald and Heuer, Jörg}, booktitle = {Proceedings of the 6th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS 2005)}, title = {Indexing of MPEG-7 Streams}, year = {2005}, address = {Montreux}, editor = {Dufaux, F and Ebrahimi, T and Strintzis, M}, month = apr, pages = {00}, publisher = {IEEE}, abstract = {The ISO/IEC Motion Picture Group (MPEG) issued in 2002 a standard, called MPEG-7, which enables the content description of multimedia data in XML. The standard supports applications to exchange, identify and filter multimedia contents based on MPEG-7 descriptions. However, processing MPEG-7 documents on mobile terminals is problematic, since the verbose XML is not adequate to limited bandwidth, low computational power and limited battery life. In this document we describe an index system that allows filtering and random access to encoded MPEG-7 streams and which overcomes the limitation of the network and the consuming terminal. Encoding is applied in order to reduce the data rate of the XML documents to be transmitted. The indexed parts of the encoded streams can be accessed without the need to deserialize the complete stream. Furthermore, the system is evaluated and results of the experimental evaluation are discussed.}, language = {EN}, location = {Montreux, Switzerland}, talkdate = {2005.04.14}, talktype = {none} } @InProceedings{Kettner2005, author = {Kettner, Cartsten and Kosch, Harald and Lang, Margit and Lachner, Janine and Oborny, Doris and Teppan, Erich}, booktitle = {Database Theory - ICDT 2005}, title = {Creating a Medicinal Plant Database}, year = {2005}, address = {Edinburgh}, editor = {Eiter, T and Libkin, L}, month = {jan}, pages = {413}, publisher = {Springer Verlag}, series = {LNCS}, abstract = {This paper presents the experiences of creating the information system MEDPHYT which is built to collect data on the complete European pharmaceutical and toxicological plant world whose representatives are determined by medical and therapeutic benefit. Focus of the database content is the plant with description of their botanical characteristics, and history of discovery of therapeutic use, etymology, and synonyms. Apart the botanical characterisation there is information on both medical relevant biochemical compounds and their physicochemical characteristics, and toxicological as well as pharmaceutical facts. These data sets determine the basic system of MEDPHYT.}, issn = {3-540-24288-0}, language = {EN}, talktype = {none} } @InProceedings{Karpati2005a, author = {Karpati, Peter and Kocsor, Andras and Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 9th IASTED International Conference on Internet and Multimedia Systems and Applications (EuroIMSA 2005)}, title = {Client Behaviour Prediction in a Proactive Video Server}, year = {2005}, address = {Grindelwald}, editor = {Hamza, MH}, month = feb, pages = {492-497}, publisher = {ACTA Press}, abstract = {We present a possibility how to add proactive behaviour to Video-on-Demand systems. To do so we propose categorizing videos and using external information as well as observing the behaviour of our clients. We examined 23 predictor functions on artificial and real datasets using different similarity measures to compare them. Our model is quite simple; therefore some extensions are proposed at the end.}, language = {EN}, talktype = {none} } @InProceedings{Hutter2005, author = {Hutter, Andreas and Amon, Peter and Panis, Gabriel and Delfosse, Eric and Ransburg, Michael and Hellwagner, Hermann}, booktitle = {Image Processing, 2005. ICIP 2005. IEEE International Conference on}, title = {Automatic Adaptation of Streaming Multimedia Content in a Dynamic and Distributed Environment}, year = {2005}, address = {Genova, Italy}, editor = {IEEE,}, month = sep, pages = {716-719}, publisher = {IEEE Computer Society}, abstract = {The diversity of end-terminal and access network capabilities as well as the dynamic nature of wireless connections pose significant challenges to providers of multimedia streaming services. In this paper, we present a system based on MPEG-21 Digital Item Adaptation (DIA) technologies that automatically adapts scalable multimedia resources, like upcoming MPEG-21 Scalable Video Coding (SVC) streams, in a generic and transparent way to the user and session context. This context includes terminal and network capabilities as well as user characteristics. A server side adaptation engine reacts to context changes by dynamic decision taking and accordingly modified bitstream adaptation. Furthermore, novel concepts are presented that facilitate multimedia adaptation in a distributed fashion along the delivery path.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Automatic Adaptation of streaming multimedia content in a dynamic and distributed environment.pdf}, talktype = {none} } @InProceedings{DeSutter2005, author = {De Sutter, Robbie and Timmerer, Christian and Hellwagner, Hermann and Van de Walle, Rik}, booktitle = {Proceedings of IASTED International Conference on Internet and Multimedia Systems and Applications (EuroIMSA 2005)}, title = {Multimedia Metadata Processing: A Format Independent Approach}, year = {2005}, address = {Zürich, Schweiz}, editor = {Hamza, M H}, month = {jan}, pages = {343-348}, publisher = {ACTA Press}, abstract = {In multimedia applications, XML is being increasingly used to represent metadata; examples are MPEG-7 multimedia description schemes and MPEG-21 usage environment descriptions. As with the media data, the size of, or the overhead induced by, the XML metadata is important, particularly when used on constrained mobile devices. Therefore, compression (binary encoding) of the XML data becomes relevant to reduce this overhead. Within the MPEG-7 standardization effort, a Binary Format for Metadata (BiM) was developed, ´providing good compression efficiency and facilitating random access into, and manipulation of, the binary encoded bit stream. However, using binary encoded XML should not introduce interoperability issues with existing applications, nor add additional complexity to new applications. In this paper we investigate a solution for this issue by handling the binary encoded XML data by the XML parser. As such, applications do not need to be aware of the type of encoding of the XML data. In this paper, we introduce such an XML parser and evaluate its usability in different scenarios. We measure the memory requirements and compare the processing speed of parsing binary encoded XML to plain text XML.}, issn = {14827905}, keywords = {Multimedia Information Systems, Multimedia Communication Systems, Multimedia Metadata, Binary Encoded XML, MPEG-7 BiM}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Multimedia Metadata Processing.pdf}, talktype = {none} } @InProceedings{Boeszoermenyi2005, author = {Böszörmenyi, Laszlo}, booktitle = {From Computer Literacy to Informatics Fundamentals}, title = {Teaching: People to People – About People (A plea for the historic and human view)}, year = {2005}, address = {Heidelberg, Germany}, editor = {Mittermeir, Roland}, month = feb, pages = {93-103}, publisher = {Springer Verlag}, series = {LNCS}, abstract = {The importance of the historical and human aspects of the didactics of informatics is discussed. The threefold human aspects of teaching: by, for and about people is explored. Using the example of the notion of the procedure, the potential of the historical discussion is investigated. A strengthening of the historical and human view is required both in university research and in the curricula of the informatics education at both secondary and university levels.}, issn = {978-3-540-253}, language = {EN}, talktype = {none} } @InProceedings{Timmerer2004, author = {Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Informatik 2004 : Informatik verbindet; Band 2, Beiträge der 34. Jahrestagung der Gesellschaft für Informatik e.V. (GI), Ulm, 20.-24. September 2004}, title = {Interoperable multimediale Kommunikation im Internet mittels MPEG-21 Digital Item Adaptation}, year = {2004}, address = {Bonn}, editor = {Dadam, Peter and Reichert, Manfred}, month = {jan}, pages = {301-305}, publisher = {Gesellschaft für Informatik}, series = {Lecture Notes in Informatics, Proceedings}, abstract = {Digital Item Adaptation (DIA) ist der jüngste Standard im Rahmen des ISO/IEC MPEG-21 Multimedia Frameworks. Dieser Standard spezifiziert Deskriptoren und Konzepte (Tools) für die interoperable Kommunikation und ggf. Adaption von komplexen digitalen multimedialen Objekten, sog. Digital Items. Schwierigkeiten der Kommunikation und ggf. die Notwendigkeit der Adaption multimedialer Inhalte entstehen durch die Heterogenität und Beschränkungen der durchlaufenen Netzwerke (z.B. im heutigen Internet) und der benutzten Endgeräte sowie durch unterschiedliche Präferenzen und Profile der Nutzer. Dieser Artikel beschreibt eine endgeräte- und codierformat-unabhängige Komponente zur Adaption von Digital Items an verschiedene mobile Endgeräte und Netzcharakteristika.}, isbn10 = {3885793792}, isbn13 = {978-3885793793}, issn = {3-88579-380-6}, language = {DE}, pdf = {https://www.itec.aau.at/bib/files/Interoperable multimediale Kommunikation im Internet.pdf}, talktype = {none} } @InProceedings{Szkaliczki2004, author = {Szkaliczki, Tibor and Böszörmenyi, Laszlo}, booktitle = {Distributed and Parallel Systems: Cluster and Grid Computing (DAPSYS 2004, Austrian-Hungarian Workshop on Distributed and Parallel Systems, Budapest, Hungary September 19-22, 2004)}, title = {Incremental Placement of Nodes in a Large-Scale Adaptive Distributed Multimedia Server}, year = {2004}, address = {New York [u. a.]}, editor = {Zoltan, Juhasz and Kacsuk, Peter and Kranzlmüller, Dieter}, month = {jan}, pages = {165-172}, publisher = {Springer}, series = {Kluwer International Series in Engineering and Computer Science}, issn = {0-387-23094-7}, language = {EN}, talktype = {none} } @InProceedings{Libsie2004, author = {Libsie, Mulugeta and Kosch, Harald}, booktitle = {Multimedia Signal Processing, 2004 IEEE 6th Workshop on}, title = {Video Adaptation Using The Variation Factory}, year = {2004}, address = {Washington}, editor = {n, A}, month = sep, pages = {403-406}, publisher = {IEEE}, abstract = {Video adaptation is an active research area aiming at delivering heterogeneous content to yet heterogeneous devices under different network conditions. This paper presents an architecture for generating variations (different versions) from methods such as video transcoding, media conversion and summarization. The work in this paper concentrates on video data and aims to show video variation supported with metadata as an approach to adaptation to enable ubiquitous access. By video products are defined and the variation factory is introduced It generates different versions of the source and an MPEG-7 metadata document. The information contained in the metadata document helps the system to identify the most appropriate version that meets the required quality of service (QoS). In addition to the implementation of the commonly used reduction methods, two novel methods, viz. object-based and segment-based variations are introduced. Our proposals are implemented and experimentally validated.}, doi = {10.1109/MMSP.2004.1436578}, isbn10 = {0-7803-8578-0}, language = {EN}, talktype = {none} } @InProceedings{Leopold2004a, author = {Leopold, Klaus and Jannach, Dietmar and Hellwagner, Hermann}, booktitle = {Multimedia Software Engineering}, title = {A Knowledge and Component Based Multimedia Adaptation Framework}, year = {2004}, address = {Los Alamitos, USA}, editor = {Werner, Bob}, month = dec, pages = {1-8}, publisher = {IEEE Computer Society}, abstract = {The rapid evolution in the hardware sector brought up various (mobile) end user devices like PDAs or cell phones on which online multimedia content can be consumed. Due to different capabilities of these devices as well as individual user preferences, the original multimedia resources have to be adapted in order to fit the specific devices’ constraints and to meet the users’ requirements. Given the high variety of possible adaptation operations both on the format as well as the content level, an intelligent multimedia server must be able to integrate multiple existing and specialized adaptation tools. In this paper, we demonstrate how the usage of modular software components and declarative descriptions of component behavior enables us to develop extensible multimedia adaptation systems. The precise semantics of the utilized functionality description mechanism as well as the defined vocabulary from existing and emerging multimedia standards also allows us to automatically assemble adaptation chains that are executed on a given resource involving multiple, externally provided software components.}, issn = {0-7695-2217-3}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/A Knowledge and Component Based Multimedia Adaptation Framework.pdf}, talktype = {none} } @InProceedings{Leopold2004, author = {Leopold, Klaus and Jannach, Dietmar and Hellwagner, Hermann}, booktitle = {Proceedings of SPIE, Internet Multimedia Mangement Systems V}, title = {Knowledge-based media adaptation}, year = {2004}, address = {Bellingham, WA}, editor = {Smith, John R and Zhang, Tong and Panchanathan, Sethuraman}, month = oct, pages = {111-120}, publisher = {SPIE- The International Society for Optical Engineering}, series = {SPIE Proceedings Series}, abstract = {This paper introduces the principal approach and describes the basic architecture and current implementation of the knowledge-based multimedia adaptation framework we are currently developing. The framework can be used in Universal Multimedia Access scenarios, where multimedia content has to be adapted to specific usage environment parameters (network and client device capabilities, user preferences). Using knowledge-based techniques (state-space planning), the framework automatically computes an adaptation plan, i.e., a sequence of media conversion operations, to transform the multimedia resources to meet the client's requirements or constraints. The system takes as input standards-compliant descriptions of the content (using MPEG-7 metadata) and of the target usage environment (using MPEG-21 Digital Item Adaptation metadata) to derive start and goal states for the planning process, respectively. Furthermore, declarative descriptions of the conversion operations (such as available via software library functions) enable existing adaptation algorithms to be invoked without requiring programming effort. A running example in the paper illustrates the descriptors and techniques employed by the knowledge-based media adaptation system.}, doi = {10.1117/12.577420}, edition = {Volume 5601}, isbn13 = {9780819455543}, issn = {0277-786X}, language = {EN}, talktype = {none} } @InProceedings{Kropfberger2004a, author = {Kropfberger, Michael and Hellwagner, Hermann}, booktitle = {Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on}, title = {Evaluation of RTP immediate feedback and retransmission extensions}, year = {2004}, address = {kA}, editor = {IEEE,}, month = jun, pages = {1751-1754}, publisher = {IEEE Xplore}, abstract = {Modern video streaming servers should adapt, and switch quality levels of, the streamed data according to precise and timely feedback about the network conditions, and should also incorporate selective retransmissions of important reference frames (I- and P-VOPs). This paper evaluates two recent IETF Internet Drafts on RTP extensions for immediate feedback and retransmission and shows, in conjunction with temporal video adaptation, how a substantial visual quality gain can be achieved by using those extensions (up to 4.4 dB PSNR under lossy conditions).}, doi = {10.1109/ICME.2004.1394593}, edition = {Vol. 3}, isbn10 = {0-7803-8603-5}, issn = {0-7803-8604-3}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Evaluation of RTP immediate feedback and retransmission extensions.pdf}, talktype = {none}, url = {http://www.icme2004.org} } @InProceedings{Kropfberger2004, author = {Kropfberger, Michael and Leopold, Klaus and Hellwagner, Hermann}, booktitle = {Multimedia Signal Processing, 2004 IEEE 6th Workshop on}, title = {Quality variations of different priority-based temporal video adaptation algorithms}, year = {2004}, address = {kA}, editor = {IEEE,}, month = {jan}, pages = {183-186}, publisher = {IEEE Xplore}, abstract = {If videos are streamed over heterogeneous networks like the Internet, severe bandwidth fluctuations can emerge which hamper seamless transmission to the end user. To overcome this issue, a video's quality and, as a consequence, its bandwidth requirements can be reduced. Quality reduction in the temporal domain (i.e., frame dropping) turned out to be a promising approach because it is fast and easy to perform. In this paper, we present different approaches for temporal video adaptation and we investigate their performance in terms of the achieved visual quality when applied on several videos. The results show that our QCTVA approach (quality controlled temporal video adaptation), based on PSNR evaluation of frames, yields superior quality.}, doi = {10.1109/MMSP.2004.1436384}, isbn10 = {0-7803-8578-0}, issn = {0-7803-8578-0}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Quality Variations of Different Priority-based Temporal Video Adaptation Algorithms.pdf}, talktype = {none} } @InProceedings{Jannach2004b, author = {Jannach, Dietmar and Leopold, Klaus and Timmerer, Christian and Hellwagner, Hermann}, booktitle = {Web Information Systems - WISE 2004}, title = {Toward Semantic Web Services for Multimedia Adaptation}, year = {2004}, address = {Berlin, Heidelberg, New York}, editor = {Zhou, Xiaofang and Su, Stanley and Papazoglou, Mike and Orlowska, Maria and Jeffery, Keith}, month = nov, pages = {641-652}, publisher = {Springer}, series = {LNCS}, abstract = {Abstract. Universal Multimedia Access (UMA), where users can consume any multimedia resource anywhere at any time, is the driving vision of ongoing ISO/IEC Moving Picture Experts Group (MPEG) standardization efforts. In that context, intelligent adaptation means that before resources are sent over the network, they are prepared according to the client’s device capabilities, the network conditions, or even the user’s content preferences. In this paper, we argue that Semantic Web Services can serve as a key enabling technology to achieve the goals of UMA. As the standards evolve, more and more specialized software tools will be available that provide specific functionalities for adapting the media in different dimensions. When the functionality of such tools is described declaratively with the means of Semantic Web Services technology, intelligent adaptation network nodes can be developed, capable of automatically composing multi-step adaptation sequences and dynamically integrating such services available on the Web. This paper describes the architecture and a prototypical implementation of an intelligent adaptation node that supports automatic, knowledge-based service composition which is made possible by the shared domain ontology defined in MPEG metadata standards.}, doi = {10.1007/978-3-540-30480-7_66}, issn = {0302-9743}, language = {EN}, talktype = {none} } @InProceedings{Jannach2004a, author = {Jannach, Dietmar and Leopold, Klaus and Hellwagner, Hermann}, booktitle = {Proceedings of the 17th International Conference on Industrial \& Engineering Applications of Artificial Intelligence \& Expert Systems}, title = {An extensible framework for knowledge-based multimedia adaptation}, year = {2004}, address = {Berlin [u. a.]}, editor = {Orchard, Robert and Yang, Chunsheng and Moonis, Ali}, month = may, pages = {144-153}, publisher = {Springer Verlag}, series = {LNCS}, abstract = {Multimedia content is becoming increasingly important in many areas not only for pure entertainment but also for commercial or educational purposes like, e.g., distance learning or online training. In parallel, the rapid evolution in the hardware sector brought up various new (mobile) end user devices like pocket PCs or mobile phones that are capable of displaying such content. Due to the different capabilities and usage environments of these devices, the basic multimedia content has to be adapted in order to fit the specific devices' capabilities and requirements, whereby such transformations typically include changes in the display size or quality adaptation. Based on the capabilities of the target device that can be expressed using recent multimedia standards like MPEG-21, these adaptation steps are typically carried out by the video server or a proxy node before the data is transferred to the client. In this paper, we present a software framework and implementation of such a multimedia server add-on that advances state-of-the-art technology in two ways. First, the framework supports the integration of various (already existing) multimedia transformation tools based on declarative interface and semantic capability descriptions in a way comparable to Semantic Web Services approaches. Second, by using the components' capability descriptions and the usage environment of the end user device, we employ a knowledge-based planning approach for dynamically constructing and executing the needed transformation program for a specific multi-media content request.}, issn = {3-5402-2007-0}, language = {EN}, talktype = {none} } @InProceedings{Jannach2004, author = {Jannach, Dietmar and Leopold, Klaus and Hellwagner, Hermann and Timmerer, Christian}, booktitle = {Proceedings of the 5th International Workshop on Image Analysis for Multimedia Interactive Services}, title = {A Knowledge Based Approach for Multi-step Media Adaptation}, year = {2004}, address = {Lisboa, Portugal}, editor = {Pereira, Fernando and Correia, Paulo Lobato}, month = apr, pages = {1-4}, publisher = {Instituto Superior Téchnico}, abstract = {In order to enable transparent and augmented use of multimedia resources across a wide range of networks and devices, the forthcoming MPEG-21 standard aims at integrating the various existing technologies for delivery and consumption of digital content in a common multimedia framework. Digital Item Adaptation is one of the core concepts of the framework that will support the adaptation of multimedia resources to device capabilities, underlying network characteristics, or the user’s preferences. The scope of the standardization, however, is limited to the definition of description tools and does not deal with the internals of the adaptation process itself. In this paper, we first discuss the requirements of the resource adaptation component of an adaptation engine. These requirements include, for instance, openness for the integration of external multimedia transforming tools as well as intelligent decision taking when determining the set of required adaptation steps. We also present a prototype of a simple video resource adaptation engine that completely relies on descriptions of the resource itself (MPEG-7), the usage environment of the resource (MPEG-21), as well as declarative descriptions of the transformation tools. The prototype employs a knowledge-based engine for finding and executing the needed adaptation sequences.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/A knowledge supported approach for multi-step media adaptation.pdf}, talktype = {none} } @InProceedings{Goldschmidt2004, author = {Goldschmidt, Balázs and Skaliczki, Tibnor and Böszörmenyi, Laszlo}, booktitle = {Eur-Par 2004, Parallel Processing}, title = {Placement of Nodes in an Adaptive Distributed Multimedia Server}, year = {2004}, address = {Pisa, Italy}, editor = {Danelutto, M and Laforenza, D and Vanneschi, M}, month = {jan}, pages = {776-783}, publisher = {Springer}, series = {LNCS}, abstract = {Multimedia services typically need not only huge resources but also a fairly stable level of Quality of Services. This requires server architectures that enable continuous adaptation. The Adaptive Distributed Multimedia Server (ADMS) of the University Klagenfurt is able to dynamically add and remove nodes to the actual configuration, thus realizing the offensive adaptation approach. This paper focuses on the optimal placement of nodes for hosting certain ADMS components (the so-called data collectors, collecting and streaming stripe units of a video) in the network. We propose four different algorithms for host recommendation and compare the results gained by running their implementations on different test networks. The greedy algorithm seems to be a clear looser. Among the three other algorithms (particle swarm, linear programming and incremental) there is no single winner of the comparison, they can be applied in a smart combination.}, issn = {0302-9743}, language = {EN}, talktype = {none} } @InProceedings{DeSutter2004, author = {De Sutter, Robbie and Timmerer, Christian and Hellwagner, Hermann and Van de Walle, Rik}, booktitle = {Proceedings of the International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS2004)}, title = {Evaluation of Models for Parsing Binary Encoded XML-based Metadata}, year = {2004}, address = {Piscataway, USA}, editor = {Ko, Sung Jea}, month = nov, pages = {1-6}, publisher = {IEEE}, abstract = {In multimedia applications, XML is being increasingly used to represent metadata; examples are MPEG-7 multimedia description schemes and MPEG-21 usage environment descriptions. As with the media data, the size of, or the overhead induced by, the XML metadata is important, particularly when used on constrained mobile devices. Therefore, compression (binary encoding) of the XML data becomes relevant to reduce this overhead. Within the MPEG-7 standardization effort, a Binary Format for Metadata (BiM) was developed, providing good compression efficiency and facilitating random access into, and manipulation of, the binary encoded bit stream. In order to support processing of metadata streams in the binary domain and making this task for client applications as simple as possible, we are developing a universal parser for handling both plain text and binary encoded XML-based metadata. The parser exposes a single interface making it transparent for the application whether a plain text or a binary XML document is being processed. As part of this effort, this paper provides a detailed study of five existing XML parser models and evaluates their applicability to serve as a model for parsing binary XML data, encoded using the BiM codec. Additionally, the parser models are investigated against important usage scenarios enabled by BiM, such as dynamic updates of XML data. From the five models, two are rejected and one is only applicable for domain specific applications. Of the remaining two, one model is proposed as preferred model because of different advantages over the other model.}, isbn10 = {0780386396}, isbn13 = {978-0780386396}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Evaluation of Models for Parsing Binary Encoded XML-based Metadata.pdf}, talktype = {none} } @InProceedings{Tusch2003b, author = {Tusch, Roland and Böszörmenyi, Laszlo and Goldschmidt, Balázs and Hellwagner, Hermann and Schojer, Peter}, booktitle = {Proceedings of ICETA 2003, 2nd International Conference on Emerging Telecommunications Technologies and Applications}, title = {Offensive and Defensive Adaptation in Distributed Multimedia Systems}, year = {2003}, address = {Košice, Slovak Republic}, editor = {Jakab, F and Cizmar, A}, month = sep, pages = {17-19}, publisher = {Elfa}, abstract = {Adaptation is usually restricted to defensive, reactive media adaptation (often called stream-level adaptation). We argue that offensive, proactive, system-level adaptation deserves not less attention. If a distributed multimedia system cares for overall, end-to-end quality of service then it should provide a meaningful combination of both. We introduce an adaptive multimedia server (ADMS) and a supporting middleware which implement offensive adaptation based on a lean, flexible architecture. The measured costs and benefits of the offensive adaptation process are presented. We introduce an intelligent video proxy (QBIX), which implements defensive adaptation. The cost/benefit measurements of QBIX are presented elsewhere~\citeSchojer03. We show the benefits of the integration of QBIX in ADMS. Offensive adaptation is used to find an optimal, user-friendly configuration dynamically for ADMS, and defensive adaptation is added to take usage environment (network and terminal) constraints into account.}, isbn10 = {8089066674}, issn = {80-89066-06-2}, language = {EN}, talktype = {none} } @InProceedings{Tusch2003a, author = {Tusch, Roland}, booktitle = {Modular Programming Languages. Joint Modular Languages Conference, JMLC 2003, Klagenfurt, Austria, August 25-27, 2003, Proceedings}, title = {Towards an Adaptive Distributed Multimedia Streaming Server Architecture Based on Service-oriented Components}, year = {2003}, address = {Berlin, Heidelberg, New York}, editor = {Schojer, Peter and Böszörmenyi, Laszlo}, month = aug, pages = {78-87}, publisher = {Springer}, abstract = {Abstract. This paper presents an adaptive distributed multimedia streaming server architecture (ADMS) which explicitly controls the serverlayout. It consists of four types of streaming server components, which all provide dedicated services in an arbitrary number of instances on an arbitrary number of server hosts. Vagabond2 is used as the underlying middleware for component adaptation. It is shown, how the CORBA-based components have to be declared in order to run on top of Vagabond2. Finally, inter-component dependencies are pointed out, which have to be taken into account during component adaptations.}, issn = {0302-9743}, language = {EN}, talktype = {none}, url = {http://jmlc-itec.uni-klu.ac.at/} } @InProceedings{Tusch2003, author = {Tusch, Roland and Spielvogel, Christian and Kröpfl, Michael and Böszörmenyi, Laszlo}, booktitle = {Proceedings of Information Technologies and Communications (ITCom), Internet Multimedia Management Systems IV, Orlando, USA}, title = {An Adaptive Distributed Multimedia Streaming Server in Internet Settings}, year = {2003}, address = {Orlando}, editor = {Panchanathan, S and Zhang, T and Smith, JR}, month = {jan}, pages = {312-323}, publisher = {SPIE}, abstract = {We present an adaptive distributed multimedia server architecture (ADMS) that builds upon the idea of offensive adaptivity, where the server proactively controls its layout through replication or migration of server components to recommended hosts. Proactive actions are taken when network or server resources become critical when fulfilling client demands. Recommendations are provided by a so-called “host recommender” which represents an integral part of Vagabond2 - the middleware used for component distribution. Recommendations are based on measured or estimated server and network resource availabilities. Network distance and host resource metrics - obtained from network and host resource services respectively - may be communicated as MPEG-21 DIA descriptors. Finally we evaluate our architecture in a real-world streaming scenario.}, language = {EN}, talktype = {none}, url = {http://spie.org/conferences/programs/03/it/index.cfm?fuseaction=proceedings} } @InProceedings{Timmerer2003, author = {Timmerer, Christian and Panis, Gabriel and Kosch, Harald and Heuer, Jörg and Hellwagner, Hermann and Hutter, Andreas}, booktitle = {Proceedings of SPIE International Symposium ITCom 2003 on Internet Multimedia Managment Systems IV, Vol. 5242}, title = {Coding format independent multimedia content adaptation using XML}, year = {2003}, address = {Orlando}, editor = {N,A}, month = {jan}, pages = {92-103}, publisher = {SPIE Press}, abstract = {Due to the heterogeneity of the current terminal and network infrastructures, multimedia content needs to be adapted to specific capabilities of these terminals and network devices. Furthermore, user preferences and user environment characteristics must also be taken into consideration. The problem becomes even more complex by the diversity of multimedia content types and encoding formats. In order to meet this heterogeneity and to be applicable to different coding formats, the adaptation must be performed in a generic and interoperable way. As a response to this problem and in the context of MPEG-21, we present an approach which uses XML to describe the high-level structure of a multimedia resource in a generic way, i.e., how the multimedia content is organized, for instance in layers, frames, or scenes. For this purpose, a schema for XML-based bitstream syntax descriptions (generic Bitstream Syntax Descriptions or gBSDs) has been developed. A gBSD can describe the high-level structure of a multimedia resource in a coding format independent way. Adaptation of the resource is based on elementary transformation instructions formulated with respect to the gBSDs. These instructions have been separated from the gBSDs in order to use the same descriptions for different adaptations, e.g., temporal scaling, SNR scaling, or semantic adaptations. In the MPEG-21 framework, those adaptations can be steered for instance by the network characteristics and the user preferences. As a result, it becomes possible for coding format agnostic adaptation engines to transform media bitstreams and associated descriptions to meet the requirements imposed by the network conditions, device capabilities, and user preferences.}, isbn10 = {0819451401}, isbn13 = {978-0819451408}, keywords = {Multimedia, Adaptation, Interoperability, XML, MPEG-21, Digital Item Adaptation}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Coding format independent multimedia content adaptation.pdf}, talktype = {none} } @InProceedings{Schojer2003, author = {Schojer, Peter and Böszörmenyi, Laszlo and Hellwagner, Hermann and Penz, Bernhard and Podlipnig, Stefan}, booktitle = {The Twelfth International World Wide Web Conference}, title = {Architecture of a Quality Based Intelligent Proxy (QBIX) for MPEG-4 Videos}, year = {2003}, address = {New York, USA}, editor = {Hencsey, Gusztáv and White, Bebo}, month = {jan}, pages = {394-402}, publisher = {ACM}, abstract = {Due to the increasing availability and use of digital video data on the Web, video caching will be an important performance factor in the future WWW. We propose an architecture of a video proxy cache that integrates modern multimedia and communication standards. Especially we describe features of the MPEG-4 and MPEG-7 multimedia standards that can be helpful for a video proxy cache. QBIX supports real-time adaptation in the compressed and in the decompressed domain. It uses adaptation to improve the cache replacement strategies in the proxy, but also to realize media gateway functionality driven by the clients' terminal capabilities.}, issn = {1-58113-680-3}, language = {EN}, talktype = {none}, url = {http://www.2003.org} } @InProceedings{Ohlenroth2003, author = {Ohlenroth, Mathias and Hellwagner, Hermann}, booktitle = {ICME 2003 Proceedings CD-Rom}, title = {A Protocol for Adaptation-aware Multimedia Streaming}, year = {2003}, address = {NA}, editor = {Mercer, Billene and Cantu, St and Garza, Ch and Stewart, B}, month = jul, pages = {1-4}, publisher = {NA}, abstract = {Multimedia streaming is becoming ever more popular. However, the Internet does not support streaming with its high bandwidth and low latency requirements very well. The problem is that QoS guarantees cannot be given. Hence, communication partners have to deal with rapidly changing connection parameters. This requires sophisticated streaming concepts that can handle these varying conditions using adaptation techniques. Adaptation methods can be dropping layers, dropping access units or transcoding the contents. But this places specific requirements on the underlying protocol. This paper identifies and discusses these requirements and analyzes how existing protocols can meet them. Unfortunately, none of the known protocols can meet all requirements. Hence, we propose a new adaptation-aware multimedia streaming protocol that can operate as required in the given Internet environment. Furthermore, we show how this protocol can be used to carry MPEG-4 audio-visual contents.}, issn = {0-7803-7966-7}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/A protocol for adaptation-aware multimedia streaming.pdf}, talktype = {none} } @InProceedings{Leopold2003, author = {Leopold, Klaus and Hellwagner, Hermann and Kropfberger, Michael}, booktitle = {Proc. of SPIE}, title = {QCTVA - Quality Controlled Temporal Video Adaptation}, year = {2003}, address = {NA}, editor = {N,A}, month = sep, pages = {163-174}, publisher = {NA}, abstract = {Multimedia streaming is becoming more and more popular. Seamless video streaming in heterogeneous networks like the Internet turns out as almost impossible due to varying network conditions - streams must be adapted to the current network QoS. Temporal scalability is one of the most reasonable adaptation techniques because it is fast and easy to perform. Today's approaches simply drop frames out of a video without spending much effort on finding an intelligent dropping behavior. This usually leads to good adaptation results in terms of bandwidth consumption but also to suboptimal video quality within the given bounds. Our approach offers analysis of video streams to achieve the qualitatively best temporal scalability. For this reason, we introduce a data structure called modification lattice which represents all frame dropping combinations within a sequence of frames. On the basis of the modification lattice, qualityestimations on frame sequences can be performed. Moreover, a heuristic for fast and efficient quality computation in a modification lattice is presented. Experimental results illustrate that temporal video adaptation based on QCTVA information leads to a better video quality compared to "usual" frame dropping approaches. Furthermore, QCTVA offers frame priority lists for videos. Based on these priorities, numerous adaptation techniques can increase their overall performance when using QCTVA.}, edition = {Vol. 5242}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/QCTVA.pdf}, talktype = {none} } @InProceedings{Doeller2003, author = {Döller, Mario and Kosch, Harald}, booktitle = {SPIE Conference on Multimedia Computing and Networking 2003 (MMCN03), Santa Clara, CA, January 29-31, 2003}, title = {An MPEG-7 Multimedia Data Cartridge}, year = {2003}, address = {Santa Clara, USA}, editor = {Rajkumar, Ragunathan}, month = jan, pages = {240}, publisher = {SPIE}, series = {Electronic Imaging Science and Technology}, abstract = {Broadly used Database Management Systems (DBMS) are not able to tackle the requirements of multimedia in querying, indexing and content modeling. Therefore, extenders for multimedia data types have been proposed. These extensions, however, offer only limited semantic modeling and rely on basic index structures which do not meet the whole nature of multimedia, for instance for a Nearest-Neighbor Search. In this context, the paper presents a methodology for enhancing extensible ORDBMS for multimedia data. In particular, we introduce an MPEG-7 Multimedia Data Cartridge which includes a semantically rich metadata model for multimedia content relying on the MPEG-7 standard. Furthermore, to fulfill the needs for efficient multimedia query processing, we created in this Cartridge a new indexing and query framework for various types of retrieval operations}, isbn10 = {9780819448194}, issn = {0-89298-244-5}, language = {EN}, talktype = {none}, url = {http://www.fim.uni-passau.de/fileadmin/files/lehrstuhl/kosch/Papers/2003/2003-0257-HKAM.pdf} } @InProceedings{Boeszoermenyi2003a, author = {Böszörmenyi, Laszlo and Tusch, Roland}, booktitle = {Suchbilder. Visuelle Kultur zwischen Algorithmen und Archiven}, title = {Inhaltsbasierte Suche in Videoarchiven}, year = {2003}, address = {Berlin}, editor = {Heidenreich, Ernst}, month = {jan}, pages = {67-75}, publisher = {Kulturverlag Kadmos}, abstract = {Bei der Indizierung von Videoarchiven haben im allgemeinen bessere Ergebnisse einen höheren Preis. Automatische Indizierung, basierend auf physikalischen Eigenschaften, kann für viele Bereiche (wie z.B. ein Grossteil der Unterhaltung) ausreichend gute Ergebnisse erzielen. Sie ist allerdings in der Genauigkeit der Fragestellungen eingeschränkt, und zwingt uns – oft unbewusste – Suchkriterien auf. Wenn es uns wichtig ist, auf fein differenzierte Fragen genaue Antworten zu erhalten (wie das z.B. in wissenschaftlich/technischen Systemen meistens der Fall ist), so sind wir auf eine zumindest teilweise manuelle Annotierung angewiesen. In einem kombinierten System – wie dem VIDEX-Modell – können die physikalischen Eigenschaften dazu benutzt werden, den manuellen Annotierungsprozess zu erleichtern. Kombinierte Systeme dieser Art bieten beide Arten der Indizierung an und kombinieren sie miteinander. Längerfristig ist zu erwarten, dass sich zu jeder Anwendung die angemessenen Indizierungs- und Suchmethoden herausstellen. Die zwei Verfahren – das automatische und das teils manuelle – sollten nicht als Gegner, sondern als Partner angesehen werden.}, issn = {3-931659-35-6}, language = {DE}, talktype = {none} } @InProceedings{Schojer2002, author = {Schojer, Peter and Böszörmenyi, Laszlo and Hellwagner, Hermann}, booktitle = {Distributed and parallel systems: cluster and grid computing. Proceedings of International Conference on Distributed and Parallel Systems (DAPSYS 02), Linz, Austria.}, title = {An Adaptive MPEG-4 Proxy Cache}, year = {2002}, address = {Boston [u. a.]}, editor = {Kascuk, Péter and Kranzlmüller, Dieter and Németh, Zsolt and Volkert, Jens}, month = aug, pages = {149-156}, publisher = {Kluwer Academic Publishers}, series = {The Kluwer international series in engineering and computer science}, abstract = {Multimedia is gaining ever more importance on the Internet. This increases the need for intelligent and efficient video caches. Typical Web proxies were not designed to efficiently support the caching of videos. A promising approach to improve caching efficiency is to adapt videos. With the availability of MPEG-4 it is possible to develop a standard compliant proxy that allows fast and efficient adaptation. We propose a modular design for an adaptive MPEG-4 video proxy that supports efficient full and partial video caching in combination with filtering options that are driven by the terminal capabilities of the client. We use the native scalability operations provided by MPEG-4 and use the emerging MPEG-7 standard to describe the scalability options for a video. The proxy parses the MPEG-7 description and decides, based on this description and the terminal capabilities of the client, which adaptation step to choose. Simple MPEG-4 audio-visual streams are supported by filter operations in the compressed domain that realize several temporal scaling algorithms and color reduction. In this paper, we will restrict ourselves to full video caching. The combination of adaptation with MPEG-4, MPEG-7 and client terminal capabilities is to the best of our knowledge unique and will increase the quality of service for end users.}, issn = {1-4020-7209-0}, keywords = {adaptation, MPEG-4, MPEG-7, adaptive proxy, caching}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/An Adaptive MPEG-4 Proxy Cache.pdf}, talktype = {none} } @InProceedings{Podlipnig2002, author = {Podlipnig, Stefan and Böszörmenyi, Laszlo}, booktitle = {IEEE International Conference on Multimedia and Expo (ICME)}, title = {Replacement Strategies for Quality Based Video Caching}, year = {2002}, address = {Lausanne, Schweiz}, editor = {Swiss, Federal Institute of Technology}, month = aug, pages = {5}, publisher = {IEEE}, abstract = {Due to the future dominance of video data video caching will be an important performance factor in future networked multimedia systems. A major component of video caches is the replacement strategy. This paper presents replacement strategies for video caches that incorporate quality reduction and the use of metadata given by the content provider. The strategies are evaluated by simulation.}, issn = {0780373049}, language = {EN}, talktype = {none} } @InProceedings{Ohlenroth2002, author = {Ohlenroth, Matthias and Hellwagner, Hermann}, booktitle = {ICME Proceedings}, title = {RTP Packetization of MPEG-4 Elementary Streams}, year = {2002}, address = {NA}, editor = {IEEE,}, month = mar, pages = {1-4}, publisher = {IEEE Xplore}, abstract = {Multimedia streaming becomes ever more popular. The multimedia standard MPEG-4 has been designed to support scenes of different levels of complexity and applications with low bandwidth requirements up to very high bandwidth requirements. One protocol suitable to transfer this kind of data over IP networks is the real-time transport protocol (RTP). This report describes standardized and proposed payload formats that support the transport of MPEG-4 elementary streams over RTP connections. These RTP packetization formats are compared w.r.t. their suitability for the adaptation (scaling) of the media data within the network, i.e., by advanced routers or proxy caches. This adaptation process is governed by metadata that need to be transferred and inspected in conjunction with the media streams.}, issn = {0-7803-7305-7}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/RTP Packetization of MPEG-4 Elementary Streams.pdf}, talktype = {none}, url = {http://www.icme2002.org/} } @InProceedings{Libsie2002, author = {Libsie, Mulugeta and Kosch, Harald}, booktitle = {Proceedings of the tenth ACM international conference on Multimedia}, title = {Content Adaptation of Multimedia Delivery and Indexing using MPEG-7.}, year = {2002}, address = {New York, USA}, editor = {Rowe, Lawrence and Merialdo, Bernard and Muehlhaeuser, Max and Ross, Keith and Dimitrova, Nevenka}, month = dec, pages = {644-646}, publisher = {ACM}, abstract = {This work introduces a framework for adapting MPEG-4 intra- and inter-Elementary Streams and for encoding the results in an MPEG-7 stream to be used for resource adaptation on the delivery path to the user.}, doi = {10.1145/641007.641134}, isbn10 = {1-58113-620-X}, keywords = {MPEG-7, MPEG4, multimedia indexing, resource adaptation}, language = {EN}, talktype = {none} } @InProceedings{Kosch2002d, author = {Kosch, Harald and Döller, Mario}, booktitle = {Proceedings of the 10th International Conference on Multimedia, Antibes, France, Nov. to Dec. 2002.}, title = {Demonstration of an MPEG-7 Multimedia Data Cartridge.}, year = {2002}, address = {New York, NY, USA}, editor = {Rowe, Lawrence and Merialdo, Bernard and Muehlhaeuser, Max and Ross, Keith and Dimitrova, Nevenka}, month = dec, pages = {85-86}, publisher = {ACM Press}, abstract = {Multimedia Database Systems (MMDBMS) organize and store multimedia data for content retrieval. The relying multimedia data models represent abstractions of media objects for querying, indexing, and so on. However, most currently available implementations reval shortcomings. Either they are limited by one kind of multimedia data supported or by the capacity of their semantic modelling. Despite the upcoming MPEG-7 standard for representing low-level and high-level features of multimedia and respective annotation and use tools (see http://www.mpeg-industry.com), we are not aware of any MMDBMS product which integrates this standard for the purpose of a more meaningful indexing and querying. In this context, our paper presents a Multimedia Data Cartridge (MDC) for demonstration at ACM Multimedia 2002 that implements an object-relational data model for the core part of the MPEG-7 standard. It is an open and extensible system realized with the Oracle Data Cartridge technology. Oracle offers with that technology a mechanism for extending the capabilities of an Oracle database (e.g., type system, query processing and indexing) for the users needs. Besides the more effective modelling of multimedia content, efficient retrieval was considered. Efficient query processing is guaranteed through new database indexing mechanisms. Innately, most database systems provide only a limited number of integrated access methods such as B-trees. Available multimedia database extension packages (e.g., DataBlades of Informix) rarely handle indexing of d-dimensional data (e.g., feature vectors with d>2) or advanced similarity search functionalities (e.g., k-NN search). These circumstances limit the use of database systems in multimedia. For overcoming this drawback, we introduce an Multimedia Indexing Framework (MIF) relying on the GiST framework. Finally, in order to use the MMDBMS we provide query and presentation interfaces which automatically adapt to their usage environment.}, doi = {10.1145/641007.641024}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/p85-doller.pdf}, talktype = {none} } @InProceedings{Kosch2002b, author = {Hameurlain, Abdelkader and Morvan, Franck and Tomsich, Philipp and Bruckner, Robert M and Kosch, Harald and Brezany, Peter}, booktitle = {Database and Expert Systems Applications, Aix-en-Provence, France, Proceedings of the 13th International Conference on Database and Expert Systems Applications}, title = {Mobile query optimization based on agent-technology for distributed data warehouse and OLAP applications}, year = {2002}, address = {Berlin [u. a.]}, editor = {Hameurlain, Abdelkader and Cicchetti, Rosine and Traunmüller, Roland}, month = sep, pages = {795-799}, publisher = {Springer Verlag}, series = {Lecture Notes in Computer Science}, abstract = {This book constitutes the refereed proceedings of the 13th International Conference on Database and Export Systems Applications, DEXA 2002, held in Aix-en-Provence, France, in September 2002. The 89 revised full papers presented together with three invited papers and a position paper were carefully reviewed and selected from 241 submissions. The papers are organized in topical sections on Web, workflow, data warehouses and datamining, applications, XML, distributed systems, knowledge engineering, advanced databases, queries, information retrieval, and indexing.}, issn = {3-540-44126-3}, language = {EN}, talktype = {none}, url = {http://dl.acm.org/citation.cfm?id=646130.679339} } @InProceedings{Csizmazia2002, author = {Csizmazia, Balázs and Hellwagner, Hermann}, booktitle = {Proceedings Fourth International Workshop on Active Middleware Services}, title = {The design and implementation of the A2QM3 System}, year = {2002}, address = {Washington, DC, USA}, editor = {N,A}, month = {jan}, pages = {19-27}, publisher = {IEEE Computer Society}, abstract = {In this paper we present the design, architecture and implementation of the A2QM3 System. It provides programmers re-usable QoS-aware Control Objects to enable building a complete middleware for adaptive applications over active networks. We introduce the programming model, the system architecture, and show the parts that make this system a full-featured middleware supporting QoS-aware reliable stream-oriented communication, communication using the request/reply-based CORBA model and real-time streaming for continuous multimedia contents.}, isbn10 = {0-7695-1721-8}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/The design and implementation of the A2QM3 System.pdf}, talktype = {none} } @InProceedings{Boeszoermenyi2002a, author = {Böszörmenyi, Laszlo and Döller, Mario and Hellwagner, Hermann and Kosch, Harald and Libsie, Mulugeta and Schojer, Peter}, booktitle = {Proceedings of the tenth ACM international conference on Multimedia}, title = {Comprehensive Treatment of Adaptation in Distributed Mulimedia Systems in the ADMITS Project}, year = {2002}, address = {New York}, editor = {Les Pins, Juan}, month = {jan}, pages = {429-430}, publisher = {ACM}, abstract = {Adaptation is becoming an increasingly important tool for resource and media management in distributed multimedia systems. Best-effort scheduling and worst-case reservation of resources are two extreme cases, none of them well suited to cope with large-scale, dynamic multimedia systems. The middle course can be met by a system which dynamically adapts its data, resource requirements, and processing components to achieve user satisfaction. Nevertheless, there is no agreement about the questions, where, when, what and who should adapt. A number of papers have been published in recent years, where adaptation is a central issue, however, in most different interpretations and generally in a somehow limited scope; e.g.,[1, 2, 8, 9, 10, 12]. A distributed multimedia system comprises several types of components, such as media servers, meta-databases, proxies, routers, clients. Also, a large number of adaptation possibilities exist, from simple frame dropping up to virtual server systems which dynamically allocate new resources on demand. The main question is, which kind of component can be best used for what kind of adaptation. In the ADMITS project (Adaptation in Distributed Multimedia IT Systems), we are seeking for answers to exactly this basic question, and to a number of related questions.}, issn = {1-58113-620-X}, language = {EN}, talktype = {none}, url = {http://portal.acm.org/citation.cfm?doid=641007.641101} } @InProceedings{Boeszoermenyi2002, author = {Böszörmenyi, Laszlo and Tusch, Roland and Goldschmidt, Balázs}, booktitle = {Distributed and parallel systems: cluster and grid computing}, title = {A Mobile Agent-based Infrastructure for an Adaptive Multimedia Server}, year = {2002}, address = {Boston}, editor = {Kacsuk, Peter and Kranzlmüller, Dieter and Nemeth, Zsolt and Volkert, Jens}, month = {jan}, pages = {141-148}, publisher = {Kluwer Academic Publishers/Springer Verlag}, abstract = {This paper introduces a mobile agent-based infrastructure for an adaptive multimedia server enabling a dynamic migration or replication of certain multimedia applications among a set of available server nodes. It discusses the requirements from both, the server’s and the middleware’s point of view to each other and comes up with a specification and implementation of a CORBA-based interface between them.}, issn = {1-4020-7209-0}, language = {EN}, talktype = {none} } @InProceedings{Taschwer2001, author = {Taschwer, Mario}, booktitle = {Kommunikationssicherheit im Zeichen des Internet}, title = {Modular Multiplication Using Special Prime Moduli}, year = {2001}, address = {Braunschweig/Wiesbaden}, editor = {Horster, Patrick}, month = {jan}, pages = {346--371}, publisher = {Vieweg}, abstract = {Elliptic curve cryptosystems allow the use of prime fields with special prime moduli that speed up the finite field arithmetic considerably. Two algorithms for reduction with respect to special moduli have been implemented in software on both a 32-bit and a 64-bit platform and compared to well-known generic modular reduction methods. Timing results for multiplications in prime fields of size between 2^{191} and 2^{512} are presented and discussed.}, isbn10 = {3-528-05763-7}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/2001si_modmult.pdf}, talktype = {none} } @InProceedings{Kosch2001c, author = {Kosch, Harald and Böszörmenyi, Laszlo and Bachlechner, Alexander and Hanin, Christian and Hofbauer, Christian and Lang, Margit and Riedler, Carmen and Tusch, Roland}, booktitle = {VLDB 2001, Proceedings of 27th International Conference on VeryLarge Data Bases, Roma, Italy, September, 11-14, 2001}, title = {SMOOTH-A Distributed Multimedia Database System}, year = {2001}, address = {Orlando, Fla.}, editor = {Apers, P M G and Atzeni, P and Ceri, St and Paraboschi, St and Ramamohanarao, K and Snodgrass, KT}, month = sep, pages = {713-714}, publisher = {Morgan Kaufmann}, issn = {1-55860-804-4}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/P713.pdf}, talktype = {none} } @InProceedings{Kosch2001b, author = {Kosch, Harald and Böszörmenyi, Laszlo and Hellwagner, Hermann}, booktitle = {Proceedings of the 12th International Conference on Database and Expert Systems Application - DEXA 2001, Munich, Germany, September 3-5, 2001}, title = {Modeling Quality Adaptation Capabilities of Audio-Visual Data}, year = {2001}, address = {Berlin [u. a.]}, editor = {Mayr, HC and Lazansky, J and Quichmayr, G and Vogel, P}, month = sep, pages = {744-753}, publisher = {Springer Verlag}, series = {LNCS}, issn = {0302-9743}, language = {EN}, talktype = {none} } @InProceedings{Kosch2001a, author = {Kosch, Harald and Sampaio P, Falcone and Hameurlain, A and Brunie, Lionel}, booktitle = {Euro-Par 2001: Parallel Processing 7th International Euro-Par Conference Manchester, UK August 28-31, 2001, Proceedings}, title = {Parallel and Distributed Databases, Data Mining and Knowledge Discovery}, year = {2001}, address = {Berlin [u. a.]}, editor = {Sakellariou, R and Keane, J and Gurd, J and Freeman, L}, month = aug, pages = {278-279}, publisher = {Springer Verlag}, series = {LNCS}, issn = {3-540-42495-4}, language = {EN}, talktype = {none} } @InProceedings{Kosch2001, author = {Kosch, Harald and Döller, Mario and Böszörmenyi, Laszlo}, booktitle = {Multimedia Databases and Image Communication, Second International Workshop MDIC 2001, Amalfi, Italy, September 17-18, 2001; Proceedings}, title = {Content-based Indexing and Retrieval Supported by Mobile Agent Technology}, year = {2001}, address = {Berlin [u. a.]}, editor = {Tucci, M}, month = {jan}, pages = {152-165}, publisher = {Springer Verlag}, series = {LNCS}, abstract = {This book constitutes the refereed proceedings of the Second International Workshop on Multimedia Databases and Image Communication, MDIC 2001, held in Amalfi, Italy, in September 2001. The 16 revised full papers presented together with two invited papers were carefully reviewed and selected for inclusion in the book. The papers are organised in topical sections on image and visual computing applications, multimedia technology, image and visual information querying and browsing, and video indexing and communication.}, issn = {3-540-42587-X}, language = {EN}, talktype = {none} } @InProceedings{Hellwagner2001a, author = {Hellwagner, Hermann and Kargl, Erich}, booktitle = {SCI 2001 Proceedings of the 5th World Multi-Conference on Systemics, Cybernetics and Informatics, Volume XV, IEEE CS, July 2001}, title = {A Cluster-Based QoS Testbed for Multimedia Communications}, year = {2001}, address = {--}, editor = {Callaos, N and Badawy, W and Bozinovski, S}, month = jul, pages = {362-367}, publisher = {IEEE}, abstract = {This paper presents an inexpensive cluster-based QoS networking testbed that can be employed to \emulate" different networks for multimedia communication ex-periments. Such a network can be built using standard PC and Ethernet hardware and open-source software components, e.g., IP routing and traÆc control avail- able in recent Linux kernels as well as a Differentiated Services package built atop these building blocks. The testbed can exibly be configured to model various link bandwidths as well as IP routers capable of classifying, queuing (with various disciplines), forward-ing and/or dropping packets and shaping traÆc. The QoS components and facilities of the testbed are in-troduced and initial performance analysis experiments and results are reported. A simple video streaming application under QoS control is presented to show the usefulness of the testbed.}, issn = {980-07-7552-8}, keywords = {multimedia communications, quality of service, QoS, networking testbed, routing, Linux}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/A Cluster-Based QoS Testbed for Multimedia Communications.pdf}, talktype = {none} } @InProceedings{Boeszoermenyi2001, author = {Böszörmenyi, Laszlo and Hellwagner, Hermann and Kosch, Harald}, booktitle = {Elektronische Geschäftsprozesse: Grundlagen, Sicherheitsaspekte, Realisierungen, Anwendungen. Tagungsband zur gemeinsamen Arbeitskonferenz GI/VOI/BITKOM/OCG/TeleTrusT}, title = {Multimedia Technologies for E-Buisness Systems and Process}, year = {2001}, address = {Höhenkirchen}, editor = {Horster, Patrick}, month = {jan}, pages = {471-481}, publisher = {it Verlag}, series = {IT Security \& IT Management}, issn = {3-936052-00-X}, language = {EN}, talktype = {none} } @InProceedings{Atnafu2001a, author = {Atnafu, Solomon and Brunie, Lionel and Kosch, Harald}, booktitle = {International Database Engineering and Applications Symposium (IDEAS) 2001, July 2001, Proceedings}, title = {Similarity -Based Operators and Query Optimization for Multimedia Database Systems}, year = {2001}, address = {Los Alamitos, Calif. [u.a.]}, editor = {Adiba, ME and Collet, Ch and Bipin, C}, month = jul, pages = {346-355}, publisher = {IEEE Computer Society}, issn = {0-7695-1140-6}, language = {EN}, talktype = {none} } @InProceedings{Atnafu2001, author = {Atnafu, Solomon and Brunie, Lionel and Kosch, Harald}, booktitle = {Advances in Web-Age Information Management. Second International Conference, WAIM 2001, Xi'an, China, July 9-11, 2001. Proceedings}, title = {Similarity-Based Operators in Image Database Systems}, year = {2001}, address = {Berlin [u. a.]}, editor = {Wang, XS and Yu, G and Lu, H}, month = {jan}, pages = {14-25}, publisher = {Springer Verlag}, series = {LNCS}, issn = {3-540-42298-6}, language = {EN}, talktype = {none} } @InProceedings{Tusch2000, author = {Tusch, Roland and Kosch, Harald and Böszörmenyi, Laszlo}, booktitle = {Proceedings ACM Multimedia 2000 : Los Angeles, California, October 30 - November 4, 2000}, title = {VIDEX: Integrated Generic Video Indexing Approach}, year = {2000}, address = {Reading, Mass.}, editor = {Ghandeharizadeh, Shahram and Chang, Shih-Fu and Fischer, Stephen and Konstan, Joseph A and Nahrstedt, Klara}, month = dec, pages = {448-451}, publisher = {ACM}, isbn10 = {1-58113-198-4}, issn = {0-2014-8566-4}, language = {EN}, talktype = {none} } @InProceedings{Schordan2000, author = {Schordan, Markus and Amme, Wolfram}, booktitle = {Proceedings of the 8th International Workshop on Compilers for Parallel Computers}, title = {Virtual Method Resolution with Typed Alias Graphs}, year = {2000}, address = {Heidelberg}, editor = {Midkiff, Samuel and Moreira, José and Gupta, Manish and Chatterjee, Siddhartha and Ferrante, Jeanne and Prins, Jan and Pugh, William and Tseng, Chau-Wen}, month = jan, pages = {151-162}, publisher = {Springer}, series = {LNCS}, edition = {LNCS}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/2000-0001-ScAm.pdf}, talktype = {none} } @InProceedings{Moustefaoui2000, author = {Moustefaoui, Ahmed and Kosch, Harald and Böszörmenyi, Laszlo and Brunie, Lionel}, booktitle = {Proceedings of IEEE Conference Multimedia and Expo. ICME 2000: 30 July - 2 August 2000, New York, USA/ IEEE Signal Processing Society}, title = {Multi-Clip Query Optimization in Video Databases}, year = {2000}, address = {Piscataway, NJ}, editor = {Basu, Sankar}, month = {jan}, pages = {363-366}, publisher = {IEEE Servoce Center}, abstract = {A multi-clip query requests multiple video clips. We address the multi-clip query optimization problem. We propose a new heuristic called restricted search interval that maximizes clip sharing between queries and consequently reduces the workload of the video server. The experimental results show that the suggested heuristics reduce the server workload by about 68.7% in comparison to a classical heuristic approach.}, doi = {10.1109/ICME.2000.869616}, issn = {0-7803-6536-4}, language = {EN}, location = {New York}, pdf = {https://www.itec.aau.at/bib/files/00869616.pdf}, subtitle = {IEEE Interantional Conference on Multimedia & Expo 2000}, talkdate = {2000.08.31}, talktype = {registered}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=869616&tag=1} } @InProceedings{Kosch2000e, author = {Kosch, Harald and Tusch, Roland and Böszörmenyi, Laszlo and Bachlechner, Alexander and Dörflinger, Bernhard and Hofbauer, Christian and Riedler, Carmen}, booktitle = {Proceedings ACM Multimedia 2000 : Los Angeles, California, October 30 - November 4, 2000}, title = {The SMOOTH Video DB -Demonstration of an Integrated Generic Indexing Approach}, year = {2000}, address = {Reading, Mass.}, editor = {Ghandeharizadeh, Shahram and Chang, Shih-Fu and Fischer, Stephen and Konstan, Joseph and Nahrstedt, Klara}, month = dec, pages = {448-451}, publisher = {Addison-Wesley [u. a.]}, isbn10 = {1-58113-198-4}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/10.1.1.87.1278.pdf}, talktype = {none} } @InProceedings{Kosch2000d, author = {Kosch, Harald and Breidler, Kurt and Böszörmenyi, Laszlo}, booktitle = {Distributed and Parallel Systems - From Concepts to Architectures}, title = {The Parallel Video Server SESAME-KB}, year = {2000}, address = {Boston, Mass.}, editor = {Kacsuk, Peter and Kotsis, Gabriele}, month = sep, pages = {151-154}, publisher = {Kluwer Academic Publ}, series = {The Kluwer international series in engineering and computer science}, abstract = {This paper presents the parallel video server SESAME-KB, by the means of its architectural design, striping, scheduling, caching and admission policy. Furthermore we compare our prototype to approaches which influenced our realization. Keywords: Parallel Video Server, Parallel Systems and Communication.}, issn = {0-7923-7892-X}, language = {EN}, talktype = {none} } @InProceedings{Kosch2000c, author = {Kosch, Harald}, booktitle = {Dexa 2000 Workshop Proceedings, W 10, Greenwich (UK), Sept 2000, Tutorial Abstract}, title = {CORBA, Web and Databases}, year = {2000}, address = {Greenwich, London}, editor = {Tjoa, A M and Wagner, R and Al-Zobaidie, A}, month = sep, pages = {674}, publisher = {IEEE CS Press}, issn = {0-7695-0680-1}, language = {EN}, talktype = {none} } @InProceedings{Kosch2000b, author = {Kosch, Harald and Breidler, Kurt and Böszörmenyi, Laszlo}, booktitle = {11th International Workshop on Database and Expert Systems Applications (DEXA'00)6-8 September 2000 , Greenwich, London}, title = {A Comparative Study of Selected Parallel Video Servers}, year = {2000}, address = {U.K., Greenwich}, editor = {Tjoa, A M and Wagner, R R and Al-Zobaidie, A}, month = sep, pages = {669-673}, publisher = {IEEE CS Press}, abstract = {This paper compares different selected and representative parallel video servers, including our server SESAME-KB, by the means of their architectural design, striping, scheduling, caching and admission policy. It is shown that these parallel video servers can support a high number of concurrent accesses, but will also reveal missing components, as bottlenecks. Finally we point to further developments}, doi = {10.1109/DEXA.2000.875095}, isbn10 = {0-7695-0680-1}, language = {EN}, talktype = {none} } @InProceedings{Kosch2000a, author = {Kosch, Harald and Slota, Renata and Nikolow, Darin and Podlipnig, Stefan and Breidler, Kurt}, booktitle = {High-Performance Computing and Networking, 8th International Conference, HPCN Europe 2000 Amsterdam, May 8-10, 2000 Proceedings}, title = {MMSRS-Multimedia Storage and Retrieval System for a Distributed System}, year = {2000}, address = {Berlin [u. a.]}, editor = {Bubak, Marian}, month = may, pages = {517-524}, publisher = {Springer Verlag}, series = {LNCS}, abstract = {The Multimedia Storage and Retrieval System described in this paper is aimed at storing and retrieving medical multimedia data such as images and videos. There are three significant problems that automatically need to be addressed: providing enough capacity to fit Terabytes of MPEG files, efficient extraction of video fragments from MPEG files and quality of service issues. We are working on two different approaches to build MMSRS. The first one, described in this article, utilizes commercial HSM software for managing the tertiary storage hardware. The second approach that we have started to investigate is an attempt to build a specialised storage management system from scratch.}, doi = {10.1007/3-540-45492-6_52}, issn = {3-540-67553-1}, language = {EN}, talktype = {none}, url = {http://www.springerlink.com/content/r334107699313461/} } @InProceedings{Hellwagner2000b, author = {Hellwagner, Hermann and Leopold, Klaus and Schlatterbeck, Ralf and Weich, Carsten}, booktitle = {Proceedings Distributed and Parallel Systems}, title = {Performance Tuning of Parallel Real-Time Voice Communication Software}, year = {2000}, address = {Norwell, MA, USA}, editor = {Kascuk, Peter and Kotsis, Gabriele}, month = sep, pages = {57-60}, publisher = {Kluwer Academic Publishers}, abstract = {This paper describes an unconventional way to apply a performance analysis tool for parallel programs (Vampir) to understand and tune the performance of the real-time voice and data communication software running on top of Frequentis’ V4 switch. The execution schedule of the strictly time-triggered V4 switching software is computed off-line; analyzing the schedule to identify e.g. performance bottlenecks used to be a complex and time-consuming process. We present our approach to transform the V4 software schedule’s information into Vampir trace files and use this tool’s facilities to provide a visualization of the schedule. A case study illustrates the benefits of this approach.}, keywords = {This paper describes an unconventional way to apply a performance analysis tool for parallel programs (Vampir) to understand and tune the performance of the real-time voice and data communication software running on top of Frequentis’ V4 switch. The execution schedule of the strictly time-triggered V4 switching software is computed off-line; analyzing the schedule to identify e.g. performance bottlenecks used to be a complex and time-consuming process. We present our approach to transform the V4 software schedule’s information into Vampir trace files and use this tool’s facilities to provide a visualization of the schedule. A case study illustrates the benefits of this approach.}, language = {DE}, pdf = {https://www.itec.aau.at/bib/files/2000-0084-HHKL.pdf}, talktype = {none} } @InProceedings{Hellwagner2000, author = {Hellwagner, Hermann and Lachowitz, Markus and Ohlenroth, Matthias}, booktitle = {Proceedings International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA´2000), June 26, 2000, Las Vegas, Vol. 5}, title = {Exploring the Performance of VI Architecture Communication Features in the Giganet Cluster LAN}, year = {2000}, address = {[Athens, Ga.]}, editor = {Arabnia, Hamid R}, month = {jan}, pages = {2615-2621}, publisher = {CSREA Press}, abstract = {The Virtual Interface (VI) Architecture standard was developed to satisfy the need for a high-throughput, low-latency communication system required for cluster computing. This paper presents the results of a performance study of one VI Architecture hardware implementation, the Giganet cLAN (Cluster LAN). The focus of the study is to assess and compare the performance of different VI Architecture data transfer modes and specific features that are available to higher-level communication software like MPI, in order to aid the implementor to decide which VI Architecture options to employ for various communication scenarios. Examples of such options include the use of send/receive vs. RDMA data transfers, polling vs. blocking to check completion of communication operations, multiple VIs, completion queues, and scatter capabilities of VI Architecture.}, doi = {DOI:10.1016/S0167-739X(01)00060-7}, issn = {1-892512-51-3}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/2000-0079-HHML.pdf}, talktype = {none} } @InProceedings{Kosch1999, author = {Kosch, Harald and Slota, R and Böszörmenyi, Laszlo and Kitowski, J and Otfinowski, J and Wójcik, P}, booktitle = {High-Performance Computing and Networking}, title = {A Distributed Medical Information System for Multimedia Data - The first Years Experience of the PARMED Project}, year = {1999}, address = {Berlin [u. a.]}, editor = {Bubak , M and Williams, R and Afsarmanesh, H and Hertzberger, B}, month = apr, pages = {543-546}, publisher = {Springer Verlag}, series = {LNCS}, issn = {3-540-67553-1}, language = {EN}, talktype = {none} } @InProceedings{Boeszoermenyi1999f, author = {Böszörmenyi, Laszlo}, booktitle = {Proceedings of the Workshop on Object-Oriented Technology}, title = {Introducing OO with Bottom-up Approach, Structured First}, year = {1999}, address = {Berlin, Heidelberg, New York}, editor = {Moreira, Ana and Demeyer, Serge}, month = oct, pages = {340-342}, publisher = {Springer Verlag}, series = {LNCS}, abstract = {Object-Oriented Technology.}, edition = {1743}, issn = {3-540-66954-X}, language = {EN}, location = {Lisbon, Portugal}, talkdate = {1999.06.16}, talktype = {registered} } @InProceedings{Boeszoermenyi1999e, author = {Böszörmenyi, Laszlo and Eisner, Robert and Groiss, Herbert}, booktitle = {10th DEXA 1999 Workshop Proceedings, Sept 1-3 1999, Florence, Italy}, title = {Adding Distribution to a Workflow Managment System}, year = {1999}, address = {Los Alamitos, Calif. [u. a.]}, editor = {Bench-Capon, Trevor and Soda, Giovanni and Tjoa, A Min}, month = sep, pages = {17-21}, publisher = {IEEE CS Press}, abstract = {The Workflow Management System AltaVista Works has been extended to be able to process workflows in a distributed, partly even parallel manner. Build-time data are replicated over all participating workflow servers. The distribution of workflow execution is based on migration. Instead of the usual static re-partitioning, a highly dynamic management of distribution is applied.}, doi = {10.1109/DEXA.1999.795118}, issn = {0-7695-0281-4}, language = {EN}, talktype = {none} } @InProceedings{Boeszoermenyi1999d, author = {Böszörmenyi, Laszlo and Kosch, Harald and Schordan, Markus}, booktitle = {Proceedings of the 3rd International Austrian-Israeli Technion Symposium}, title = {JavaSet - extending Java by persistent sets}, year = {1999}, address = {Wien}, editor = {Gutmann, Helmut}, month = apr, pages = {58-66}, publisher = {Austrian Technion Society}, issn = {3-9501023-0-2}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/10.1.1.47.3866.pdf}, talktype = {none} } @InProceedings{Boeszoermenyi1999c, author = {Böszörmenyi, Laszlo and Kosch, Harald and Slota, Renata}, booktitle = {Proceedings of the 3rd International Austrian-Israeli Technion Symposium, 26.-27. April 1999, RISC Linz, Austrian Technion Society}, title = {PARMED-Information system for long distance collaboration in medicine}, year = {1999}, address = {Wien}, editor = {Gutmann, Helmut}, month = apr, pages = {157-164}, publisher = {Austrian Technion Society}, abstract = {This paper describes the PARMED project initiative The aim of PARMED is to provide medical stu with a large virtual database of image and video data distributed over several medical centers Clients can access the PARMED system by an active client software which provides graphical interfaces to query the virtual database Incoming video streams and image data is postprocessed by the active client software to allow analysis of this data for diagnostics or virtual teaching Quality of service and security aspects are crucial for such kind of distributed system and will be addressed with priority}, issn = {3-9501023-0-2}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1999-0001-BoKS.pdf}, talktype = {none} } @InProceedings{Boeszoermenyi1999b, author = {Böszörmenyi, Laszlo and Hölzl, Günter and Pirker, Emanuel}, booktitle = {Parallel Computatuin. 4th International ACPC Conference Including Special Tracks on Parallel Numerics (ParNum'99) and Parallel Computing in Image Processing, Video Processing, and Multimedia Salzburg, Austria, February 16-18, 1999, Proceedings}, title = {Parallel Cluster Computing with IEEE-1394}, year = {1999}, address = {Berlin [u. a.]}, editor = {Zinterhof, Peter and Vajtersic, Marian and Uhl, Andreas}, month = feb, pages = {552-532}, publisher = {Springer Verlag}, series = {LNCS}, abstract = {Diverging demands on computer networks, such as high bandwidth, guaranteed quality of service and low latency lead to growing heterogeneity. IEEE1394-1995 is a standardized low-cost highperformance serial-bus-system with both isochronous and asynchronous operation. It might be an interesting candidate for all-round local and system area networks, providing a good compromise in fulfilling the above demands for low costs. Beside providing some technical background we show the possibilities and advantages of building parallel clusters on top of IEEE1394-1995. The main advantage is that minimal speed-up can be guaranteed, as shown on the basis of the parallel implementation of discrete Fourier transformation.}, isbn10 = {3-540-65641-3}, issn = {3-540-65641-3}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1999-0003-BoHP.pdf}, talktype = {none} } @InProceedings{Boeszoermenyi1999, author = {Böszörmenyi, Laszlo and Wickner, Andreas and Wolf, Harald}, booktitle = {Euro-Par 1999, Parallel Processing, Proceedings of 5th International EuroPar Conference, Toulouse, France, August 31 - September 3, 1999}, title = {Performance Evaluation of Object Oriented Middleware}, year = {1999}, address = {Berlin [u. a.]}, editor = {Amestoy, Patrick and Berger, Philippe and Daydé, Michael and Duff, Iain and Frayssé, Valerie and Giraud, Luc and Ruiz, Daniel}, month = {jan}, pages = {258-261}, publisher = {Springer Verlag}, series = {LCNS}, abstract = {A method for evaluating several aspects of the performance of object oriented middleware is introduced. Latency, data transfer, parameter marshalling and scalability are considered. A portable benchmark toolkit has been developed to implement the method. A number of actual middleware products have been measured, such as C++ and Java based CORBA implementations, DCOM and Java/RMI. The measurements are evaluated and related to each other.}, doi = {10.1007/3-540-48311-X_31}, isbn10 = {978-3-540-66443-7}, issn = {3-540-66443-2}, language = {EN}, talktype = {none}, url = {http://www.enseeiht.fr/events/europar99/} } @InProceedings{Angster1999, author = {Angster, Erzsébet and Bergin, Joseph and Böszörmenyi, Laszlo}, booktitle = {Object-Oriented Technology: ECOOP´99 Workshop Reader; ECOOP´99 Workshops, Panels, and Poster: Lisbon, Portugal, June 14-18, 1999; Proceedings}, title = {Introducing OO Programming - with Special Emphasis on Concrete Examples}, year = {1999}, address = {Berlin [u. a.]}, editor = {Demeyer, Serge and Moreira, A}, month = {jan}, pages = {338-358}, publisher = {Springer Verlag}, abstract = {This book constitutes the joint refereed post-proceedings of 20 workshops, one panel session, and one poster session held during the 13th European Conference on Object-Oriented Programming, ECOOP'99, in Lisbon, Portugal in June 1999. The volume presents overviews of the 20 workshops as well as more than 200 individual short presentations by the contributing authors in a coherent and systematic way. The wealth of up-to-date information provided spans the whole spectrum of object technology, from theoretical and foundational issues to applications in various domains.}, doi = {10.1007/3-540-46589-8_20}, issn = {3-540-66954-X}, language = {EN}, talktype = {none}, url = {http://www.springerlink.com/content/8fxf7j38q9vtbd0u/} } @InProceedings{Amme1999, author = {Amme, Wolfram and Schordan, Markus and Böszörmenyi, Laszlo and Rossak, Willibald}, booktitle = {Object-Oriented Technology, ECOOP 99 Workshop Reader. ECOOP´99 Workshops, panels, posters, Lisbon, Portugal, June 14-18, 1999 Proceedings}, title = {PAOLA-Program Analysis of Object-Oriented Languages}, year = {1999}, address = {Berlin [u. a.]}, editor = {Moreiera, Anna and Demeyer, Serge}, month = oct, pages = {143-146}, publisher = {Springer Verlag}, series = {LNCS}, abstract = {Aliasing in Object-Oriented Systems.}, issn = {3-540-66954-X}, language = {EN}, location = {Lisbon, Portugal}, talktype = {none} } @InProceedings{Schulz1998a, author = {Schulz, Martin and Hellwagner, Hermann}, booktitle = {Proceedings of SCI-Europe ´98}, title = {Global Virtual Memory based on SCI-DSM}, year = {1998}, address = {N, A}, editor = {N, A}, month = sep, pages = {59-67}, publisher = {N, A}, language = {EN}, talktype = {none} } @InProceedings{Schulz1998, author = {Schulz, Martin and Hellwagner, Hermann}, booktitle = {Proceedings of 2nd USENIX Windows NT Symposium}, title = {Extending NT Virtual Memory by SCI-based Hardware DSM}, year = {1998}, address = {Seattle, WA, USA}, editor = {N, A}, month = aug, pages = {-}, publisher = {USENIX Association}, issn = {1-8804-4695-2}, language = {EN}, talktype = {none} } @InProceedings{Richter1998, author = {Richter, Harald and Kleber, Richard and Hellwagner, Hermann}, booktitle = {Proceedings of the High Performance Computing Symposium}, title = {Cost-Efficient SCI-based Banyan Networks}, year = {1998}, address = {N, A}, editor = {N, A}, month = apr, pages = {-}, publisher = {N, A}, keywords = {Cluster Computing, Scalable Coherent Interface, Banyan Networks}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1998-0050-RiKH.pdf}, talktype = {none} } @InProceedings{Eberl1998, author = {Eberl, Michael and Hellwagner, Hermann and Herland, Bjarne Geir}, booktitle = {Proceedings of HPCN-Europe 98}, title = {Common Messaging Layer for MPI and PVM over SCI}, year = {1998}, address = {NA}, editor = {Sloot, Peter and Bubak, Marian and Hertzberger, Bob}, month = apr, pages = {576-587}, publisher = {Springer Verlag}, series = {LNCS}, abstract = {This paper describes the design of a common message passing layer for implementing both MPI and PVM over the SCI interconnect in a workstation or PC cluster. The design is focused at obtaining low latency. The message layer encapsulates all necessary knowledge of the underlying interconnect and operating system. Yet, we claim that it can be used to implement such different message passing libraries as MPI and PVM without sacrificing efficiency. Initial results obtained from using the message layer in SCI clusters are presented.}, isbn13 = {978-3-540-64443-9}, language = {EN}, talktype = {none} } @InProceedings{Boeszoermenyi1998b, author = {Böszörmenyi, Laszlo and Kosch, Harald}, booktitle = {High-Performance Computing and Networking}, title = {High Performance Sets}, year = {1998}, address = {Heidelberg}, editor = {Sloot, Peter and Bubak, Marian and Hertzberger, Bob}, month = apr, pages = {972-974}, publisher = {Springer}, series = {LNCS}, abstract = {This short paper presents a system offering parallel persistent and polymorphic sets of objects, on the level of an existing general purpose object-oriented programming language, like Modula-3 and JAVA. The user of such a system gets distribution and persistence in the same natural way, as users of traditional systems get volatile arrays of numbers of objects. In addition, advantages are taken from sophisticated optimization techniques.}, issn = {3-540-64443-1}, language = {DE}, talktype = {none} } @InProceedings{Boeszoermenyi1998a, author = {Böszörmenyi, Laszlo and Weich, Carsten}, booktitle = {Proceedings of Database and Expert Systems Applications (DEXA '98)}, title = {Simple and Efficient Transactions for a Distributed Object Store}, year = {1998}, address = {Wien}, editor = {Wagner, Roland}, month = {jan}, pages = {693-698}, publisher = {IEEE}, abstract = {Even the more or less "canonical'', lower-level architecture of information systems needs to be revisited from time to time. Notions like persistence and transactions belong traditionally to the area of database management systems. There are, however, many applications, such as CAD, VLSI design or simulation, which need persistence and could take advantage of transactions, but require especially fast implementations not provided by DBMS. In this paper we are describing a low-level transaction concept used to implement our parallel main memory object store (PPOST), to provide main memory access times combined with the safety and convenience of transactions.}, doi = {10.1109/DEXA.1998.707480}, isbn10 = {0-8186-8353-8}, issn = {0818683538}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/00707480.pdf}, talktype = {none} } @InProceedings{Hellwagner1997f, author = {Hellwagner, Hermann}, booktitle = {Informatik-Handbuch}, title = {Arbeitsspeicher- und Bussysteme}, year = {1997}, address = {München}, editor = {Rechenberg, Peter and Pomberger, Gustav}, month = sep, pages = {239-255}, publisher = {Carl Hanser Verlag}, issn = {3-446-18691-3}, language = {DE}, talktype = {none} } @InProceedings{Hellwagner1997, author = {Hellwagner, Hermann and Karl, Wolfgang and Leberecht, Markus}, booktitle = {Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications, 1997: PDPTA}, title = {Fast Communication Mechanisms--Coupling Hardware Distributed Shared Memory and User-Level Messaging}, year = {1997}, address = {Las Vegas, Nevada, USA}, editor = {Arabnia, Hamid R}, month = {jan}, pages = {8}, publisher = {CSREA Press}, abstract = {Low latencies for small messages are an important factor of efficient fine-grained parallel computation. The Active Messages concept provides this minimal overhead by eliminating certain parts of the critical path of sending and receiving messages, that is the context switch into the operating system kernel when using user-mode I/O, and multiple buffering in the network layer. Hardware-supported distributed shared memory (DSM) architectures exhibit various properties that make them particularly useful for an implementation of the aforementioned messaging mechanisms. This paper thus describes the concept, implementation, and the performance of a DSM-based Active Messages layer.}, issn = {0-9648666-8-4}, keywords = {Distributed Shared Memory, Active Messages, User-Level Communication, Scalable Coherent Interface}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1997-0047-HeLe.pdf}, talktype = {none} } @InProceedings{Eberl1997c, author = {Eberl, Michael and Hellwagner, Hermann and Herland, Bjarne Geir and Schulz, Martin}, booktitle = {Tagungsband zum 1. Workshop Cluster Computing}, title = {SISCI - Implementing a Standard Software Infrastructure on an SCI Cluster}, year = {1997}, address = {N, A}, editor = {Rehm, Wolfgang}, month = nov, pages = {49-61}, publisher = {N, A}, series = {Chemnitzer-Informatik-Berichte}, abstract = {To enable the efficient utilization of clusters of workstations it is crucial to develop a stable and rich software infrastructure. The ESPRIT Project SISCI will provide two widely used message-passing interfaces, MPI and PVM, as well as a POSIX compliant, distributed thread package (Pthreads) on multiple SCI-based clusters. This paper features motivation and background on this projects as well as details of the two core components: the common messaging layer and the Pthreads package.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/10.1.1.39.9157.pdf}, talktype = {none} } @InProceedings{Eberl1997b, author = {Eberl, Michael and Hellwagner, Hermann and Karl, Wolfgang and Leberecht, Markus}, booktitle = {Architektur von Rechensystemen: Arbeitsteilige Systemarchitekturen - Konzepte, Lösungen, Anwendungen, Trends (ARCS´97)}, title = {Sicherheit und Effizienz in einer Active-Message-Kommunikationsschicht}, year = {1997}, address = {N, A}, editor = {Tavangarian, Djamshid}, month = sep, pages = {-}, publisher = {VDE Verlag}, series = {Vorträge der 14. ITG/GI Fachtagung ARCS}, abstract = {Active Messages haben sich als effizientes Kommunikationsverfahren insbesondere auf Kommunikationstechnologien durchgesetzt, die einen direkten Zugriff des Benutzers ohne Intervention des Betriebssystems zulassen. Als Nachteil der leichtgewichtigen Kommunikation erwiesen sich jedoch die nicht ausreichenden Schutzmechanismen, vor allem bei der Verwendung mehrerer Prozesse, die sich gleichzeitig einer Active-Message-Bibliothek bedienen. Die Spezifikation 2.0 der Berkeley-Active-Messages unternimmt nun den Versuch, f¨ur das bekannte und schnelle Kommunikationsverfahren Schutzabstraktionen vorzusehen. Im Rahmen dieser Arbeit wird die Implementation eines solchen Active-Message-Layers der Version 2.0 auf einem Cluster von SCI-gekoppelten Arbeitsplatzrechnern beschrieben. Wir k¨onnen zeigen, daß die zus¨atzlichen Schutzmechanismen nur wenig Einfluß auf die Leistung haben und somit der Vorteil der Active Messages, die leichtgewichtige, feingranulare Kommunikation, erhalten bleibt.}, issn = {3-8007-2295-X}, language = {DE}, pdf = {https://www.itec.aau.at/bib/files/1997-0043-EbHL.pdf}, talktype = {none} } @InProceedings{Eberl1997a, author = {Eberl, Michael and Hellwagner, Hermann and Karl, Wolfgang and Leberecht, Markus}, booktitle = {Architektur von Rechensystemen, Arbeitsteilige Systemarchitekturen: Konzepte, Lösungen, Anwendungen, Trends - Vorträge der 14. ITG/GI-Fachtagung ARCS '97}, title = {Sicherheit und Effizienz in einer Active Message-Kommunikationsschicht}, year = {1997}, address = {N, A}, editor = {Tavangarian, Djamshid}, month = {jan}, pages = {211-220}, publisher = {VDE Verlag}, abstract = {Active Messages haben sich als effizientes Kommunikationsverfahren insbesondere auf Kommunikationstechnologien durchgesetzt, die einen direkten Zugriff des Benutzers ohne Intervention des Betriebssystems zulassen. Als Nachteil der leichtgewichtigen Kommunikation erwiesen sich jedoch die nicht ausreichenden Schutzmechanismen, vor allem bei der Verwendung mehrerer Prozesse, die sich gleichzeitig einer Active-Message- Bibliothek bedienen. Die Spezifikation 2.0 der Berkeley-Active-Messages unternimmt nun den Versuch, für das bekannte und schnelle Kommunikationsverfahren Schutzabstraktionen vorzusehen. Im Rahmen dieser Arbeit wird die Implementation eines solchen Active- Message-Layers der Version 2.0 auf einem Cluster von SCI-gekoppelten Arbeitsplatzrechnern beschreiben. Wir können zeigen, daß die zusätzlichen Schutzmechanismen nur wenig Einfluß auf die Leistung haben und somit der Vorteil der Active Messages, die leichtgewichtige, feingranulare Kommunikation, erhalten bleibt.}, issn = {3-8007-2295-X}, language = {DE}, talktype = {none} } @InProceedings{Boeszoermenyi1997c, author = {Böszörmenyi, Laszlo and Mittermeir, Roland}, booktitle = {Modular Programming Language}, title = {Choosing Modula-3 as "Mother Tongue"}, year = {1997}, address = {Heidelberg}, editor = {Mössenböck, Hans-Peter}, month = mar, pages = {382}, publisher = {Springer}, series = {LNCS}, abstract = {Choosing the "First Computer Language" is still a crucial issue. While the debate is quite often conducted on the language level, the arguments for making the choice are rather of much deeper methodological, didactical, and non-technical nature. Here, we describe the decision process that lead us to choose Modula-3 as the first language to be taught to informatics students at the Universität Klagenfurt and report on the experience gained.}, issn = {0302-9743}, language = {EN}, talktype = {none} } @InProceedings{Acher1997, author = {Acher, Georg and Hellwagner, Hermann and Karl, Wolfgang and Leberecht, Markus}, booktitle = {Arbeitsplatz-Rechensysteme: Anwendungen, Architekturen, Betriebssysteme und Netzwerke}, title = {Eine PCI-SCI-Adapterkarte für ein PC-Cluster mit verteiltem gemeinsamen Speicher}, year = {1997}, address = {N, A}, editor = {N, A}, month = {jan}, pages = {-}, publisher = {N, A}, issn = {3-9235-3261-X}, language = {DE}, talktype = {none} } @InProceedings{Hellwagner1996, author = {Hellwagner, Hermann and Zoraja, Ivan and Sunderam, Vaidy}, booktitle = {Proceedings PVM User Group Meeting}, title = {PVM Data Transfers on SCI Workstation Clusters}, year = {1996}, address = {N, A}, editor = {Bode, Arndt and Dongarra, Jack and Ludwig, Thomas and Sunderam, Vaidy}, month = feb, pages = {-}, publisher = {Springer}, language = {EN}, talktype = {none} } @InProceedings{Eder1996, author = {Eder, Karl-Heinz and Böszörmenyi, Laszlo}, booktitle = {DEXA '96 Proceedings of the 7th International Workshop on Database and Expert Systems Applications}, title = {Optimized Parallel Sets for Data Intensive Applications}, year = {1996}, address = {Heidelberg}, editor = {Wagner, Roland and Thoma, Helmut}, month = sep, pages = {185}, publisher = {Springer Verlag}, series = {LNCS}, abstract = {An extension of a general-purpose programming language (gpPL) is presented. It enables parallelism, persistence and query optimization based on sets. The authors demonstrate that in gpPLs the primitive "set" can be generalised for the needs of database and expert system applications. Side-effect free declarative queries, based on set expressions, can be optimized and executed in parallel. Individual optimization and parallelization are integral parts of the language system and compiler. Very different combinations of persistent or volatile, and parallel or sequential, and optimized or non-optimized implementations are possible. This is eased by the fact that a great part of the implementation is located outside the compiler with the help of predefined interfaces. Different algebras, optimizers or algorithms can be considered. The same program can be executed without modification in various systems or platforms.}, doi = {http://doi.ieeecomputersociety.org/10.1109/DEXA.1996.558293}, edition = {LNCS 1134}, isbn10 = {0-8186-7662-0}, issn = {3-540-61656-X}, language = {EN}, talktype = {none} } @InProceedings{Boeszoermenyi1996b, author = {Böszörmenyi, Laszlo and Stopper, Andreas}, booktitle = {Directory of Simulation Software, 1996}, title = {Acceleration of Distributed, Object-Oriented Simulations Using a Graph-Optimizing Approach}, year = {1996}, address = {Genoa, Italy}, editor = {Bruzzone, Agostino and Kerckhoffs, Eugene}, month = {jan}, pages = {56}, publisher = {Society for Computer Simulation International}, series = {Proceedings of ESS´96, Genoa, Italy}, abstract = {An approach to accelerate distributed, object-oriented simulations is presented in this paper. It is based on the assumption that a higher acceleration can be achieved in an easier way, if the problem is alread tackled early at the modeling stage [STOP 95]. The user adds hints about the communication behavior and frequencies of object classes to the simulation model. Based on this information, an object graph is generated and distributed to a selected number of partitions. The distribution phase is fully automatic. As a result a distribution of the problem nearby the communication optimum is generated. In the next phase the distributed simulation program (code) is generated. In a final step the user only has to code the methods of the object classes and run the simulation. The major advantage of this approach is that the user is freed from the difficult task of finding a good distribution for the problem to be simulated, which is an important factor for the overall performance of the simulation. Another advantage is the possibility to vary model information (hints) about the communication, and get a new (quasi optimal) version of the simulation automatically generated.}, issn = {1-565-55099-4}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1996-0020-StBo.pdf}, talktype = {none} } @InProceedings{Bode1996a, author = {Bode, Arndt and Gerndt, Michael and Hackenberg, R and Hellwagner, Hermann}, booktitle = {Proceedings of IPPS '96, The 10th International Parallel Processing Symposium}, title = {High-Level Programming Models and Supportive Environments (HIPS´96)}, year = {1996}, address = {N, A}, editor = {N, A}, month = apr, pages = {-}, publisher = {IEEE Computer Society}, issn = {0-8186-7255-2}, language = {EN}, talktype = {none} } @InProceedings{Boeszoermenyi1995a, author = {Böszörmenyi, Laszlo and Stopper, Andreas}, booktitle = {Eurosim´95}, title = {A Distributed, Object Oriented Simulation System based on Hints}, year = {1995}, address = {Vienna}, editor = {Breitenecker, Felix and Husinsky, Irmgard}, month = sep, pages = {1356}, publisher = {Elsevier}, series = {Proceedings of the 1995 EUROSIM Conference}, abstract = {A hint-based, distributed, discrete, object-oriented simulation system is described. In course of the design phase of the simulation model, explicit hints can be provided concerning dependencies and information flow inside the model. The process of parallelization consists of two major steps. In the first step, the abstract model, enriched with user-supplied hints is mapped onto an arbitrary number of active units. In the second step, the active units are mapped onto a given number of physical nodes, characterized by their processing capacity and by the communication latency between them. The distribution scheme may be dynamic, i.e. simulation objects can change their location in course of the simulation, in order to get better performance. Klaus.Leopold 05.04.2001.}, issn = {0-444-82241-0}, language = {EN}, talktype = {none} } @InProceedings{Eurosim94, author = {Böszörmenyi, Laszlo and Eder, Karl-Heinz and Weich, Carsten}, booktitle = {Massively Parallel Processing Applications and Develompent, Proceedings of the 1994 EUROSIM Conference on Massively Parallel Processing}, title = {PPOST - A Persistent Parallel Object Store}, year = {1994}, address = {Langford Lane, Kidlington, Oxford OX5 1GB, United Kingdom}, editor = {Dekker, Lan and Smit, Wim and Zuidervaart, Jan C}, month = {jun}, pages = {163-170}, publisher = {Elsevier}, isbn10 = {0-444-81784-0}, keywords = {parallel, memory-resident, object-oriented database management system, object store, database architecture}, language = {EN}, location = {Delft, The Netherlands}, pdf = {https://www.itec.aau.at/bib/files/10.1.1.21.1896.pdf}, talkdate = {1994.06.22}, talktype = {registered} } @InProceedings{Boeszoermenyi1994b, author = {Böszörmenyi, Laszlo and Eder, Karl-Heinz}, booktitle = {Proceedings of the Joint Modular Languages Conference}, title = {Adding Parallel and Persistent Sets to Modula-3}, year = {1994}, address = {Ulm}, editor = {Schulthess, Peter}, month = sep, pages = {201-216}, publisher = {Universitätsverlag Ulm}, abstract = {Parallel and persistent object sets are suggested to be incorporated into general-purpose programming languages. Two alternative implementations are presented. The actual form of the proposal is an extension of Modula-3.}, language = {EN}, location = {Ulm}, pdf = {https://www.itec.aau.at/bib/files/1994-0012-BoEd.pdf}, talkdate = {1994.09.28}, talktype = {registered} } @InProceedings{Boeckle1994, author = {Böckle, Günter and Hellwagner, Hermann}, booktitle = {Innovationen bei Rechen- und Kommunikationssystemen, Eine Herausforderung für die Informatik}, title = {Systematic Assessment of Computer Systems Architectures}, year = {1994}, address = {N, A}, editor = {Wolfinger, Bernd E}, month = aug, pages = {310-317}, publisher = {Springer Verlag}, issn = {3-5405-8313-0}, language = {EN}, talktype = {none} } @InProceedings{Hellwagner1993a, author = {Hellwagner, Hermann}, booktitle = {Parallel Computer Architectures: Theory, Hardware, Software, Applications}, title = {Randomized Shared Memory - Concept and Efficiency of a Scalable Shared Memory Scheme}, year = {1993}, address = {London, UK}, editor = {Arndt, Bode and Dal Cin, Mario}, month = {jan}, pages = {102-117}, publisher = {Springer Verlag}, series = {LNCS}, abstract = {Our work explores the practical relevance of Randomized Shared Memory (RSM), a theoretical concept that has been proven to enable an (asymptotically) optimally efficient implementation of scalable and universal shared memory in a distributed-memory parallel system. RSM (address hashing) pseudo-randomly distributes global memory addresses throughout the nodes' local memories. High memory access latencies are masked through massive parallelism. This paper introduces the basic principles and properties of RSM and analyzes its practical efficiency in terms of constant factors through simulation studies, assuming a state-of-the-art parallel architecture. Bottlenecks in the architecture are pointed out, and improvements are being made and their effects assessed quantitatively. The results show that RSM efficiency is encouragingly high, even in a non-optimized architecture. We propose architectural features to support RSM and conclude that RSM may indeed be a feasible shared-memory implementation in future massively parallel computers.}, issn = {3-540-57307-0}, language = {EN}, talktype = {none} } @InProceedings{Hellwagner1992, author = {Hellwagner, Hermann}, booktitle = {Parallel Processing: CONPAR 92 - VAPP V, Second Joint International Conference on Vector and Parallel Processing}, title = {On the Practical Efficiency of Randomized Shared Memory}, year = {1992}, address = {Berlin-Heidelberg}, editor = {Bougé, Luc and Cosnard, Michel and Robert, Yves and Trystram, Denis}, month = sep, pages = {429-440}, publisher = {Springer}, series = {LNCS}, abstract = {This paper analyzes the efficiency of Randomized Shared Memory (RSM) in terms of constant factors. RSM or memory hashing, that is, pseudorandom distribution of global memory addresses throughout local memories in a distributed-memory parallel system, has been proven to enable an (asymptotically) optimally efficient implementation of scalable and universal shared memory. High memory access latencies are hidden through massive parallelism. Our work examines the practical relevance and feasibility of this potentially significant theoretical result. After an introduction of the background, principles, and desirable properties of RSM and an outline of the approach to determine RSM efficiency, the major results of our simulations are presented. The results show that RSM efficiency is encouragingly high (up to 20% efficiency of idealized shared memory), even in an architecture modelled on the basis of state-of-the-art technology. Performance-limiting factors are identified from the results and architectural features to increase efficiency are proposed, most notably extremely fast process switching and a combining network. Several novel machine designs document the increased interest in RSM and hardware support.}, issn = {3-540-55895-0}, language = {EN}, talktype = {none} } @InProceedings{Boeszoermenyi1992, author = {Böszörmenyi, Laszlo}, booktitle = {Proceedings of the 7th Joint Conference of the Austrian Computer Society (OCG) and the John von Neumann Society for Computing Sciences (NJSZT), Klagenfurt, 1992}, title = {A Comparison of Modula-3 and Oberon-2}, year = {1992}, address = {Berlin, Heidelberg, New York}, editor = {Mittermeir, Roland}, month = {jan}, pages = {126-137}, publisher = {Springer}, abstract = {Proceedings of the 7th Joint Conference of the Austrian Computer Society (OCG) and the John von Neumann Society for Computing Sciences (NJSZT), Klagenfurt, 1992.}, issn = {3211824081}, language = {EN}, location = {Klagenfurt}, talkdate = {--}, talktype = {none} }