% Type: Article % Encoding: utf-8 @Article{Verma2021, author = {Pawan Kumar Verma and Prateek Agrawal and Ivone Amorim and Radu Prodan}, journal = {IEEE Transactions on Computational Social Systems}, title = {{WELFake: Word Embedding Over Linguistic Features for Fake News Detection}}, year = {2021}, issn = {2329-924X}, month = {aug}, number = {4}, pages = {881--893}, volume = {8}, abstract = {Social media is a popular medium for the dissemination of real-time news all over the world. Easy and quick information proliferation is one of the reasons for its popularity. An extensive number of users with different age groups, gender, and societal beliefs are engaged in social media websites. Despite these favorable aspects, a significant disadvantage comes in the form of fake news, as people usually read and share information without caring about its genuineness. Therefore, it is imperative to research methods for the authentication of news. To address this issue, this article proposes a two-phase benchmark model named WELFake based on word embedding (WE) over linguistic features for fake news detection using machine learning classification. The first phase preprocesses the data set and validates the veracity of news content by using linguistic features. The second phase merges the linguistic feature sets with WE and applies voting classification. To validate its approach, this article also carefully designs a novel WELFake data set with approximately 72,000 articles, which incorporates different data sets to generate an unbiased classification output. Experimental results show that the WELFake model categorizes the news in real and fake with a 96.73% which improves the overall accuracy by 1.31% compared to bidirectional encoder representations from transformer (BERT) and 4.25% compared to convolutional neural network (CNN) models. Our frequency-based and focused analyzing writing patterns model outperforms predictive-based related works implemented using the Word2vec WE method by up to 1.73%.}, doi = {10.1109/tcss.2021.3068519}, keywords = {Bidirectional encoder representations from transformer (BERT), convolutional neural network (CNN), fake news, linguistic feature, machine learning (ML), text classification, voting classifier, word embedding (WE)}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9395133} } @Article{Timmerer2021, author = {Christian Timmerer and Mathias Wien and Lu Yu and Amy Reibman}, journal = {Proceedings of the IEEE}, title = {{Special issue on Open Media Compression: Overview, Design Criteria, and Outlook on Emerging Standards}}, year = {2021}, issn = {1558-2256}, month = {sep}, number = {9}, pages = {1423--1434}, volume = {109}, abstract = {Universal access to and provisioning of multimedia content is now a reality. It is easy to generate, distribute, share, and consume any multimedia content, anywhere, anytime, or any device. Open media standards took a crucial role toward enabling all these use cases leading to a plethora of applications and services that have now become a commodity in our daily life. Interestingly, most of these services adopt a streaming paradigm, are typically deployed over the open, unmanaged Internet, and account for most of today’s Internet traffic. Currently, the global video traffic is greater than 60% of all Internet traffic [1], and it is expected that this share will grow to more than 80% in the near future [2]. In addition, Nielsen’s law of Internet bandwidth states that the users’ bandwidth grows by 50% per year, which roughly fits data from 1983 to 2019 [3]. Thus, the users’ bandwidth can be expected to reach approximately 1 Gb/s by 2022. At the same time, network applications will grow and utilize the bandwidth provided, just like programs and their data expand to fill the memory available in a computer system. Most of the available bandwidth today is consumed by video applications, and the amount of data is further increasing due to already established and emerging applications, e.g., ultrahigh definition, high dynamic range, or virtual, augmented, mixed realities, or immersive media applications in general.}, doi = {10.1109/jproc.2021.3098048}, keywords = {Special issues and sections, Video coding, Video compression, Media, Streaming media, Transform coding, Virtual reality, Mixed reality, Internet}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9519598} } @Article{Taraghi2021a, author = {Babak Taraghi and Minh Nguyen and Hadi Amirpour and Christian Timmerer}, journal = {IEEE Access}, title = {{Intense: In-Depth Studies on Stall Events and Quality Switches and Their Impact on the Quality of Experience in {HTTP} Adaptive Streaming}}, year = {2021}, issn = {2169-3536}, month = aug, pages = {118087--118098}, volume = {9}, abstract = {With the recent growth of multimedia traffic over the Internet and emerging multimedia streaming service providers, improving Quality of Experience (QoE) for HTTP Adaptive Streaming (HAS) becomes more important. Alongside other factors, such as the media quality, HAS relies on the performance of the media player’s Adaptive Bitrate (ABR) algorithm to optimize QoE in multimedia streaming sessions. QoE in HAS suffers from weak or unstable internet connections and suboptimal ABR decisions. As a result of imperfect adaptiveness to the characteristics and conditions of the internet connection, stall events and quality level switches could occur and with different durations that negatively affect the QoE. In this paper, we address various identified open issues related to the QoE for HAS, notably (i) the minimum noticeable duration for stall events in HAS; (ii) the correlation between the media quality and the impact of stall events on QoE; (iii) the end-user preference regarding multiple shorter stall events versus a single longer stall event; and (iv) the end-user preference of media quality switches over stall events. Therefore, we have studied these open issues from both objective and subjective evaluation perspectives and presented the correlation between the two types of evaluations. The findings documented in this paper can be used as a baseline for improving ABR algorithms and policies in HAS.}, doi = {10.1109/access.2021.3107619}, keywords = {Crowdsourcing, HTTP adaptive streaming, quality of experience, quality switches, stall events, subjective evaluation, objective evaluation}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9521894} } @Article{Sokolova2021, author = {Natalia Sokolova and Klaus Schoeffmann and Mario Taschwer and Stephanie Sarny and Doris Putzgruber-Adamitsch and Yosuf El-Shabrawi}, journal = {PLOS ONE}, title = {{Automatic detection of pupil reactions in cataract surgery videos}}, year = {2021}, issn = {1932-6203}, month = {oct}, number = {10}, pages = {e0258390}, volume = {16}, abstract = {In the light of an increased use of premium intraocular lenses (IOL), such as EDOF IOLs, multifocal IOLs or toric IOLs even minor intraoperative complications such as decentrations or an IOL tilt, will hamper the visual performance of these IOLs. Thus, the post-operative analysis of cataract surgeries to detect even minor intraoperative deviations that might explain a lack of a post-operative success becomes more and more important. Up-to-now surgical videos are evaluated by just looking at a very limited number of intraoperative data sets, or as done in studies evaluating the pupil changes that occur during surgeries, in a small number intraoperative picture only. A continuous measurement of pupil changes over the whole surgery, that would achieve clinically more relevant data, has not yet been described. Therefore, the automatic retrieval of such events may be a great support for a post-operative analysis. This would be especially true if large data files could be evaluated automatically. In this work, we automatically detect pupil reactions in cataract surgery videos. We employ a Mask R-CNN architecture as a segmentation algorithm to segment the pupil and iris with pixel-based accuracy and then track their sizes across the entire video. We can detect pupil reactions with a harmonic mean (H) of Recall, Precision, and Ground Truth Coverage Rate (GTCR) of 60.9% and average prediction length (PL) of 18.93 seconds. However, we consider the best configuration for practical use the one with the H value of 59.4% and PL of 10.2 seconds, which is much shorter. We further investigate the generalization ability of this method on a slightly different dataset without retraining the model. In this evaluation, we achieve the H value of 49.3% with the PL of 18.15 seconds.}, doi = {10.1371/journal.pone.0258390}, editor = {Andreas Wedrich}, publisher = {Public Library of Science (PLoS)}, url = {https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0258390} } @Article{Saurabh2021, author = {Nishant Saurabh and Carlos Rubia and Anandakumar Palanisamy and Spiros Koulouzis and Mirsat Sefidanoski and Antorweep Chakravorty and Zhiming Zhao and Aleksandar Karadimce and Radu Prodan}, journal = {Blockchain: Research and Applications}, title = {{The ARTICONF Approach to Decentralized Car-Sharing}}, year = {2021}, issn = {2096-7209}, month = {may}, pages = {1--37}, 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 [1] 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 that address 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 decentralized application (DApp) use case, 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 DApp and illustrate through real snapshots how the different ARTICONF tools support it in a simulated scenario.}, doi = {10.1016/j.bcra.2021.100013}, keywords = {Social media, car-sharing, decentralization, blockchain}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/pii/S2096720921000087?via=ihub} } @Article{Rossetto2021, author = {Luca Rossetto and Ralph Gasser and Jakub Lokoc and Werner Bailer and Klaus Schoeffmann and Bernd Muenzer and Tomas Soucek and Phuong Anh Nguyen and Paolo Bolettieri and Andreas Leibetseder and Stefanos Vrochidis}, journal = {IEEE Transactions on Multimedia}, title = {{Interactive Video Retrieval in the Age of Deep Learning - Detailed Evaluation of VBS 2019}}, year = {2021}, issn = {1941-0077}, month = mar, pages = {243--256}, volume = {23}, abstract = {Despite the fact that automatic content analysis has made remarkable progress over the last decade - mainly due to significant advances in machine learning - interactive video retrieval is still a very challenging problem, with an increasing relevance in practical applications. The Video Browser Showdown (VBS) is an annual evaluation competition that pushes the limits of interactive video retrieval with state-of-the-art tools, tasks, data, and evaluation metrics. In this paper, we analyse the results and outcome of the 8th iteration of the VBS in detail. We first give an overview of the novel and considerably larger V3C1 dataset and the tasks that were performed during VBS 2019. We then go on to describe the search systems of the six international teams in terms of features and performance. And finally, we perform an in-depth analysis of the per-team success ratio and relate this to the search strategies that were applied, the most popular features, and problems that were experienced. A large part of this analysis was conducted based on logs that were collected during the competition itself. This analysis gives further insights into the typical search behavior and differences between expert and novice users. Our evaluation shows that textual search and content browsing are the most important aspects in terms of logged user interactions. Furthermore, we observe a trend towards deep learning based features, especially in the form of labels generated by artificial neural networks. But nevertheless, for some tasks, very specific content-based search features are still being used. We expect these findings to contribute to future improvements of interactive video search systems.}, doi = {10.1109/tmm.2020.2980944}, keywords = {Interactive Video Retrieval, Video Browsing, Video Content Analysis, Content-based Retrieval, Evaluations}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9037125} } @Article{Ross2021, author = {Tobias Ross and Annika Reinke and Peter M. Full and Martin Wagner and Hannes Kenngott and Martin Apitz and Hellena Hempe and Diana Mindroc-Filimon and Patrick Scholz and Thuy Nuong Tran and Pierangela Bruno and Pablo Arbeláez and Gui-Bin Bian and Sebastian Bodenstedt and Jon Lindström Bolmgren and Laura Bravo-Sánchez and Hua-Bin Chen and Cristina González and Dong Guo and Paal Halvorsen and Pheng-Ann Heng and Enes Hosgor and Zeng-Guang Hou and Fabian Isensee and Debesh Jha and Tingting Jiang and Yueming Jin and Kadir Kirtac and Sabrina Kletz and Stefan Leger and Zhixuan Li and Klaus H. Maier-Hein and Zhen-Liang Ni and Michael A. Riegler and Klaus Schoeffmann and Ruohua Shi and Stefanie Speidel and Michael Stenzel and Isabell Twick and Gutai Wang and Jiacheng Wang and Liansheng Wang and Lu Wang and Yujie Zhang and Yan-Jie Zhou and Lei Zhu and Manuel Wiesenfarth and Annette Kopp-Schneider and Beat P. Müller-Stich and Lena Maier-Hein}, journal = {Medical Image Analysis}, title = {{Comparative validation of multi-instance instrument segmentation in endoscopy: Results of the ROBUST-MIS 2019 challenge}}, year = {2021}, issn = {1361-8415}, month = {may}, number = {66}, pages = {1--62}, volume = {70}, abstract = {Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization; algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions. In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts).}, doi = {10.1016/j.media.2020.101920}, keywords = {Multi-instance instrument, minimally invasive surgery, robustness and generalization, surgical data science}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/pii/S136184152030284X} } @Article{Ristov2021, author = {Sasko Ristov and Thomas Fahringer and Radu Prodan and Magdalena Kostoska and Marjan Gusev and Schahram Dustdar}, journal = {IEEE Internet Computing}, title = {{Inter-host Orchestration Platform Architecture for Ultra-scale Cloud Applications}}, year = {2021}, issn = {1941-0131}, pages = {1--1}, abstract = {Cloud data centers exploit many memory page management techniques that reduce the total memory utilization and access time. Mainly these techniques are applied to a hypervisor in a single host (intra-hypervisor) without the possibility to exploit the knowledge obtained by a group of hosts (clusters). We introduce a novel inter-hypervisor orchestration platform to provide intelligent memory page management for horizontal scaling. It will use the performance behavior of faster virtual machines to activate pre-fetching mechanisms that reduce the number of page faults. The overall platform consists of five modules - profiler, collector, classifier, predictor, and pre-fetcher. We developed and deployed a prototype of the platform, which comprises the first three modules. The evaluation shows that data collection is feasible in real-time, which means that if our approach is used on top of the existing memory page management techniques, it can significantly lower the miss rate that initiates page faults.}, doi = {10.1109/mic.2020.3034293}, keywords = {Cloud infrastructure, memory access management, page faults, pre-fetching, virtualiziation, XEN}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9245504} } @Article{Rinner2021, author = {Bernhard Rinner and Christian Bettstetter and Hellwagner, Hermann and Stephan Weiss}, journal = {Computer}, title = {{Multidrone Systems: More Than the Sum of the Parts}}, year = {2021}, issn = {0018-9162}, month = {may}, number = {5}, pages = {34--43}, volume = {54}, abstract = {Now that drones have evolved from bulky platforms to agile devices, a challenge is to combine multiple drones into an integrated autonomous system, offering functionality that individual drones cannot achieve. Such multidrone systems require connectivity, communication, and coordination. We discuss these building blocks along with case studies and lessons learned.}, doi = {10.1109/mc.2021.3058441}, keywords = {Autonomous systems, Drones}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9427128} } @Article{Moll2021, author = {Philipp Moll and Selina Isak and Hellwagner, Hermann and Jeff Burke}, journal = {Computer Networks}, title = {{A Quadtree-based synchronization protocol for inter-server game state synchronization}}, year = {2021}, issn = {1389-1286}, month = {feb}, pages = {107723}, volume = {185}, abstract = {Online games are a fundamental part of the entertainment industry but the current IP infrastructure does not satisfactorily fulfill the needs of these services. The novel networking architecture Named Data Networking (NDN) inherently supports network-level multicast and packet-level security and thereby introduces promising features for online games. In this paper, we propose an NDN-based approach to synchronize game state in a server cluster, a task necessary to allow multiple players in large numbers to play in the same game world. The proposed Quadtree Synchronization Protocol applies NDN’s data-centric nature to decouple the game world from the game servers hosting it. This means that requesting changes of a specific game world region becomes possible without knowing which game server is responsible for the requested region. We use a hierarchic game world structure when requesting data that allows the network to forward requests to the responsible game server without directly addressing it. This region-based naming scheme decouples world regions from servers which eases the management of the game server cluster and allows easier recovery after server failures. In addition, this decoupling allows exchanging information about a geographical region, such as a game world, without knowledge of the other participants changing the world. Such a region-based synchronization mode is not possible to implement with existing protocols. However, it allows building distributed systems that do not require a central server to work. Besides architectural benefits, network emulations show that our protocol increases the efficiency of data transport by utilizing network-level multicast. Our proposed approach can keep up with current protocols which can be used for inter-server game state synchronization.}, doi = {10.1016/j.comnet.2020.107723}, keywords = {Named Data Networking, Distributed dataset synchronization, Online games}, publisher = {Elsevier {BV}}, url = {https://www.sciencedirect.com/science/article/pii/S1389128620313177} } @Article{Madaan2021, author = {Vishu Madaan and Aditya Roy and Charu Gupta and Prateek Agrawal and Anand Sharma and Cristian Bologa and Radu Prodan}, journal = {New Generation Computing}, title = {{XCOVNet: Chest X-ray Image Classification for COVID-19 Early Detection Using Convolutional Neural Networks}}, year = {2021}, issn = {1882-7055}, month = {feb}, pages = {1--15}, abstract = {COVID-19 (also known as SARS-COV-2) pandemic has spread in the entire world. It is a contagious disease that easily spreads from one person in direct contact to another, classified by experts in five categories: asymptomatic, mild, moderate, severe, and critical. Already more than 66 million people got infected worldwide with more than 22 million active patients as of 5 December 2020 and the rate is accelerating. More than 1.5 million patients (approximately 2.5% of total reported cases) across the world lost their life. In many places, the COVID-19 detection takes place through reverse transcription polymerase chain reaction (RT-PCR) tests which may take longer than 48 h. This is one major reason of its severity and rapid spread. We propose in this paper a two-phase X-ray image classification called XCOVNet for early COVID-19 detection using convolutional neural Networks model. XCOVNet detects COVID-19 infections in chest X-ray patient images in two phases. The first phase pre-processes a dataset of 392 chest X-ray images of which half are COVID-19 positive and half are negative. The second phase trains and tunes the neural network model to achieve a 98.44% accuracy in patient classification.}, doi = {10.1007/s00354-021-00121-7}, keywords = {Coronavirus, SARS-COV-2, COVID-19 disease diagnosis, Machine learning, Image classification}, publisher = {Springer Science and Business Media LLC}, url = {https://link.springer.com/article/10.1007/s00354-021-00121-7} } @Article{Lokoc2021, author = {Jakub Lokoc and Patrik Vesely and Frantisek Mejzlik and Gregor Kovalcik and Tomas Soucek and Luca Rossetto and Klaus Schoeffmann and Werner Bailer and Cathal Gurrin and Loris Sauter and Jaeyub Song and Stefanos Vrochidis and Jiaxin Wu and Björn Thor Jonsson}, journal = {ACM Transactions on Multimedia Computing, Communications, and Applications}, title = {{Is the Reign of Interactive Search Eternal? Findings from the Video Browser Showdown 2020}}, year = {2021}, issn = {1551-6865}, month = {jul}, number = {3}, pages = {1--26}, volume = {17}, abstract = {Comprehensive and fair performance evaluation of information retrieval systems represents an essential task for the current information age. Whereas Cranfield-based evaluations with benchmark datasets support development of retrieval models, significant evaluation efforts are required also for user-oriented systems that try to boost performance with an interactive search approach. This article presents findings from the 9th Video Browser Showdown, a competition that focuses on a legitimate comparison of interactive search systems designed for challenging known-item search tasks over a large video collection. During previous installments of the competition, the interactive nature of participating systems was a key feature to satisfy known-item search needs, and this article continues to support this hypothesis. Despite the fact that top-performing systems integrate the most recent deep learning models into their retrieval process, interactive searching remains a necessary component of successful strategies for known-item search tasks. Alongside the description of competition settings, evaluated tasks, participating teams, and overall results, this article presents a detailed analysis of query logs collected by the top three performing systems, SOMHunter, VIRET, and vitrivr. The analysis provides a quantitative insight to the observed performance of the systems and constitutes a new baseline methodology for future events. The results reveal that the top two systems mostly relied on temporal queries before a correct frame was identified. An interaction log analysis complements the result log findings and points to the importance of result set and video browsing approaches. Finally, various outlooks are discussed in order to improve the Video Browser Showdown challenge in the future.}, doi = {10.1145/3445031}, keywords = {Interactive video retrieval, deep learning, interactive search evaluation}, publisher = {Association for Computing Machinery (ACM)}, url = {https://dl.acm.org/doi/10.1145/3445031} } @Article{Kimovski2021c, author = {Dragi Kimovski and Roland Matha and Josef Hammer and Narges Mehran and Hellwagner, Hermann and Radu Prodan}, journal = {IEEE Internet Computing}, title = {{Cloud, Fog, or Edge: Where to Compute?}}, year = {2021}, issn = {1941-0131}, month = {jul}, number = {4}, pages = {30--36}, volume = {25}, abstract = {The computing continuum extends the high-performance cloud data centers with energy-efficient and low-latency devices close to the data sources located at the edge of the network. However, the heterogeneity of the computing continuum raises multiple challenges related to application management. These include where to offload an application – from the cloud to the edge – to meet its computation and communication requirements. To support these decisions, we provide in this article a detailed performance and carbon footprint analysis of a selection of use case applications with complementary resource requirements across the computing continuum over a real-life evaluation testbed.}, doi = {10.1109/mic.2021.3050613}, keywords = {Edge computing, Cloud computing, Benchmarking, Carbon footprint}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9321525} } @Article{Kimovski2021b, author = {Dragi Kimovski and Narges Mehran and Christopher Emanuel Kerth and Radu Prodan}, journal = {IEEE Transactions on Services Computing}, title = {{Mobility-Aware IoT Applications Placement in the Cloud Edge Continuum}}, year = {2021}, issn = {2372-0204}, month = jul, pages = {1--14}, abstract = {The Edge computing extension of the Cloud services towards the network boundaries raises important placement challenges for IoT applications running in a heterogeneous environment with limited computing capacities. Unfortunately, existing works only partially address this challenge by optimizing a single or aggregate objective (e.g., response time) and not considering the edge devices' mobility and resource constraints. To address this gap, we propose a novel mobility-aware multi-objective IoT application placement (mMAPO) method in the Cloud -- Edge Continuum that optimizes completion time, energy consumption, and economic cost as conflicting objectives. mMAPO utilizes a Markov model for predictive analysis of the Edge device mobility and constrains the optimization to devices that do not frequently move through the network. We evaluate the quality of the mMAPO placements using simulation and real-world experimentation on two IoT applications. Compared to related work, mMAPO reduces the economic cost by 28% and decreases the completion time by 80% while maintaining a stable energy consumption.}, doi = {10.1109/tsc.2021.3094322}, keywords = {Cloud-Edge Continuum, mobility, application placement, multi-objective optimization, energy consumption, cost}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9473013} } @Article{Kimovski2021a, author = {Dragi Kimovski and Roland Matha and Gabriel Iuhasz and Fabrizio Marozzo and Dana Petcu and Radu Prodan}, journal = {Frontiers in Big Data}, title = {{Autotuning of Exascale Applications With Anomalies Detection}}, year = {2021}, issn = {2624-909X}, month = {nov}, pages = {1--14}, volume = {4}, abstract = {The execution of complex distributed applications in exascale systems faces many challenges, as it involves empirical evaluation of countless code variations and application runtime parameters over a heterogeneous set of resources. To mitigate these challenges, the research field of autotuning has gained momentum. The autotuning automates identifying the most desirable application implementation in terms of code variations and runtime parameters. However, the complexity and size of the exascale systems make the autotuning process very difficult, especially considering the number of parameter variations that have to be identified. Therefore, we introduce a novel approach for autotuning exascale applications based on a genetic multi-objective optimization algorithm integrated within the ASPIDE exascale computing framework. The approach considers multi-dimensional search space with support for pluggable objective functions, including execution time and energy requirements. Furthermore, the autotuner employs a machine learning-based event detection approach to detect events and anomalies during application execution, such as hardware failures or communication bottlenecks.}, doi = {10.3389/fdata.2021.657218}, keywords = {exascale computing, autotuning, events and anomalies detection, multi-objective optimization, IoT applications}, publisher = {Frontiers Media (SA)}, url = {https://www.frontiersin.org/articles/10.3389/fdata.2021.657218/full} } @Article{Khalid2021, author = {Yasir Noman Khalid and Muhammad Aleem and Usman Ahmed and Radu Prodan and Muhammad Arshad Islam and Muhammad Azhar Iqbal}, journal = {Computing}, title = {{FusionCL: a machine-learning based approach for OpenCL kernel fusion to increase system performance}}, year = {2021}, issn = {1436-5057}, month = jun, pages = {1--32}, abstract = {Employing general-purpose graphics processing units (GPGPU) with the help of OpenCL has resulted in greatly reducing the execution time of data-parallel applications by taking advantage of the massive available parallelism. However, when a small data size application is executed on GPU there is a wastage of GPU resources as the application cannot fully utilize GPU compute-cores. There is no mechanism to share a GPU between two kernels due to the lack of operating system support on GPU. In this paper, we propose the provision of a GPU sharing mechanism between two kernels that will lead to increasing GPU occupancy, and as a result, reduce execution time of a job pool. However, if a pair of the kernel is competing for the same set of resources (i.e., both applications are compute-intensive or memory-intensive), kernel fusion may also result in a significant increase in execution time of fused kernels. Therefore, it is pertinent to select an optimal pair of kernels for fusion that will result in significant speedup over their serial execution. This research presents FusionCL, a machine learning-based GPU sharing mechanism between a pair of OpenCL kernels. FusionCL identifies each pair of kernels (from the job pool), which are suitable candidates for fusion using a machine learning-based fusion suitability classifier. Thereafter, from all the candidates, it selects a pair of candidate kernels that will produce maximum speedup after fusion over their serial execution using a fusion speedup predictor. The experimental evaluation shows that the proposed kernel fusion mechanism reduces execution time by 2.83× when compared to a baseline scheduling scheme. When compared to state-of-the-art, the reduction in execution time is up to 8%.}, doi = {10.1007/s00607-021-00958-2}, keywords = {Scheduling, Kernel fusion, High-performance computing, Machine learning}, publisher = {Springer Science and Business Media LLC}, url = {https://link.springer.com/article/10.1007/s00607-021-00958-2} } @Article{Karandikar_2021, author = {Nikita Karandikar and Rockey Abhishek and Nishant Saurabh and Zhiming Zhao and Alexander Lercher and Ninoslav Marina and Radu Prodan and Chunming Rong and Antorweep Chakravorty}, journal = {Blockchain: Research and Applications}, title = {Blockchain-based prosumer incentivization for peak mitigation through temporal aggregation and contextual clustering.1}, year = {2021}, issn = {2096-7209}, month = jun, pages = {1--35}, abstract = {Peak mitigation is of interest to power companies as peak periods may require the operator to over provision supply in order to meet the peak demand. Flattening the usage curve can result in cost savings, both for the power companies and the end users. Integration of renewable energy into the energy infrastructure presents an opportunity to use excess renewable generation to supplement supply and alleviate peaks. In addition, demand side management can shift the usage from peak to off peak times and reduce the magnitude of peaks. In this work, we present a data driven approach for incentive based peak mitigation. Understanding user energy profiles is an essential step in this process. We begin by analysing a popular energy research dataset published by the Ausgrid corporation. Extracting aggregated user energy behavior in temporal contexts and semantic linking and contextual clustering give us insight into consumption and rooftop solar generation patterns. We implement, and performance test a blockchain based prosumer incentivization system. The smart contract logic is based on our analysis of the Ausgrid dataset. Our implementation is capable of supporting 792,540 customers with a reasonably low infrastructure footprint.}, doi = {10.1016/j.bcra.2021.100016}, keywords = {Peak shaving, aggregation analysis, contextual clustering, blockchain, incentivization}, publisher = {Elsevier (BV)}, url = {https://www.sciencedirect.com/science/article/pii/S2096720921000117?via=ihub} } @Article{Jha2021, author = {Debesh Jha and Sharib Ali and Steven Hicks and Vajira Thambawita and Hanna Borgli and Pia H. Smedsrud and Thomas de Lange and Konstantin Pogorelov and Xiaowei Wang and Philipp Harzig and Minh-Triet Tran and Wenhua Meng and Trung-Hieu Hoang and Danielle Dias and Tobey H. Ko and Taruna Agrawal and Olga Ostroukhova and Zeshan Khan and Muhammad Atif Tahir and Yang Liu and Yuan Chang and Mathias Kirkerod and Dag Johansen and Mathias Lux and Haavard D. Johansen and Michael A. Riegler and Paal Halvorsen}, journal = {Medical Image Analysis}, title = {{A comprehensive analysis of classification methods in gastrointestinal endoscopy imaging}}, year = {2021}, issn = {1361-8415}, month = {may}, pages = {102007}, volume = {70}, abstract = {Gastrointestinal (GI) endoscopy has been an active field of research motivated by the large number of highly lethal GI cancers. Early GI cancer precursors are often missed during the endoscopic surveillance. The high missed rate of such abnormalities during endoscopy is thus a critical bottleneck. Lack of attentiveness due to tiring procedures, and requirement of training are few contributing factors. An automatic GI disease classification system can help reduce such risks by flagging suspicious frames and lesions. GI endoscopy consists of several multi-organ surveillance, therefore, there is need to develop methods that can generalize to various endoscopic findings. In this realm, we present a comprehensive analysis of the Medico GI challenges: Medical Multimedia Task at MediaEval 2017, Medico Multimedia Task at MediaEval 2018, and BioMedia ACM MM Grand Challenge 2019. These challenges are initiative to set-up a benchmark for different computer vision methods applied to the multi-class endoscopic images and promote to build new approaches that could reliably be used in clinics. We report the performance of 21 participating teams over a period of three consecutive years and provide a detailed analysis of the methods used by the participants, highlighting the challenges and shortcomings of the current approaches and dissect their credibility for the use in clinical settings. Our analysis revealed that the participants achieved an improvement on maximum Mathew correlation coefficient (MCC) from 82.68% in 2017 to 93.98% in 2018 and 95.20% in 2019 challenges, and a significant increase in computational speed over consecutive years.}, doi = {10.1016/j.media.2021.102007}, keywords = {Gastrointestinal endoscopy challenges, Artificial intelligence, Computer-aided detection and diagnosis, Medical imaging, Medico Task 2017, Medico Task 2018, BioMedia 2019 grand challenge}, publisher = {Elsevier (BV)}, url = {https://www.sciencedirect.com/science/article/pii/S1361841521000530?via=ihub} } @Article{Hayat2021, author = {Samira Hayat and Roland Jung and Hellwagner, Hermann and Christian Bettstetter and Driton Emini and Dominik Schnieders}, journal = {IEEE Robotics and Automation Letters}, title = {{Edge Computing in 5G for Drone Navigation: What to Offload?}}, year = {2021}, issn = {2377-3766}, month = {apr}, number = {2}, pages = {2571--2578}, volume = {6}, abstract = {Small drones that navigate using cameras may be limited in their speed and agility by low onboard computing power. We evaluate the role of edge computing in 5G for such autonomous navigation. The offloading of image processing tasks to an edge server is studied with a vision-based navigation algorithm. Three computation modes are compared: onboard, fully offloaded to the edge, and partially offloaded. Partial offloading is expected to pose lower demands on the communication network in terms of transfer rate than full offloading but requires some onboard processing. Our results on the computation time help select the most suitable mode for image processing, i.e., whether and what to offload, based on the network conditions.}, doi = {10.1109/lra.2021.3062319}, keywords = {Aerial systems, autonomous vehicle navigation, perception and autonomy, vision-based navigation}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9363523} } @Article{Erfanian2021a, author = {Alireza Erfanian and Hadi Amirpour and Farzad Tashtarian and Christian Timmerer and Hellwagner, Hermann}, journal = {IEEE Access}, title = {{LwTE: Light-Weight Transcoding at the Edge}}, year = {2021}, issn = {2169-3536}, month = aug, pages = {112276--112289}, volume = {9}, abstract = {Due to the growing demand for video streaming services, providers have to deal with increasing resource requirements for increasingly heterogeneous environments. To mitigate this problem, many works have been proposed which aim to ( i ) improve cloud/edge caching efficiency, (ii) use computation power available in the cloud/edge for on-the-fly transcoding, and (iii) optimize the trade-off among various cost parameters, e.g., storage, computation, and bandwidth. In this paper, we propose LwTE, a novel L ight- w eight T ranscoding approach at the E dge, in the context of HTTP Adaptive Streaming (HAS). During the encoding process of a video segment at the origin side, computationally intense search processes are going on. The main idea of LwTE is to store the optimal results of these search processes as metadata for each video bitrate and reuse them at the edge servers to reduce the required time and computational resources for on-the-fly transcoding. LwTE enables us to store only the highest bitrate plus corresponding metadata (of very small size) for unpopular video segments/bitrates. In this way, in addition to the significant reduction in bandwidth and storage consumption, the required time for on-the-fly transcoding of a requested segment is remarkably decreased by utilizing its corresponding metadata; unnecessary search processes are avoided. Popular video segments/bitrates are being stored. We investigate our approach for Video-on-Demand (VoD) streaming services by optimizing storage and computation (transcoding) costs at the edge servers and then compare it to conventional methods (store all bitrates, partial transcoding). The results indicate that our approach reduces the transcoding time by at least 80% and decreases the aforementioned costs by 12% to 70% compared to the state-of-the-art approaches.}, doi = {10.1109/access.2021.3102633}, keywords = {Video Streaming, transcoding, video on demand, edge computing}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9507473} } @Article{Erfanian2021, author = {Alireza Erfanian and Farzad Tashtarian and Anatoliy Zabrovskiy and Christian Timmerer and Hellwagner, Hermann}, journal = {IEEE Transactions on Network and Service Management}, title = {{OSCAR: On Optimizing Resource Utilization in Live Video Streaming}}, year = {2021}, issn = {1932-4537}, month = {mar}, number = {1}, pages = {552--569}, volume = {18}, abstract = {Live video streaming traffic and related applications have experienced significant growth in recent years. However, this has been accompanied by some challenging issues, especially in terms of resource utilization. Although IP multicasting can be recognized as an efficient mechanism to cope with these challenges, it suffers from many problems. Applying software-defined networking (SDN) and network function virtualization (NFV) technologies enable researchers to cope with IP multicasting issues in novel ways. In this article, by leveraging the SDN concept, we introduce OSCAR (Optimizing reSourCe utilizAtion in live video stReaming) as a new cost-aware video streaming approach to provide advanced video coding (AVC)-based live streaming services in the network. In this article, we use two types of virtualized network functions (VNFs): virtual reverse proxy (VRP) and virtual transcoder function (VTF). At the edge of the network, VRPs are responsible for collecting clients’ requests and sending them to an SDN controller. Then, by executing a mixed-integer linear program (MILP), the SDN controller determines a group of optimal multicast trees for streaming the requested videos from an appropriate origin server to the VRPs. Moreover, to elevate the efficiency of resource allocation and meet the given end-to-end latency threshold, OSCAR delivers only the highest requested quality from the origin server to an optimal group of VTFs over a multicast tree. The selected VTFs then transcode the received video segments and transmit them to the requesting VRPs in a multicast fashion. To mitigate the time complexity of the proposed MILP model, we present a simple and efficient heuristic algorithm that determines a near-optimal solution in polynomial time. Using the MiniNet emulator, we evaluate the performance of OSCAR in various scenarios. The results show that OSCAR surpasses other SVC- and AVC-based multicast and unicast approaches in terms of cost and resource utilization.}, doi = {10.1109/tnsm.2021.3051950}, keywords = {Dynamic adaptive streaming over HTTP (DASH), live video streaming, software defined networking (SDN), video transcoding, network function virtualization (NFV)}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9327491} } @Article{Cetinkaya2021a, author = {Ekrem Cetinkaya and Hadi Amirpour and Christian Timmerer and Mohammad Ghanbari}, journal = {IEEE Open Journal of Signal Processing}, title = {{Fast Multi-Resolution and Multi-Rate Encoding for HTTP Adaptive Streaming Using Machine Learning}}, year = {2021}, issn = {2644-1322}, month = jun, pages = {1--12}, abstract = {Video streaming applications keep getting more attention over the years, and HTTP Adaptive Streaming (HAS) became the de-facto solution for video delivery over the Internet. In HAS, each video is encoded at multiple quality levels and resolutions (i.e., representations) to enable adaptation of the streaming session to viewing and network conditions of the client. This requirement brings encoding challenges along with it, e.g., a video source should be encoded efficiently at multiple bitrates and resolutions. Fast multi-rate encoding approaches aim to address this challenge of encoding multiple representations from a single video by re-using information from already encoded representations. In this paper, a convolutional neural network is used to speed up both multi-rate and multi-resolution encoding for HAS. For multi-rate encoding, the lowest bitrate representation is chosen as the reference. For multi-resolution encoding, the highest bitrate from the lowest resolution representation is chosen as the reference. Pixel values from the target resolution and encoding information from the reference representation are used to predict Coding Tree Unit (CTU) split decisions in High-Efficiency Video Coding (HEVC) for dependent representations. Experimental results show that the proposed method for multi-rate encoding can reduce the overall encoding time by 15.08 % and parallel encoding time by 41.26 %, with a 0.89 % bitrate increase compared to the HEVC reference software. Simultaneously, the proposed method for multi-resolution encoding can reduce the encoding time by 46.27 % for the overall encoding and 27.71 % for the parallel encoding on average with a 2.05 % bitrate increase.}, doi = {10.1109/ojsp.2021.3078657}, keywords = {HTTP Adaptive Streaming, HEVC, Multirate Encoding, Machine Learning}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9427195} } @Article{Cetinkaya2021, author = {Ekrem Cetinkaya and Hadi Amirpour and Mohammad Ghanbari and Christian Timmerer}, journal = {Signal Processing: Image Communication}, title = {{CTU depth decision algorithms for HEVC: A survey}}, year = {2021}, issn = {0923-5965}, month = {nov}, pages = {116442}, volume = {99}, abstract = {High Efficiency Video Coding (HEVC) surpasses its predecessors in encoding efficiency by introducing new coding tools at the cost of an increased encoding time-complexity. The Coding Tree Unit (CTU) is the main building block used in HEVC. In the HEVC standard, frames are divided into CTUs with the predetermined size of up to 64 × 64 pixels. Each CTU is then divided recursively into a number of equally sized square areas, known as Coding Units (CUs). Although this diversity of frame partitioning increases encoding efficiency, it also causes an increase in the time complexity due to the increased number of ways to find the optimal partitioning. To address this complexity, numerous algorithms have been proposed to eliminate unnecessary searches during partitioning CTUs by exploiting the correlation in the video. In this paper, existing CTU depth decision algorithms for HEVC are surveyed. These algorithms are categorized into two groups, namely statistics and machine learning approaches. Statistics approaches are further subdivided into neighboring and inherent approaches. Neighboring approaches exploit the similarity between adjacent CTUs to limit the depth range of the current CTU, while inherent approaches use only the available information within the current CTU. Machine learning approaches try to extract and exploit similarities implicitly. Traditional methods like support vector machines or random forests use manually selected features, while recently proposed deep learning methods extract features during training. Finally, this paper discusses extending these methods to more recent video coding formats such as Versatile Video Coding (VVC) and AOMedia Video 1(AV1).}, doi = {10.1016/j.image.2021.116442}, keywords = {HEVC, Coding tree unit, Complexity, CTU partitioning, Statistics, Machine learning}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/pii/S0923596521002113} } @Article{Barcis2021, author = {Michal Barcis and Agata Barcis and Nikolaos Tsiogkas and Hellwagner, Hermann}, journal = {Frontiers in Robotics and AI}, title = {{Information Distribution in Multi-Robot Systems: Generic, Utility-Aware Optimization Middleware}}, year = {2021}, issn = {2296-9144}, month = {jul}, pages = {1--11}, volume = {8}, abstract = {This work addresses the problem of what information is worth sending in a multi-robot system under generic constraints, e.g., limited throughput or energy. Our decision method is based on Monte Carlo Tree Search. It is designed as a transparent middleware that can be integrated into existing systems to optimize communication among robots. Furthermore, we introduce techniques to reduce the decision space of this problem to further improve the performance. We evaluate our approach using a simulation study and demonstrate its feasibility in a real-world environment by realizing a proof of concept in ROS 2 on mobile robots.}, doi = {10.3389/frobt.2021.685105}, keywords = {multi-robot systems, information distribution, adaptive communication, information utility, communication optimization, Monte Carlo tree search}, publisher = {Frontiers Media (SA)}, url = {https://www.frontiersin.org/articles/10.3389/frobt.2021.685105/full} } @Article{Abdullah2021, author = {Fatima Abdullah and Dragi Kimovski and Radu Prodan and Kashif Munir}, journal = {Computing}, title = {Handover authentication latency reduction using mobile edge computing and mobility patterns}, year = {2021}, issn = {1436-5057}, month = {jun}, pages = {1--20}, abstract = {With the advancement in technology and the exponential growth of mobile devices, network traffic has increased manifold in cellular networks. Due to this reason, latency reduction has become a challenging issue for mobile devices. In order to achieve seamless connectivity and minimal disruption during movement, latency reduction is crucial in the handover authentication process. Handover authentication is a process in which the legitimacy of a mobile node is checked when it crosses the boundary of an access network. This paper proposes an efficient technique that utilizes mobility patterns of the mobile node and mobile Edge computing framework to reduce handover authentication latency. The key idea of the proposed technique is to categorize mobile nodes on the basis of their mobility patterns. We perform simulations to measure the networking latency. Besides, we use queuing model to measure the processing time of an authentication query at an Edge servers. The results show that the proposed approach reduces the handover authentication latency up to 54% in comparison with the existing approach.}, doi = {10.1007/s00607-021-00969-z}, keywords = {Mobile edge computing, Handover authentication, Mobility patterns}, publisher = {Springer Science and Business Media (LLC)}, url = {https://link.springer.com/article/10.1007/s00607-021-00969-z} } @Article{Zhao2020, author = {Zhiming Zhao and Ian Taylor and Radu Prodan}, journal = {Future Generation Computer Systems}, title = {{Editorial for FGCS Special issue on "Time-critical Applications on Software-defined Infrastructures"}}, year = {2020}, issn = {0167-739X}, month = {nov}, pages = {1170--1171}, volume = {112}, doi = {10.1016/j.future.2020.07.056}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/abs/pii/S0167739X20324146} } @Article{Versluis2020, author = {Laurens Versluis and Roland Matha and Sacheendra Talluri and Tim Hegeman and Radu Prodan and Ewa Deelman and Alexandru Iosup}, journal = {IEEE Transactions on Parallel and Distributed Systems}, title = {{The Workflow Trace Archive: Open-Access Data From Public and Private Computing Infrastructures}}, year = {2020}, issn = {1045-9219}, month = {sep}, number = {9}, pages = {2170--2184}, volume = {31}, abstract = {Realistic, relevant, and reproducible experiments often need input traces collected from real-world environments. In this work, we focus on traces of workflows—common in datacenters, clouds, and HPC infrastructures. We show that the state-of-the-art in using workflow-traces raises important issues: (1) the use of realistic traces is infrequent and (2) the use of realistic, open-access traces even more so. Alleviating these issues, we introduce the Workflow Trace Archive (WTA), an open-access archive of workflow traces from diverse computing infrastructures and tooling to parse, validate, and analyze traces. The WTA includes >48 million workflows captured from >10 computing infrastructures, representing a broad diversity of trace domains and characteristics. To emphasize the importance of trace diversity, we characterize the WTA contents and analyze in simulation the impact of trace diversity on experiment results. Our results indicate significant differences in characteristics, properties, and workflow structures between workload sources, domains, and fields.}, doi = {10.1109/tpds.2020.2984821}, keywords = {Workflow, open-source, open-access, traces, characterization, archive, survey, simulation}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9066946} } @Article{Torre2020, author = {Ennio Torre and Juan J. Durillo and Vincenzo de Maio and Prateek Agrawal and Shajulin Benedict and Nishant Saurabh and Radu Prodan}, journal = {Information and Software Technology}, title = {{A dynamic evolutionary multi-objective virtual machine placement heuristic for cloud data centers}}, year = {2020}, issn = {0950-5849}, month = {dec}, pages = {106390}, volume = {128}, 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. The effective tradeoff between resource wastage and overcommitment is a challenging task in virtualized Clouds and depends on the allocation of virtual machines (VMs) to physical resources. We propose in this paper a multi-objective method for dynamic VM placement, which exploits live migration mechanisms to simultaneously optimize the resource wastage, overcommitment ratio and migration energy. Our optimization algorithm uses a novel evolutionary meta-heuristic based on an island population model to approximate the Pareto optimal set of VM placements with good accuracy and diversity. Simulation results using traces collected from a real Google cluster demonstrate that our method outperforms related approaches by reducing the migration energy by up to 57% with a QoS increase below 6%.}, doi = {10.1016/j.infsof.2020.106390}, keywords = {VM placement, Multi-objective optimisation, Resource overcommitment, Resource wastage, Live migration, Energy consumption, Pareto optimal set, Genetic algorithm, Data center simulation}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/pii/S0950584919302101} } @Article{Saurabh2020, author = {Nishant Saurabh and Shajulin Benedict and Jorge G. Barbosa and Radu Prodan}, journal = {Journal of Parallel and Distributed Computing}, title = {{Expelliarmus: Semantic-centric virtual machine image management in IaaS Clouds}}, year = {2020}, issn = {0743-7315}, month = {dec}, pages = {107--121}, volume = {146}, abstract = {Infrastructure-as-a-service (IaaS) Clouds concurrently accommodate diverse sets of user requests, requiring an efficient strategy for storing and retrieving virtual machine images (VMIs) at a large scale. The VMI storage management requires dealing with multiple VMIs, typically in the magnitude of gigabytes, which entails VMI sprawl issues hindering the elastic resource management and provisioning. Unfortunately, existing techniques to facilitate VMI management overlook VMI semantics (i.e at the level of base image and software packages), with either restricted possibility to identify and extract reusable functionalities or with higher VMI publishing and retrieval overheads. In this paper, we propose Expelliarmus, a novel VMI management system that helps to minimize VMI storage, publishing and retrieval overheads. To achieve this goal, Expelliarmus incorporates three complementary features. First, it models VMIs as semantic graphs to facilitate their similarity computation. Second, it provides a semantically-aware VMI decomposition and base image selection to extract and store non-redundant base image and software packages. Third, it assembles VMIs based on the required software packages upon user request. We evaluate Expelliarmus through a representative set of synthetic Cloud VMIs on a real test-bed. Experimental results show that our semantic-centric approach is able to optimize the repository size by 2.3 - 22 times compared to state-of-the-art systems (e.g. IBM’s Mirage and Hemera) with significant VMI publishing and slight retrieval performance improvement.}, doi = {10.1016/j.jpdc.2020.08.001}, keywords = {Theoretical Computer Science, Computer Networks and Communications, Hardware and Architecture, Software, Artificial Intelligence}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/pii/S0743731520303415} } @Article{Perkis2020, author = {Andrew Perkis and Christian Timmerer and Sabina Baraković and Jasmina Baraković Husić and Søren Bech and Sebastian Bosse and Jean Botev and Kjell Brunnström and Luis Cruz and Katrien De Moor and Andrea de Polo Saibanti and Wouter Durnez and Sebastian Egger-Lampl and Ulrich Engelke and Tiago H. Falk and Jesús Gutiérrez and Asim Hameed and Andrew Hines and Tanja Kojic and Dragan Kukolj and Eirini Liotou and Dragorad Milovanovic and Sebastian Möller and Niall Murray and Babak Naderi and Manuela Pereira and Stuart Perry and Antonio Pinheiro and Andres Pinilla and Alexander Raake and Sarvesh Rajesh Agrawal and Ulrich Reiter and Rafael Rodrigues and Raimund Schatz and Peter Schelkens and Steven Schmidt and Saeed Shafiee Sabet and Ashutosh Singla and Lea Skorin-Kapov and Mirko Suznjevic and Stefan Uhrig and Sara Vlahović and Jan-Niklas Voigt-Antons and Saman Zadtootaghaj}, title = {{QUALINET White Paper on Definitions of Immersive Media Experience (IMEx)}}, year = {2020}, month = jun, abstract = {With the coming of age of virtual/augmented reality and interactive media, numerous definitions, frameworks, and models of immersion have emerged across different fields ranging from computer graphics to literary works. Immersion is oftentimes used interchangeably with presence as both concepts are closely related. However, there are noticeable interdisciplinary differences regarding definitions, scope, and constituents that are required to be addressed so that a coherent understanding of the concepts can be achieved. Such consensus is vital for paving the directionality of the future of immersive media experiences (IMEx) and all related matters. The aim of this white paper is to provide a survey of definitions of immersion and presence which leads to a definition of immersive media experience (IMEx). The Quality of Experience (QoE) for immersive media is described by establishing a relationship between the concepts of QoE and IMEx followed by application areas of immersive media experience. Influencing factors on immersive media experience are elaborated as well as the assessment of immersive media experience. Finally, standardization activities related to IMEx are highlighted and the white paper is concluded with an outlook related to future developments.}, keywords = {cs.MM} } @Article{Matha2020, author = {Roland Matha and Sasko Ristov and Thomas Fahringer and Radu Prodan}, journal = {IEEE Transactions on Parallel and Distributed Systems}, title = {{Simplified Workflow Simulation on Clouds based on Computation and Communication Noisiness}}, year = {2020}, issn = {1045-9219}, month = {jul}, number = {7}, pages = {1559--1574}, volume = {31}, abstract = {Many researchers rely on simulations to analyze and validate their researched methods on Cloud infrastructures. However, determining relevant simulation parameters and correctly instantiating them to match the real Cloud performance is a difficult and costly operation, as minor configuration changes can easily generate an unreliable inaccurate simulation result. Using legacy values experimentally determined by other researchers can reduce the configuration costs, but is still inaccurate as the underlying public Clouds and the number of active tenants are highly different and dynamic in time. To overcome these deficiencies, we propose a novel model that simulates the dynamic Cloud performance by introducing noise in the computation and communication tasks, determined by a small set of runtime execution data. Although the estimating method is apparently costly, a comprehensive sensitivity analysis shows that the configuration parameters determined for a certain simulation setup can be used for other simulations too, thereby reducing the tuning cost by up to 82.46%, while declining the simulation accuracy by only 1.98% in average. Extensive evaluation also shows that our novel model outperforms other state-of-the-art dynamic Cloud simulation models, leading up to 22% lower makespan inaccuracy.}, doi = {10.1109/tpds.2020.2967662}, keywords = {Cloud computing, simulation, workflow applications, burstable instances, performance instability and noisiness}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/8964294/} } @Article{Maio2020, author = {Vincenzo De Maio and Dragi Kimovski}, journal = {Future Generation Computer Systems}, title = {{Multi-objective scheduling of extreme data scientific workflows in Fog}}, year = {2020}, issn = {0167-739X}, month = {may}, pages = {171--184}, volume = {106}, abstract = {The concept of “extreme data” is a recent re-incarnation of the “big data” problem, which is distinguished by the massive amounts of information that must be analyzed with strict time requirements. In the past decade, the Cloud data centers have been envisioned as the essential computing architectures for enabling extreme data workflows. However, the Cloud data centers are often geographically distributed. Such geographical distribution increases offloading latency, making it unsuitable for processing of workflows with strict latency requirements, as the data transfer times could be very high. Fog computing emerged as a promising solution to this issue, as it allows partial workflow processing in lower-network layers. Performing data processing on the Fog significantly reduces data transfer latency, allowing to meet the workflows’ strict latency requirements. However, the Fog layer is highly heterogeneous and loosely connected, which affects reliability and response time of task offloading. In this work, we investigate the potential of Fog for scheduling of extreme data workflows with strict response time requirements. Moreover, we propose a novel Pareto-based approach for task offloading in Fog, called Multi-objective Workflow Offloading (MOWO). MOWO considers three optimization objectives, namely response time, reliability, and financial cost. We evaluate MOWO workflow scheduler on a set of real-world biomedical, meteorological and astronomy workflows representing examples of extreme data application with strict latency requirements.}, doi = {10.1016/j.future.2019.12.054}, keywords = {Scheduling, Scientific workflows, Fog computing, Task offloading, Monte-Carlo simulation, Multi-objective optimization}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/pii/S0167739X19309197?via=ihub} } @Article{Hooft2020a, author = {Jeroen van der Hooft and Maria Torres Vega and Tim Wauters and Christian Timmerer and Ali C. Begen and Filip De Turck and Raimund Schatz}, journal = {IEEE Communications Magazine}, title = {{From Capturing to Rendering: Volumetric Media Delivery with Six Degrees of Freedom}}, year = {2020}, issn = {0163-6804}, month = {oct}, number = {10}, pages = {49--55}, volume = {58}, abstract = {Technological improvements are rapidly advancing holographic-type content distribution. Significant research efforts have been made to meet the low-latency and high-bandwidth requirements set forward by interactive applications such as remote surgery and virtual reality. Recent research made six degrees of freedom (6DoF) for immersive media possible, where users may both move their heads and change their position within a scene. In this article, we present the status and challenges of 6DoF applications based on volumetric media, focusing on the key aspects required to deliver such services. Furthermore, we present results from a subjective study to highlight relevant directions for future research.}, doi = {10.1109/mcom.001.2000242}, keywords = {Streaming media, Media, Cameras, Three-dimensional displays, Encoding, Bit rate, Real-time systems}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, url = {https://ieeexplore.ieee.org/document/9247522} } @Article{Hayat2020, author = {Samira Hayat and Evsen Yanmaz and Christian Bettstetter and Timothy X. Brown}, journal = {Autonomous Robots}, title = {{Multi-objective drone path planning for search and rescue with quality-of-service requirements}}, year = {2020}, month = {jul}, number = {7}, pages = {1183--1198}, volume = {44}, abstract = {We incorporate communication into the multi-UAV path planning problem for search and rescue missions to enable dynamic task allocation via information dissemination. Communication is not treated as a constraint but a mission goal. While achieving this goal, our aim is to avoid compromising the area coverage goal and the overall mission time. We define the mission tasks as: search, inform, and monitor at the best possible link quality. Building on our centralized simultaneous inform and connect (SIC) path planning strategy, we propose two adaptive strategies: (1) SIC with QoS (SICQ): optimizes search, inform, and monitor tasks simultaneously and (2) SIC following QoS (SIC+): first optimizes search and inform tasks together and then finds the optimum positions for monitoring. Both strategies utilize information as soon as it becomes available to determine UAV tasks. The strategies can be tuned to prioritize certain tasks in relation to others. We illustrate that more tasks can be performed in the given mission time by efficient incorporation of communication in the path design. We also observe that the quality of the resultant paths improves in terms of connectivity.}, doi = {10.1007/s10514-020-09926-9}, keywords = {multi-uav, dynamic task allocation, information dissemination, communication, path planning, search and rescue, area coverage, SIC, SICQ, connectivity}, publisher = {Springer Science and Business Media LLC}, url = {https://link.springer.com/article/10.1007/s10514-020-09926-9} } @Article{Ghamsarian2020c, author = {Negin Ghamsarian and Klaus Schoeffmann and Morteza Khademi}, journal = {Multimedia Tools and Applications}, title = {{Blind MV-based video steganalysis based on joint inter-frame and intra-frame statistics}}, year = {2020}, issn = {1573-7721}, month = {nov}, number = {6}, pages = {1--23}, volume = {80}, abstract = {Despite all its irrefutable benefits, the development of steganography methods has sparked ever-increasing concerns over steganography abuse in recent decades. To prevent the inimical usage of steganography, steganalysis approaches have been introduced. Since motion vector manipulation leads to random and indirect changes in the statistics of videos, MV-based video steganography has been the center of attention in recent years. In this paper, we propose a 54-dimentional feature set exploiting spatio-temporal features of motion vectors to blindly detect MV-based stego videos. The idea behind the proposed features originates from two facts. First, there are strong dependencies among neighboring MVs due to utilizing rate-distortion optimization techniques and belonging to the same rigid object or static background. Accordingly, MV manipulation can leave important clues on the differences between each MV and the MVs belonging to the neighboring blocks. Second, a majority of MVs in original videos are locally optimal after decoding concerning the Lagrangian multiplier, notwithstanding the information loss during compression. Motion vector alteration during information embedding can affect these statistics that can be utilized for steganalysis. Experimental results have shown that our features’ performance far exceeds that of state-of-the-art steganalysis methods. This outstanding performance lies in the utilization of complementary spatio-temporal statistics affected by MV manipulation as well as feature dimensionality reduction applied to prevent overfitting. Moreover, unlike other existing MV-based steganalysis methods, our proposed features can be adjusted to various settings of the state-of-the-art video codec standards such as sub-pixel motion estimation and variable-block-size motion estimation.}, doi = {10.1007/s11042-020-10001-9}, keywords = {Blind steganalysis, Video steganography, Information security, Motion vector, Video compression, H264/AVC}, publisher = {Springer Science and Business Media LLC}, url = {https://link.springer.com/article/10.1007/s11042-020-10001-9} } @Article{Cetinkaya2020a, author = {Cetinkaya, Ekrem and KIRAÇ, M. Furkan}, journal = {TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES}, title = {{Image denoising using deep convolutional autoencoder with feature pyramids}}, year = {2020}, issn = {1303-6203}, month = {7}, number = {4}, pages = {2096--2109}, volume = {28}, abstract = {Image denoising is 1 of the fundamental problems in the image processing field since it is the preliminary stepfor many computer vision applications. Various approaches have been used for image denoising throughout the yearsfrom spatial filtering to model-based approaches. Having outperformed all traditional methods, neural-network-baseddiscriminative methods have gained popularity in recent years. However, most of these methods still struggle to achieveflexibility against various noise levels and types. In this paper, a deep convolutional autoencoder combined with a variantof feature pyramid network is proposed for image denoising. Simulated data generated by Blender software along withcorrupted natural images are used during training to improve robustness against various noise levels. Experimental resultsshow that the proposed method can achieve competitive performance in blind Gaussian denoising with significantly lesstraining time required compared to state of the art methods. Extensive experiments showed the proposed method givespromising performance in a wide range of noise levels with a single network.}, doi = {10.3906/elk-1911-138}, keywords = {Image denoising, convolutional autoencoder, feature pyramid, image processing}, url = {https://journals.tubitak.gov.tr/elektrik/issues/elk-20-28-4/elk-28-4-20-1911-138.pdf} } @Article{Borgli2020, author = {Hanna Borgli and Vajira Thambawita and Pia H. Smedsrud and Steven Hicks and Debesh Jha and Sigrun L. Eskeland and Kristin Ranheim Randel and Konstantin Pogorelov and Mathias Lux and Duc Tien Dang Nguyen and Dag Johansen and Carsten Griwodz and H{\aa}kon K. Stensland and Enrique Garcia-Ceja and Peter T. Schmidt and Hugo L. Hammer and Michael A. Riegler and Paal Halvorsen and Thomas de Lange}, journal = {Scientific Data}, title = {{HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy}}, year = {2020}, issn = {2052-4463}, month = {aug}, number = {1}, volume = {7}, abstract = {Artificial intelligence is currently a hot topic in medicine. However, medical data is often sparse and hard to obtain due to legal restrictions and lack of medical personnel for the cumbersome and tedious process to manually label training data. These constraints make it difficult to develop systems for automatic analysis, like detecting disease or other lesions. In this respect, this article presents HyperKvasir, the largest image and video dataset of the gastrointestinal tract available today. The data is collected during real gastro- and colonoscopy examinations at Bærum Hospital in Norway and partly labeled by experienced gastrointestinal endoscopists. The dataset contains 110,079 images and 374 videos, and represents anatomical landmarks as well as pathological and normal findings. The total number of images and video frames together is around 1 million. Initial experiments demonstrate the potential benefits of artificial intelligence-based computer-assisted diagnosis systems. The HyperKvasir dataset can play a valuable role in developing better algorithms and computer-assisted examination systems not only for gastro- and colonoscopy, but also for other fields in medicine.}, doi = {10.1038/s41597-020-00622-y}, keywords = {Statistics, Probability and Uncertainty, Statistics and Probability, Education, Library and Information Sciences, Information Systems, Computer Science Applications}, publisher = {Springer Science and Business Media LLC}, url = {https://www.nature.com/articles/s41597-020-00622-y} } @Article{Bhadwal2020, author = {Neha Bhadwal and Prateek Agrawal and Vishu Madaan}, journal = {Scalable Computing: Practice and Experience}, title = {{A Machine Translation System from Hindi to Sanskrit Language using Rule based Approach}}, year = {2020}, issn = {1895-1767}, month = {aug}, number = {3}, pages = {543--554}, volume = {21}, abstract = {Machine Translation is an area of Natural Language Processing which can replace the laborious task of manual translation. Sanskrit language is among the ancient Indo-Aryan languages. There are numerous works of art and literature in Sanskrit. It has also been a medium for creating treatise of philosophical work as well as works on logic, astronomy and mathematics. On the other hand, Hindi is the most prominent language of India. Moreover,it is among the most widely spoken languages across the world. This paper is an effort to bridge the language barrier between Hindi and Sanskrit language such that any text in Hindi can be translated to Sanskrit. The technique used for achieving the aforesaid objective is rule-based machine translation. The salient linguistic features of the two languages are used to perform the translation. The results are produced in the form of two confusion matrices wherein a total of 50 random sentences and 100 tokens (Hindi words or phrases) were taken for system evaluation. The semantic evaluation of 100 tokens produce an accuracy of 94% while the pragmatic analysis of 50 sentences produce an accuracy of around 86%. Hence, the proposed system can be used to understand the whole translation process and can further be employed as a tool for learning as well as teaching. Further, this application can be embedded in local communication based assisting Internet of Things (IoT) devices like Alexa or Google Assistant.}, doi = {10.12694/scpe.v21i3.1783}, keywords = {Rule based approach, Natural Language Translation, Parts of speech tagging, Sanskrit Translation, Hindi Translation}, publisher = {Scalable Computing: Practice and Experience}, url = {https://www.scpe.org/index.php/scpe/article/view/1783} } @Article{Bentaleb2020, author = {Abdelhak Bentaleb and Christian Timmerer and Ali C. Begen and Roger Zimmermann}, journal = {ACM Transactions on Multimedia Computing, Communications, and Applications}, title = {{Performance Analysis of ACTE: a Bandwidth Prediction Method for Low-Latency Chunked Streaming}}, year = {2020}, issn = {1551-6857}, month = {jul}, number = {2s}, pages = {1--24}, volume = {16}, abstract = {HTTP adaptive streaming with chunked transfer encoding can offer low-latency streaming without sacrificing the coding efficiency.This allows media segments to be delivered while still being packaged. However, conventional schemes often make widely inaccurate bandwidth measurements due to the presence of idle periods between the chunks and hence this is causing sub-optimal adaptation decisions. To address this issue, we earlier proposed ACTE (ABR for Chunked Transfer Encoding), a bandwidth prediction scheme for low-latency chunked streaming. While ACTE was a significant step forward, in this study we focus on two still remaining open areas, namely (i) quantifying the impact of encoding parameters, including chunk and segment durations, bitrate levels, minimum interval between IDR-frames and frame rate onACTE, and (ii) exploring the impact of video content complexity on ACTE. We thoroughly investigate these questions and report on our findings. We also discuss some additional issues that arise in the context of pursuing very low latency HTTP video streaming.}, doi = {10.1145/3387921}, keywords = {HAS, ABR, DASH, CMAF, low-latency, HTTP chunked transfer encoding, bandwidth measurement and prediction, RLS, encoding parameters, FFmpeg}, publisher = {Association for Computing Machinery (ACM)}, url = {https://dl.acm.org/doi/abs/10.1145/3387921} } @Article{Barcis2020, author = {Michal Barcis and Agata Barcis and Hellwagner, Hermann}, journal = {Sensors}, title = {{Information Distribution in Multi-Robot Systems: Utility-Based Evaluation Model}}, year = {2020}, issn = {1424-8220}, month = {jan}, number = {3}, volume = {20}, abstract = {This work addresses the problem of information distribution in multi-robot systems, with an emphasis on multi-UAV (unmanned aerial vehicle) applications. We present an analytical model that helps evaluate and compare different information distribution schemes in a robotic mission. It serves as a unified framework to represent the usefulness (utility) of each message exchanged by the robots. It can be used either on its own in order to assess the information distribution efficacy or as a building block of solutions aimed at optimizing information distribution. Moreover, we present multiple examples of instantiating the model for specific missions. They illustrate various approaches to defining the utility of different information types. Finally, we introduce a proof of concept showing the applicability of the model in a robotic system by implementing it in Robot Operating System 2 (ROS 2) and performing a simple simulated mission using a network emulator. We believe the introduced model can serve as a basis for further research on generic solutions for assessing or optimizing information distribution.}, doi = {10.3390/s20030710}, keywords = {autonomous systems, multi-robot systems, information distribution, utility theory}, publisher = {MDPI AG}, url = {https://www.mdpi.com/1424-8220/20/3/710/htm} } @Article{Agrawal2020a, author = {Prateek Agrawal and Deepak Chaudhary and Vishu Madaan and Anatoliy Zabrovskiy and Radu Prodan and Dragi Kimovski and Christian Timmerer}, journal = {Multimedia Tools and Applications}, title = {{Automated bank cheque verification using image processing and deep learning methods}}, year = {2020}, issn = {1573-7721}, month = {oct}, number = {4}, pages = {5319--5350}, volume = {80}, abstract = {Automated bank cheque verification using image processing is an attempt to complement the present cheque truncation system, as well as to provide an alternate methodology for the processing of bank cheques with minimal human intervention. When it comes to the clearance of the bank cheques and monetary transactions, this should not only be reliable and robust but also save time which is one of the major factor for the countries having large population. In order to perform the task of cheque verification, we developed a tool which acquires the cheque leaflet key components, essential for the task of cheque clearance using image processing and deep learning methods. These components include the bank branch code, cheque number, legal as well as courtesy amount, account number, and signature patterns. our innovation aims at benefiting the banking system by re-innovating the other competent cheque-based monetary transaction system which requires automated system intervention. For this research, we used institute of development and research in banking technology (IDRBT) cheque dataset and deep learning based convolutional neural networks (CNN) which gave us an accuracy of 99.14% for handwritten numeric character recognition. It resulted in improved accuracy and precise assessment of the handwritten components of bank cheque. For machine printed script, we used MATLAB in-built OCR method and the accuracy achieved is satisfactory (97.7%) also for verification of Signature we have used Scale Invariant Feature Transform (SIFT) for extraction of features and Support Vector Machine (SVM) as classifier, the accuracy achieved for signature verification is 98.10%.}, doi = {10.1007/s11042-020-09818-1}, keywords = {Cheque truncation system, Image segmentation, Bank cheque clearance, Image feature extraction, Convolution neural network, Support vector machine, Scale invariant feature transform}, publisher = {Springer Science and Business Media LLC}, url = {https://link.springer.com/article/10.1007/s11042-020-09818-1} } @Article{Agrawal2020, author = {Prateek Agrawal and Anatoliy Zabrovskiy and Adithyan Ilangovan and Christian Timmerer and Radu Prodan}, journal = {Cluster Computing}, title = {{FastTTPS: fast approach for video transcoding time prediction and scheduling for HTTP adaptive streaming videos}}, year = {2020}, issn = {1573-7543}, month = {nov}, pages = {1--17}, abstract = {HTTP adaptive streaming of video content becomes an integrated part of the Internet and dominates other streaming protocols and solutions. The duration of creating video content for adaptive streaming ranges from seconds or up to several hours or days, due to the plethora of video transcoding parameters and video source types. Although, the computing resources of different transcoding platforms and services constantly increase, accurate and fast transcoding time prediction and scheduling is still crucial. We propose in this paper a novel method called fast video transcoding time prediction and scheduling (FastTTPS) of x264 encoded videos based on three phases: (i) transcoding data engineering, (ii) transcoding time prediction, and (iii) transcoding scheduling. The first phase is responsible for video sequence selection, segmentation and feature data collection required for predicting the transcoding time. The second phase develops an artificial neural network (ANN) model for segment transcoding time prediction based on transcoding parameters and derived video complexity features. The third phase compares a number of parallel schedulers to map the predicted transcoding segments on the underlying high-performance computing resources. Experimental results show that our predictive ANN model minimizes the transcoding mean absolute error (MAE) and mean square error (MSE) by up to 1.7 and 26.8, respectively. In terms of scheduling, our method reduces the transcoding time by up to 38% using a Max–Min algorithm compared to the actual transcoding time without prediction information.}, doi = {10.1007/s10586-020-03207-x}, keywords = {Transcoding time prediction, Video transcoding, Scheduling, Artificial neural networks, MPEG-DASH, Adaptive streaming}, publisher = {Springer Science and Business Media LLC}, url = {https://link.springer.com/article/10.1007/s10586-020-03207-x} } @Article{vanderHooft2019, author = {van der Hooft, Jeroen and Torres Vega, Maria and Wauters, Tim and Ravuri, Hemanth Kumar and Timmerer, C. and Hellwagner, Hermann and De Turck, Filip}, journal = {IEEE COMSOC MMTC COMMUNICATIONS - FRONTIERS}, title = {{Towards 6DoF virtual reality video streaming: status and challenges}}, year = {2019}, month = sep, number = {5}, pages = {30--37}, volume = {14}, abstract = {In the last few years, delivery of immersive video with six degrees of freedom (6DoF) has become an important topic for content providers. Recent technological advancements have resulted in affordable head-mounted displays, allowing a broad range of users to enjoy Virtual Reality (VR) content. Service providers such as Facebook1and YouTube2were among the first to provide 360°video, using the principle of HTTP Adaptive Streaming (HAS) to deliver the content to the enduser. In HAS, the content is encoded using several quality representations, temporally segmented into chunks of one to ten seconds and stored on one or multiple servers within a content delivery network. Based on the perceived network conditions, the device characteristics, and the user's preferences, the client can then decide on the quality of each of these segments[1]. Having the ability to adapt the video quality, this approach actively avoids buffer starvation, and therefore results in smoother playback of the requested content and a higher Quality of Experience (QoE) for the end user[2]. The introduction of 360° video provides the user with three degrees of freedom to move within an immersive world, allowing changes in the yaw, roll, and pitch.In the last few years, multiple solutions have been proposed to efficiently deliver VR content through HAS, focusing, for instance, on foveas-and tile-based encoding, improved viewport prediction (i.e., prediction of the user’s head movement in the near future in order to buffer useful high-quality content), and application layer optimizations [3]. In these works, however, the location of the user remains fixed to the position of the camera within the scene. Recently, significant research efforts have been made to realize 6DoF for streamed video content, i.e., the user may experience three additional degrees of freedom by being able to change the viewing position in a video scene. These efforts are promising, but significant research contributions will be required in order to realize its full potential. In this paper, an overview of existing 6DoF solutions is presented, and key challenges and opportunities are highlighted.}, language = {{eng}}, url = {https://biblio.ugent.be/publication/8666820/file/8716606} } @Article{Timmerer_Zabrovskiy2019, author = {Timmerer, Christian and Zabrovskiy, Anatoliy}, journal = {ZTE COMMUNICATIONS}, title = {{Automating QoS and QoE Evaluation of HTTP Adaptive Streaming Systems}}, year = {2019}, month = {März}, number = {1}, pages = {18--24}, volume = {17}, abstract = {Streaming audio and video content currently accounts for the majority of the In⁃ternet traffic and is typically deployed over the top of the existing infrastructure. We arefacing the challenge of a plethora of media players and adaptation algorithms showing dif⁃ferent behavior but lacking a common framework for both objective and subjective evalua⁃tion of such systems. This paper aims to close this gap byproposing such a framework,de⁃scribing its architecture,providing an example evaluation, anddiscussing open issues.}, doi = {10.12142/ZTECOM.201901004}, url = {https://www.researchgate.net/profile/Anatoliy_Zabrovskiy/publication/335620882_Automating_QoS_and_QoE_Evaluation_of_HTTP_Adaptive_Streaming_Systems/links/5d70f9074585151ee49e7674/Automating-QoS-and-QoE-Evaluation-of-HTTP-Adaptive-Streaming-Systems.pdf} } @Article{TimmererGUESTEDITORIAL, author = {Ji, Wen and Li, Zhu and Poor, H. Vincent and Timmerer, Christian and Zhu, Wenwu}, journal = {IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS}, title = {{Guest Editorial Multimedia Economics for Future Networks: Theory, Methods, and Applications}}, year = {2019}, month = {Juni}, number = {7}, pages = {1473--1477}, volume = {37}, abstract = {With the growing integration of telecommunication networks, Internet of Things (IoT), and 5G networks, there is a tremendous demand for multimedia services over heterogeneous networks. According to recent survey reports, mobile video traffic accounted for 60 percent of total mobile data traffic in 2016, and it will reach up to 78 percent by the end of 2021. Users’ daily lives are inundated with multimedia services, such as online video streaming (e.g., YouTube and Netflix), social networks (e.g., Facebook, Instagram, and Twitter), IoT and machine generated video (e.g, surveillance cameras), and multimedia service providers (e.g., Over-the-Top (OTT) services). Multimedia data is thus becoming the dominant traffic in the near future for both wired and wireless networks.}, doi = {10.1109/JSAC.2019.2918962}, url = {https://ieeexplore.ieee.org/abstract/document/8737812} } @Article{Timmerer2019a, author = {Timmerer, Christian}, title = {MPEG column: 124th MPEG meeting in Macau, China}, journal = {SIGMultimedia Records}, publisher = {ACM}, year = {2019}, volume = {10}, number = {4}, month = jan, issn = {1947-4598}, doi = {10.1145/3310195.3310203}, url = {http://doi.acm.org/10.1145/3310195.3310203}, pages = {8:8--8:8}, address = {New York, NY, USA} } @Article{Schöffmann2019e, author = {Schöffmann, Klaus and Þór Jónsson, Björn and Gurrin, Cathal}, journal = {ACM SIGMM Records}, title = {{Dataset Column: Report from the MMM 2019 Special Session on Multimedia Datasets for Repeatable Experimentation (MDRE 2019)}}, year = {2019}, month = {September}, number = {3}, volume = {11}, abstract = {Information retrieval and multimedia content access have a long history of comparative evaluation, and many of the advances in the area over the past decade can be attributed to the availability of open datasets that support comparative and repeatable experimentation. Sharing data and code to allow other researchers to replicate research results is needed in the multimedia modeling field, as it helps to improve the performance of systems and the reproducibility of published papers.This report summarizes the special session on Multimedia Datasets for Repeatable Experimentation (MDRE 2019), which was organized at the 25th International Conference on MultiMedia Modeling (MMM 2019), which was held in January 2019 in Thessaloniki, Greece.The intent of these special sessions is to be a venue for releasing datasets to the multimedia community and discussing dataset related issues. The presentation mode in 2019 was to have short presentations (8 minutes) with some questions, and an additional panel discussion after all the presentations, which was moderated by Björn Þór Jónsson. In the following we summarize the special session, including its talks, questions, and discussions.}, url = {https://records.sigmm.org/2019/10/22/dataset-column-report-from-the-mmm-2019-special-session-on-multimedia-datasets-for-repeatable-experimentation-mdre-2019/} } @Article{Schoeffmann2019g, author = {Gurrin, Cathal and Joho, Hideo and Zhou, Liting and Dang-Nguyen, Duc-Tien and Piras, Luca and Lokoc, Jakub and Schöffmann, Klaus and Leibetseder, Andreas and Duane, Aaron and Riegler, Michael and Tran, Minh-Triet and Hürst, Wolfgang}, journal = {ITE Transactions on Media Technology and Applications}, title = {{Comparing Approaches to Interactive Lifelog Search at the Lifelog Search Challenge (LSC2018)}}, year = {2019}, month = {April}, number = {2}, pages = {46--59}, volume = {7}, abstract = {The Lifelog Search Challenge (LSC) is an international content retrieval competition that evaluates search for personal lifelog data. At the LSC, content-based search is performed over a multi-modal dataset, continuously recorded by a lifelogger over 27 days, consisting of multimedia content, biometric data, human activity data, and information activities data. In this work, we report on the first LSC that took place in Yokohama, Japan in 2018 as a special workshop at ACM International Conference on Multimedia Retrieval 2018 (ICMR 2018). We describe the general idea of this challenge, summarise the participating search systems as well as the evaluation procedure, and analyse the search performance of the teams in various aspects. We try to identify reasons why some systems performed better than others and provide an outlook as well as open issues for upcoming iterations of the challenge.}, doi = {10.3169/mta.7.46}, url = {https://www.researchgate.net/publication/332118743_Invited_papers_Comparing_Approaches_to_Interactive_Lifelog_Search_at_the_Lifelog_Search_Challenge_LSC2018} } @Article{Schoeffmann2019f, author = {Rossetto, Luca and Berns, Fabian and Schöffmann, Klaus and Awad, George M. and Beecks, Christian}, journal = {ACM SIGMM Records}, title = {{The V3C1 Dataset: Advancing the State of the Art in Video Retrieval}}, year = {2019}, month = {Juni}, number = {2}, volume = {11}, abstract = {Standardized datasets are of vital importance in multimedia research, as they form the basis for reproducible experiments and evaluations. In the area of video retrieval, widely used datasets such as the IACC [5], which has formed the basis for the TRECVID Ad-Hoc Video Search Task and other retrieval-related challenges, have started to show their age. For example, IACC is no longer representative of video content as it is found in the wild [7]. This is illustrated by the figures below, showing the distribution of video age and duration across various datasets in comparison with a sample drawn from Vimeo and Youtube.}, url = {https://records.sigmm.org/2019/07/06/the-v3c1-dataset-advancing-the-state-of-the-art-in-video-retrieval/} } @Article{Prodan2019_JofGridComputing, author = {Ricci, Laura and Iosup, Alexander and Prodan, Radu Aurel}, journal = {Journal of Grid Computing}, title = {{EDITORIAL Special Issue on Large Scale Cooperative Virtual Environments}}, year = {2019}, month = {März}, pages = {1--2}, volume = {17}, doi = {10.1007/s10723-019-09480-4}, url = {https://link.springer.com/article/10.1007/s10723-019-09480-4} } @Article{Prodan2019JavaSymphony, author = {Aleem, Muhammad and Prodan, Radu Aurel and Arshad Islam, Muhammad and Azhar Iqbal, Muhammad}, journal = {International Journal of Ad Hoc and Ubiquitous Computing}, title = {{On the Parallel Programmability of JavaSymphony for Multi-cores and Clusters}}, year = {2019}, month = {März}, number = {4}, pages = {247--264}, volume = {30}, abstract = {This paper explains the programming aspects of a promising Java-based programming and execution framework called JavaSymphony. JavaSymphony provides unified high-level programming constructs for applications related to shared, distributed, hybrid memory parallel computers, and co-processors accelerators. JavaSymphony applications can be executed on a variety of multi-/many-core conventional and data-parallel architectures. JavaSymphony is based on the concept of dynamic virtual architectures, which allows programmers to define a hierarchical structure of the underlying computing resources and to control load-balancing and task-locality. In addition to GPU support, JavaSymphony provides a multi-core aware scheduling mechanism capable of mapping parallel applications on large multi-core machines and heterogeneous clusters. Several real applications and benchmarks (on modern multi-core computers, heterogeneous clusters, and machines consisting of a combination of different multi-core CPU and GPU devices) have been used to evaluate the performance. The results demonstrate that the JavaSymphony outperforms the Java implementations, as well as other modern alternative solutions.}, doi = {10.1504/IJAHUC.2019.098861}, url = {https://www.inderscience.com/info/inarticle.php?artid=98861} } @Article{Prodan2019IndersciencePublishers, author = {Aleem, Muhammad and Prodan, Radu Aurel and Arshad Islam, Muhammad and Azhar Iqbal, Muhammad}, journal = {International Journal of Ad Hoc and Ubiquitous Computing}, title = {{On the paralell programmability of JavaSymphony for multi-cores and clusters}}, year = {2019}, month = {März}, number = {4}, pages = {247--264}, volume = {30}, abstract = {This paper explains the programming aspects of a promising Java-based programming and execution framework called JavaSymphony. JavaSymphony provides unified high-level programming constructs for applications related to shared, distributed, hybrid memory parallel computers, and co-processors accelerators. JavaSymphony applications can be executed on multi-/many-core conventional and data-parallel architectures. JavaSymphony is based on the concept of dynamic virtual architectures, which allows programmers to define a hierarchical structure of the underlying computing resources and to control load-balancing and task-locality. In addition to GPU support, JavaSymphony provides a multi-core aware scheduling mechanism capable of mapping parallel applications on large multi-core machines and heterogeneous clusters. Several real applications and benchmarks (on modern multi-core computers, heterogeneous clusters, and machines consisting of a combination of different multi-core CPU and GPU devices) have been used to evaluate the performance. The results demonstrate that the JavaSymphony outperforms the Java implementations, as well as other modern alternative solutions.}, doi = {10.1504/IJAHUC.2019.098861}, url = {https://www.inderscience.com/info/inarticle.php?artid=98861} } @Article{Pohl_Hellwagner, author = {Pohl, Daniela and Bouchachia, Abdelhamid and Hellwagner, Hermann}, journal = {IEEE Transactions on Knowledge and Data Engineering}, title = {{Active Online Learning for Social Media Analysis to Support Crisis Management}}, year = {2019}, month = {März}, pages = {1--14}, abstract = {People use social media (SM) to describe and discuss different situations they are involved in, like crises. It is therefore worthwhile to exploit SM contents to support crisis management, in particular by revealing useful and unknown information about the crises in real-time. Hence, we propose a novel active online multiple-prototype classifier, called AOMPC. It identifies relevant data related to a crisis. AOMPC is an online learning algorithm that operates on data streams and which is equipped with active learning mechanisms to actively query the label of ambiguous unlabeled data. The number of queries is controlled by a fixed budget strategy. Typically, AOMPC accommodates partly labeled data streams. AOMPC was evaluated using two types of data: (1) synthetic data and (2) SM data from Twitter related to two crises, Colorado Floods and Australia Bushfires. To provide a thorough evaluation, a whole set of known metrics was used to study the quality of the results. Moreover, a sensitivity analysis was conducted to show the effect of AOMPC's parameters on the accuracy of the results. A comparative study of AOMPC against other available online learning algorithms was performed. The experiments showed very good behavior of AOMPC for dealing with evolving, partly-labeled data streams.}, doi = {10.1109/TKDE.2019.2906173}, url = {https://ieeexplore.ieee.org/document/8669861} } @Article{Muenzer_Schoeffmann_2019, author = {Lokoc, Jakub and Kovalcik, Gregor and Münzer, Bernd and Schöffmann, Klaus and Bailer, Werner and Gasser, Ralph and Vrochidis, Stefanos and Nguyen, Phuong Anh and Rujikietgumjorn, Sitapa and Barthel, Kai Uwe}, journal = {ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)}, title = {{Interactive Search or Sequential Browsing? A Detailed Analysis of the Video Browser Showdown 2018}}, year = {2019}, month = {Februar}, pages = {1--26}, volume = {15}, abstract = {This work summarizes the findings of the 7th iteration of the Video Browser Showdown (VBS) competition organized as a workshop at the 24th International Conference on Multimedia Modeling in Bangkok. The competition focuses on video retrieval scenarios in which the searched scenes were either previously observed or described by another person (i.e., an example shot is not available). During the event, nine teams competed with their video retrieval tools in providing access to a shared video collection with 600 hours of video content. Evaluation objectives, rules, scoring, tasks, and all participating tools are described in the article. In addition, we provide some insights into how the different teams interacted with their video browsers, which was made possible by a novel interaction logging mechanism introduced for this iteration of the VBS. The results collected at the VBS evaluation server confirm that searching for one particular scene in the collection when given a limited time is still a challenging task for many of the approaches that were showcased during the event. Given only a short textual description, finding the correct scene is even harder. In ad hoc search with multiple relevant scenes, the tools were mostly able to find at least one scene, whereas recall was the issue for many teams. The logs also reveal that even though recent exciting advances in machine learning narrow the classical semantic gap problem, user-centric interfaces are still required to mediate access to specific content. Finally, open challenges and lessons learned are presented for future VBS events.}, doi = {10.1145/3295663}, url = {https://dl.acm.org/doi/10.1145/3295663} } @Article{Moll_Theuermann_Lux, author = {Elmenreich, Wilfried and Moll, Philipp and Theuermann, Sebastian and Lux, Mathias}, journal = {PeerJ Computer Science}, title = {{Making simulation results reproducible - Survey, guidelines, and examples based on Gradle and Docker}}, year = {2019}, month = {Dezember}, number = {e240}, pages = {1--27}, volume = {5}, abstract = {This article addresses two research questions related to reproducibility within the context of research related to computer science. First, a survey on reproducibility addressed to researchers in the academic and private sectors is described and evaluated. The survey indicates a strong need for open and easily accessible results, in particular, reproducing an experiment should not require too much effort. The results of the survey are then used to formulate guidelines for making research results reproducible. In addition, this article explores four approaches based on software tools that could bring forward reproducibility in research results. After a general analysis of tools, three examples are further investigated based on actual research projects which are used to evaluate previously introduced tools. Results indicate that the evaluated tools contribute well to making simulation results reproducible but due to conflicting requirements, none of the presented solutions fulfills all intended goals perfectly.}, doi = {10.7717/peerj-cs.240}, url = {https://peerj.com/articles/cs-240.pdf} } @Article{Lux2019f, author = {Chryssanthi, Iakovidou and Anagnostopoulos, Nektarios and Lux, Mathias and Christodoulou, Klitos and Boutalis, Yiannis and Chatzichristofis, Savvas}, journal = {IEEE Transactions on Image Processing}, title = {{Composite Description Based on Salient Contours and Color Information for CBIR Tasks}}, year = {2019}, month = {Juni}, number = {6}, pages = {3115--3129}, volume = {28}, abstract = {This paper introduces a novel image descriptor for content-based image retrieval tasks that integrates contour and color information into a compact vector. Loosely inspired by the human visual system and its mechanisms in efficiently identifying visual saliency, operations are performed on a fixed lattice of discrete positions by a set of edge detecting kernels that calculate region derivatives at different scales and orientation. The description method utilizes a weighted edge histogram where bins are populated on the premise of whether the regions contain edges belonging to the salient contours, while the discriminative power is further enhanced by integrating regional quantized color information. The proposed technique is both efficient and adaptive to the specifics of each depiction, while it does not need any training data to adjust parameters. An experimental evaluation conducted on seven benchmarking datasets against 13 well known global descriptors along with SIFT, SURF implementations (both in VLAD and BOVW), highlight the effectiveness and efficiency of the proposed descriptor.}, doi = {10.1109/TIP.2019.2894281}, url = {https://ieeexplore.ieee.org/document/8626513} } @Article{Kletz2019a, author = {Kletz, Sabrina and Schöffmann, Klaus and Husslein, Heinrich}, journal = {IET Healthcare Technology Letters}, title = {{Learning the representation of instrument images in laparoscopy videos }}, year = {2019}, month = {November}, number = {6}, pages = {197--203}, volume = {6}, abstract = {Automatic recognition of instruments in laparoscopy videos poses many challenges that need to be addressed, like identifying multiple instruments appearing in various representations and in different lighting conditions, which in turn may be occluded by other instruments, tissue, blood, or smoke. Considering these challenges, it may be beneficial for recognition approaches that instrument frames are first detected in a sequence of video frames for further investigating only these frames. This pre-recognition step is also relevant for many other classification tasks in laparoscopy videos, such as action recognition or adverse event analysis. In this work, the authors address the task of binary classification to recognise video frames as either instrument or non-instrument images. They examine convolutional neural network models to learn the representation of instrument frames in videos and take a closer look at learned activation patterns. For this task, GoogLeNet together with batch normalisation is trained and validated using a publicly available dataset for instrument count classifications. They compared transfer learning with learning from scratch and evaluate on datasets from cholecystectomy and gynaecology. The evaluation shows that fine-tuning a pre-trained model on the instrument and non-instrument images is much faster and more stable in learning than training a model from scratch.}, doi = {10.1049/htl.2019.0077}, url = {https://digital-library.theiet.org/content/journals/10.1049/htl.2019.0077} } @Article{Kimovski_Prodan_2019, author = {Gec, Sandi and Kimovski, Dragi and Pascinski, Uros and Prodan, Radu Aurel and Stankovski, Vlado}, journal = {Concurrency and Computation: Practice and Experience}, title = {{Semantic approach for multi-objective optimisation of the ENTICE distributed Virtual Machine and container images repository}}, year = {2019}, month = {Februar}, number = {3}, volume = {31}, abstract = {New software engineering technologies facilitate development of applications from reusable software components, such as Virtual Machine and container images (VMI/CIs). Key requirements for the storage of VMI/CIs in public or private repositories are their fast delivery and cloud deployment times. ENTICE is a federated storage facility for VMI/CIs that provides optimisation mechanisms through the use of fragmentation and replication of images and a Pareto Multi‐Objective Optimisation (MO) solver. The operation of the MO solver is, however, time‐consuming due to the size and complexity of the metadata, specifying various non‐functional requirements for the management of VMI/CIs, such as geolocation, operational cost, and delivery time. In this work, we address this problem with a new semantic approach, which uses an ontology of the federated ENTICE repository, knowledge base, and constraint‐based reasoning mechanism. Open Source technologies such as Protégé, Jena Fuseki, and Pellet were used to develop a solution. Two specific use cases, (1) repository optimisation with offline and (2) online redistribution of VMI/CIs, are presented in detail. In both use cases, data from the knowledge base are provided to the MO solver. It is shown that Pellet‐based reasoning can be used to reduce the input metadata size used in the optimisation process by taking into consideration the geographic location of the VMI/CIs and the provenance of the VMI fragments. It is shown that this process leads to reduction of the input metadata size for the MO solver by up to 60% and reduction of the total optimisation time of the MO solver by up to 68%, while fully preserving the quality of the solution, which is significant.}, doi = {10.1002/cpe.4264}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/cpe.4264} } @Article{Timmerer2018b, author = {Timmerer, Christian}, journal = {SIGMultimedia Records}, title = {MPEG column: 121st MPEG meeting in Gwangju, Korea}, year = {2018}, issn = {1947-4598}, month = mar, number = {1}, pages = {6:6--6:6}, volume = {10}, address = {New York, NY, USA}, doi = {10.1145/3178422.3178426}, language = {EN}, publisher = {ACM}, url = {http://doi.acm.org/10.1145/3178422.3178426} } @Article{Timmerer2018a, author = {Timmerer, Christian}, journal = {SIGMultimedia Records}, title = {MPEG Column: 120th MPEG Meeting in Macau, China}, year = {2018}, issn = {1947-4598}, month = jan, number = {3}, pages = {4:4--4:4}, volume = {9}, address = {New York, NY, USA}, doi = {10.1145/3210241.3210247}, language = {EN}, publisher = {ACM}, url = {http://doi.acm.org/10.1145/3210241.3210247} } @Article{Taschwer2018, title = {{Automatic separation of compound figures in scientific articles}}, author = {Taschwer, Mario and Marques, Oge}, journal = {Multimedia Tools and Applications}, year = {2018}, month = {Januar}, number = {77}, pages = {519--548}, abstract = {Content-based analysis and retrieval of digital images found in scientific articles is often hindered by images consisting of multiple subfigures (compound figures). We address this problem by proposing a method (ComFig) to automatically classify and separate compound figures, which consists of two main steps: (i) a supervised compound figure classifier (ComFig classifier) discriminates between compound and non-compound figures using task-specific image features; and (ii) an image processing algorithm is applied to predicted compound images to perform compound figure separation (ComFig separation). The proposed ComFig classifier is shown to achieve state-of-the-art classification performance on a published dataset. Our ComFig separation algorithm shows superior separation accuracy on two different datasets compared to other known automatic approaches. Finally, we propose a method to evaluate the effectiveness of the ComFig chain combining classifier and separation algorithm, and use it to optimize the misclassification loss of the ComFig classifier for maximal effectiveness in the chain.}, doi = {10.1007/s11042-016-4237-x}, url = {https://link.springer.com/article/10.1007%2Fs11042-016-4237-x#enumeration} } @Article{Stankovski2018, author = {Stankovski, Vlado and Prodan, Radu}, title = {Guest Editors’ Introduction: Special Issue on Storagefor the Big Data Era}, journal = {Journal of Grid Computing}, year = {2018}, month = {März}, doi = {10.1007/s10723-018-9439-1}, url = {https://link.springer.com/article/10.1007/s10723-018-9439-1} } @Article{Ricci2018, author = {Ricci, Laura and Iosup, Alexander and Prodan, Radu}, title = {{Large Scale Cooperative Virtual Environments}}, journal = {Concurrency and Computation: Practice and Experience}, year = {2018}, month = {Juli}, doi = {10.1002/cpe.4878}, url = {https://onlinelibrary.wiley.com/doi/10.1002/cpe.4878} } @Article{Pop2018a, author = {Pop, Florin and Prodan, Radu and Antoniu, Gabriel}, title = {RM-BDP: Resource management for Big Data platforms}, journal = {Future Generation Computer Systems}, year = {2018}, volume = {86}, pages = {961--963}, month = {September}, abstract = {Nowadays, when we face with numerous data, when data cannot be classified into regular relational databases and new solutions are required, and when data are generated and processed rapidly, we need powerful platforms and infrastructure as support. Extracting valuable information from raw data is especially difficult considering the velocity of growing data from year to year and the fact that 80% of data is unstructured. In addition, data sources are heterogeneous (various sensors, users with different profiles, etc.) and are located in different situations or contexts. Cloud computing, which concerns large-scale interconnected systems with the main purpose of aggregation and efficient exploiting the power of widely distributed resources, represent one viable solution. Resource management and task scheduling play an essential role, in cases where one is concerned with optimized use of resources (Negru et al., 2017) [1].The goal of this special issue is to explore new directions and approaches for reasoning about advanced resource management and task scheduling methods and algorithms for Big Data platforms. The accepted papers present new results in the domain of resource management and task scheduling, Cloud platforms supporting Big Data processing, data handling and Big Data applications.}, doi = {10.1016/j.future.2018.05.018}, url = {https://www.sciencedirect.com/science/article/pii/S0167739X18311245?via%3Dihub} } @Article{Pop2018, author = {Pop, Florin and Iusup, Alexandru and Prodan, Radu}, title = {{HPS-HDS}: High Performance Scheduling for Heterogeneous Distributed Systems}, journal = {Future Generation Computer Systems}, year = {2018}, volume = {78}, pages = {242-244}, month = {January}, booktitle = {Future Generation Computer Systems}, chapter = {1}, doi = {10.1016/j.future.2017.09.012}, publisher = {Elsevier}, url = {http://www.sciencedirect.com/science/article/pii/S0167739X17319659} } @Article{Petscharnig2018, title = {Binary convolutional neural network features off-the-shelf for image to video linking in endoscopic multimedia databases}, author = {Stefan Petscharnig and Klaus Schöffmann}, journal = {Multimedia Tools and Applications}, year = {2018}, month = {Mai}, abstract = {With a rigorous long-term archival of endoscopic surgeries, vast amounts of video and image data accumulate. Surgeons are not able to spend their valuable time to manually search within endoscopic multimedia databases (EMDBs) or manually maintain links to interesting sections in order to quickly retrieve relevant surgery sections. Enabling the surgeons to quickly access the relevant surgery scenes, we utilize the fact that surgeons record external images additionally to the surgery video and aim to link them to the appropriate video sequence in the EMDB using a query-by-example approach. We propose binary Convolutional Neural Network (CNN) features off-the-shelf and compare them to several baselines: pixel-based comparison (PSNR), image structure comparison (SSIM), hand-crafted global features (CEDD and feature signatures), as well as CNN baselines Histograms of Class Confidences (HoCC) and Neural Codes (NC). For evaluation, we use 5.5 h of endoscopic video material and 69 query images selected by medical experts and compare the performance of the aforementioned image mathing methods in terms of video hit rate and distance to the true playback time stamp (PTS) for correct video predictions. Our evaluation shows that binary CNN features are compact, yet powerful image descriptors for retrieval in the endoscopic imaging domain. They are able to maintain state-of-the-art performance, while providing the benefit of low storage space requirements and hence provide the best compromise.}, doi = {10.1007/s11042-018-6016-3}, url = {https://link.springer.com/article/10.1007/s11042-018-6016-3?wt_mc=Internal.Event.1.SEM.ArticleAuthorOnlineFirst} } @Article{Matha2018, author = {Mathá, Roland and Kimovski, Dragi and Prodan, Radu and Gusev, Marjan}, journal = {International Journal of Parallel, Emergent and Distributed Systems}, title = {{A new model for cloud elastic services efficiency}}, year = {2018}, month = {Februar}, abstract = {The speedup measures the improvement in performance when the computational resources are being scaled. The efficiency, on the other side, provides the ratio between the achieved speedup and the number of scaled computational resources (processors). Both parameters (speedup and efficiency), which are defined according to Amdahl’s Law, provide very important information about performance of a computer system with scaled resources compared with a computer system with a single processor. However, as cloud elastic services’ load is variable, apart of the scaled resources, it is vital to analyse the load in order to determine which system is more effective and efficient. Unfortunately, both the speedup and efficiency are not sufficient enough for proper modeling of cloud elastic services, as the assumptions for both the speedup and efficiency are that the system’s resources are scaled, while the load is constant. In this paper, we extend the scaling of resources and define two additional scaled systems by (i) scaling the load and (ii) scaling both the load and resources. We introduce a model to determine the efficiency for each scaled system, which can be used to compare the efficiencies of all scaled systems, regardless if they are scaled in terms of load or resources. We have evaluated the model by using Windows Azure and the experimental results confirm the theoretical analysis. Although one can argue that web services are scalable and comply with Gustafson’s Law only, we provide a taxonomy that classifies scaled systems based on the compliance with both the Amdahl’s and Gustafson’s laws.For three different scaled systems (scaled resources R, scaled load L and combination RL), we introduce a model to determine the scaling efficiency. Our model extends the current definition of efficiency according to Amdahl’s Law, which assumes scaling the resources, and not the load.}, doi = {10.1080/17445760.2018.1434174}, url = {https://www.tandfonline.com/doi/full/10.1080/17445760.2018.1434174} } @Article{Lokoc2018, title = {On influential trends in interactive video retrieval: Video Browser Showdown 2015-2017}, author = {Jakub Lokoč and Werner Bailer and Klaus Schöffmann and Bernd Münzer and George M. Awad}, journal = {IEEE Transactions on Multimedia}, year = {2018}, month = {April}, abstract = {The last decade has seen innovations that make video recording, manipulation, storage and sharing easier than ever before, thus impacting many areas of life. New video retrieval scenarios emerged as well, which challenge the state-of-the-art video retrieval approaches. Despite recent advances in content analysis, video retrieval can still benefit from involving the human user in the loop. We present our experience with a class of interactive video retrieval scenarios and our methodology to stimulate the evolution of new interactive video retrieval approaches. More specifically, the Video Browser Showdown evaluation campaign is thoroughly analyzed, focusing on the years 2015-2017. Evaluation scenarios, objectives and metrics are presented, complemented by the results of the annual evaluations. The results reveal promising interactive video retrieval techniques adopted by the most successful tools and confirm assumptions about the different complexity of various types of interactive retrieval scenarios. A comparison of the interactive retrieval tools with automatic approaches (including fully automatic and manual query formulation) participating in the TRECVID 2016 Ad-hoc Video Search (AVS) task is discussed. Finally, based on the results of data analysis, a substantial revision of the evaluation methodology for the following years of the Video Browser Showdown is provided.}, doi = {10.1109/TMM.2018.2830110}, url = {https://ieeexplore.ieee.org/document/8352047/?tp=&arnumber=8352047&filter%3DAND(p_IS_Number:4456689)} } @Article{Khalid2018, author = {Khalid, Yasir Noman and Aleem, Muhammad and Prodan, Radu and Muhammad, Azhar Iqbal and Islam, Muhammad Arshad}, title = {E-OSched: a load balancing scheduler for heterogeneous multicores}, journal = {Journal of Supercomputing}, year = {2018}, month = {Mai}, abstract = {The contemporary multicore era has adhered to the heterogeneous computing devices as one of the proficient platforms to execute compute-intensive applications. These heterogeneous devices are based on CPUs and GPUs. OpenCL is deemed as one of the industry standards to program heterogeneous machines. The conventional application scheduling mechanisms allocate most of the applications to GPUs while leaving CPU device underutilized. This underutilization of slower devices (such as CPU) often originates the sub-optimal performance of data-parallel applications in terms of load balance, execution time, and throughput. Moreover, multiple scheduled applications on a heterogeneous system further aggravate the problem of performance inefficiency. This paper is an attempt to evade the aforementioned deficiencies via initiating a novel scheduling strategy named OSched. An enhancement to the OSched named E-OSched is also part of this study. The OSched performs the resource-aware assignment of jobs to both CPUs and GPUs while ensuring a balanced load. The load balancing is achieved via contemplation on computational requirements of jobs and computing potential of a device. The load-balanced execution is beneficiary in terms of lower execution time, higher throughput, and improved utilization. The E-OSched reduces the magnitude of the main memory contention during concurrent job execution phase. The mathematical model of the proposed algorithms is evaluated by comparison of simulation results with different state-of-the-art scheduling heuristics. The results revealed that the proposed E-OSched has performed significantly well than the state-of-the-art scheduling heuristics by obtaining up to 8.09% improved execution time and up to 7.07% better throughput.}, doi = {10.1007/s11227-018-2435-1}, url = {https://link.springer.com/article/10.1007%2Fs11227-018-2435-1#copyrightInformation} } @Article{HH_martina_Dez, author = {Yanmaz, Evsen and Yahyanejad, Saeed and Rinner, Bernhard and Hellwagner, Hermann and Bettstetter, Christian}, journal = {Ad Hoc Networks}, title = {Drone networks: Communications, coordination, and sensing}, year = {2018}, month = {jan}, pages = {1-15}, volume = {68}, abstract = {Small drones are being utilized in monitoring, transport, safety and disaster management, and other domains. Envisioning that drones form autonomous networks incorporated into the air traffic, we describe a high-level architecture for the design of a collaborative aerial system consisting of drones with on-board sensors and embedded processing, coordination, and networking capabilities. We implement a multi-drone system consisting of quadcopters and demonstrate its potential in disaster assistance, search and rescue, and aerial monitoring. Furthermore, we illustrate design challenges and present potential solutions based on the lessons learned so far.}, address = {Amsterdam}, doi = {10.1016/j.adhoc.2017.09.001}, keywords = {Drones, Unmanned aerial vehicle networks, Wireless sensor networks, Vehicular communications, Cooperative aerial imaging, Search and rescue}, language = {EN}, publisher = {Elsevier}, url = {https://www.sciencedirect.com/science/article/pii/S1570870517301671} } @Article{HH_martina, author = {Pohl, Daniela and Bouchachia, Abdelhamid and Hellwagner, Hermann}, journal = {Expert Systems with Applications}, title = {Batch-based active learning: Application to social media data for crisis management}, year = {2018}, month = {mar}, pages = {232-244}, volume = {93}, abstract = {Classification of evolving data streams is a challenging task, which is suitably tackled with online learning approaches. Data is processed instantly requiring the learning machinery to (self-)adapt by adjusting its model. However for high velocity streams, it is usually difficult to obtain labeled samples to train the classification model. Hence, we propose a novel online batch-based active learning algorithm (OBAL) to perform the labeling. OBAL is developed for crisis management applications where data streams are generated by the social media community. OBAL is applied to discriminate relevant from irrelevant social media items. An emergency management user will be interactively queried to label chosen items. OBAL exploits the boundary items for which it is highly uncertain about their class and makes use of two classifiers: k-Nearest Neighbors (kNN) and Support Vector Machine (SVM). OBAL is equipped with a labeling budget and a set of uncertainty strategies to identify the items for labeling. An extensive analysis is carried out to show OBAL’s performance, the sensitivity of its parameters, and the contribution of the individual uncertainty strategies. Two types of datasets are used: synthetic and social media datasets related to crises. The empirical results illustrate that OBAL has a very good discrimination power.}, address = {Amsterdam}, doi = {10.1016/j.eswa.2017.10.026}, language = {EN}, publisher = {Elsevier Ltd.}, url = {http://www.sciencedirect.com/science/article/pii/S095741741730708X} } @Article{Ge2018, author = {Ge, Chang and Wang, Ning and Koong Chai, Wei and Hellwagner, Hermann}, title = {{QoE-Assured 4K HTTP Live Streaming via Transient Segment Holding at Mobile Edge}}, journal = {IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS}, year = {2018}, volume = {36}, number = {8}, pages = {1816--1830}, month = {Juli}, abstract = {HTTP-based live streaming has become increasingly popular in recent years, and more users have started generating 4K live streams from their devices (e.g., mobile phones) through social-media service providers like Facebook or YouTube. If the audience is located far from a live stream source across the global Internet, TCP throughput becomes substantially suboptimal due to slow start and congestion control mechanisms. This is especially the case when the end-to-end content delivery path involves radio access network at the last mile. As a result, the data rate perceived by a mobile receiver may not meet the high requirement of 4K video streams, which causes deteriorated quality-of-experience (QoE). In this paper, we propose a scheme named edge-based transient holding of live segment (ETHLE), which addresses the above-mentioned issue by performing context-aware transient holding of video segments at the mobile edge with virtualized content caching capability. Through holding the minimum number of live video segments at the mobile edge cache in a context-aware manner, the ETHLE scheme is able to achieve seamless 4K live streaming experiences across the global Internet by eliminating buffering and substantially reducing initial startup delay and live stream latency. It has been deployed as a virtual network function at an LTE-A network, and its performance has been evaluated using real live stream sources that are distributed around the world. The significance of this paper is that by leveraging virtualized caching resources at the mobile edge, we address the conventional transport-layer bottleneck and enable QoE-assured Internet-wide live streaming services with high data rate requirements.}, doi = {10.1109/JSAC.2018.2845000}, url = {https://ieeexplore.ieee.org/abstract/document/8374847}, pdf = {https://www.itec.aau.at/bib/files/08374847.pdf} } @Article{Bentaleb2018, title = {A Survey on Bitrate Adaptation Schemes for Streaming Media over HTTP}, author = {Bentaleb, Abdelhak and Taani, Bayan and Begen, Ali Cengiz and Timmerer, Christian and Zimmermann, Roger}, journal = {IEEE Communications Surveys Tutorials}, year = {2018}, doi = {10.1109/COMST.2018.2862938}, issn = {1553-877X} } @Article{Aleem2018, author = {Aleem, Muhammad and Prodan, Radu}, title = {{On the Parallel Programmability of JavaSymphony for Multi-cores and Clusters}}, journal = {International Journal of Ad Hoc and Ubiquitous Computing}, year = {2018}, abstract = {This paper explains the programming aspects of a promising Java-based programming and execution framework called JavaSymphony. JavaSymphony provides unified high-level programming constructs for applications related to shared, distributed, hybrid memory parallel computers, and co-processors accelerators. JavaSymphony applications can be executed on a variety of multi-/many-core conventional and data-parallel architectures. JavaSymphony is based on the concept of dynamic virtual architectures, which allows programmers to define a hierarchical structure of the underlying computing resources and to control load-balancing and task-locality. In addition to GPU support, JavaSymphony provides a multi-core aware scheduling mechanism capable of mapping parallel applications on large multi-core machines and heterogeneous clusters. Several real applications and benchmarks (on modern multi-core computers, heterogeneous clusters, and machines consisting of a combination of different multi-core CPU and GPU devices) have been used to evaluate the performance. The results demonstrate that the JavaSymphony outperforms the Java implementations, as well as other modern alternative solutions.}, doi = {10.1504/IJAHUC.2017.10006700}, url = {http://www.inderscience.com/info/ingeneral/forthcoming.php?jcode=IJAHUC} } @Article{Zabrovskiy2017a, author = {Zabrovskiy, Anatoliy and Petrov, Evgeny and Kuzmin, Evgeny and Timmerer, Christian}, journal = {arXiv.org [cs.MM]}, title = {Evaluation of the Performance of Adaptive {HTTP} Streaming Systems}, year = {2017}, month = {oct}, pages = {7}, volume = {abs/1710.02459}, abstract = {Adaptive video streaming over HTTP is becoming omnipresent in our daily life. In the past, dozens of research papers have proposed novel approaches to address different aspects of adaptive streaming and a decent amount of player implementations (commercial and open source) are available. However, state of the art evaluations are sometimes superficial as many proposals only investigate a certain aspect of the problem or focus on a specific platform – player implementations used in actual services are rarely considered. HTML5 is now available on many platforms and foster the deployment of adaptive media streaming applications. We propose a common evaluation framework for adaptive HTML5 players and demonstrate its applicability by evaluating eight different players which are actually deployed in real-world services.}, address = {N.N.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1710.02459.pdf}, publisher = {N.N.}, url = {http://arxiv.org/abs/1710.02459} } @Article{Timmerer2017i, author = {Timmerer, Christian}, journal = {IEEE Communications Standards Magazine}, title = {Immersive Media Delivery: Overview of Ongoing Standardization Activities}, year = {2017}, issn = {2471-2825}, month = {dec}, number = {4}, pages = {71--74}, volume = {1}, abstract = {More and more immersive media applications and services are emerging on the market, but lack international standards to enable interoperability. This article provides an overview about ongoing standardization efforts in this exciting domain and highlights open research and standardization issues.}, address = {N.N.}, doi = {10.1109/MCOMSTD.2017.1700038}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/08258607.pdf}, publisher = {IEEE Communications Society} } @Article{Timmerer2017h, author = {Timmerer, Christian and Begen, Ali Cengiz}, journal = {Computing Now}, title = {Advancing Multimedia Content Distribution}, year = {2017}, month = {dec}, pages = {1}, address = {Los Alamitos, CA, USA}, language = {EN}, publisher = {IEEE Computer Society [online]}, url = {https://www.computer.org/web/computingnow/archive/advancing-multimedia-content-distribution-december-2017-introduction} } @Article{Timmerer2017g, author = {Timmerer, Christian}, journal = {SIGMultimedia Records}, title = {MPEG Column: 116th MPEG Meeting}, year = {2017}, issn = {1947-4598}, month = {jul}, number = {4}, pages = {N.N.}, volume = {8}, address = {New York, NY, USA}, doi = {10.1145/3129151.3129152}, language = {EN}, publisher = {ACM}, url = {http://doi.acm.org/10.1145/3129151.3129152} } @Article{Timmerer2017f, author = {Timmerer, Christian}, journal = {SIGMultimedia Records}, title = {MPEG Column: 117th MPEG Meeting}, year = {2017}, issn = {1947-4598}, month = {jul}, number = {1}, pages = {N.N.}, volume = {9}, address = {New York, NY, USA}, doi = {10.1145/3129151.3129153}, language = {EN}, publisher = {ACM}, url = {http://doi.acm.org/10.1145/3129151.3129153} } @Article{Timmerer2017e, author = {Timmerer, Christian}, journal = {SIGMultimedia Records}, title = {MPEG Column: 118th MPEG Meeting}, year = {2017}, issn = {1947-4598}, month = {oct}, number = {4}, pages = {N.N.}, volume = {8}, address = {New York, NY, USA}, doi = {10.1145/3149647.3149656}, language = {EN}, publisher = {ACM}, url = {http://doi.acm.org/10.1145/3149647.3149656} } @Article{Timmerer2017d, author = {Timmerer, Christian}, journal = {SIGMultimedia Records}, title = {MPEG Column: 119th MPEG Meeting in Turin, Italy}, year = {2017}, issn = {1947-4598}, month = {dec}, number = {2}, pages = {N.N.}, volume = {9}, address = {New York, NY, USA}, doi = {10.1145/3173058.3173061}, language = {EN}, publisher = {ACM}, url = {http://doi.acm.org/10.1145/3173058.3173061} } @Article{Timmerer2017c, author = {Timmerer, Christian}, journal = {SIGMultimedia Records}, title = {Report from ACM MMSys 2017}, year = {2017}, issn = {1947-4598}, month = {dec}, number = {2}, pages = {N.N.}, volume = {9}, address = {New York, NY, USA}, doi = {10.1145/3173058.3173068}, language = {EN}, publisher = {ACM}, url = {http://doi.acm.org/10.1145/3173058.3173068} } @Article{Timmerer2017a, author = {Timmerer, Christian and Begen, Ali Cengiz}, journal = {ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)}, title = {Best Papers of the 2016 ACM Multimedia Systems (MMSys) Conference and Workshop on Network and Operating System Support for Digital Audio and Video (NOSSDAV) 2016}, year = {2017}, month = {jun}, number = {3s}, pages = {40:1--40:2}, volume = {13}, address = {New York, NY, USA}, doi = {10.1145/3084539}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/a40-timmerer.pdf}, publisher = {ACM Digital Library}, url = {http://doi.acm.org/10.1145/3084539} } @Article{Schoeffmann2017MTAPHusslein, author = {Schoeffmann, Klaus and Husslein, Heinrich and Kletz, Sabrina and Petscharnig, Stefan and Münzer, Bernd and Beecks, Christian}, journal = {Multimedia Tools and Applications}, title = {Video Retrieval in Laparoscopic Video Recordings with Dynamic Content Descriptors}, year = {2017}, month = {nov}, pages = {18}, address = {USA}, language = {EN}, publisher = {Springer US} } @Article{Rainer2017a, author = {Rainer, Benjamin and Petscharnig, Stefan and Timmerer, Christian and Hellwagner, Hermann}, journal = {IEEE Transactions on Multimedia}, title = {Statistically Indifferent Quality Variation: An Approach for Reducing Multimedia Distribution Cost for Adaptive Video Streaming Services}, year = {2017}, month = {mar}, pages = {13}, volume = {19}, abstract = {Forecasts predict that Internet traffic will continue to grow in the near future. A huge share of this traffic is caused by multimedia streaming. The Quality of Experience (QoE) of such streaming services is an important aspect and in most cases the goal is to maximize the bit rate which -- in some cases -- conflicts with the requirements of both consumers and providers. For example, in mobile environments users may prefer a lower bit rate to come along with their data plan. Likewise, providers aim at minimizing bandwidth usage in order to reduce costs by transmitting less data to users while maintaining a high QoE. Today's adaptive video streaming services try to serve users with the highest bit rates which consequently results in high QoE. In practice, however, some of these high bit rate representations may not differ significantly in terms of perceived video quality compared to lower bit rate representations. In this paper, we present a novel approach to determine the statistically indifferent quality variation (SIQV) of adjacent video representations for adaptive video streaming services by adopting standard objective quality metrics and existing QoE models. In particular, whenever the quality variation between adjacent representations is imperceptible from a statistical point of view, the representation with higher bit rate can be substituted with a lower bit rate representation. As expected, this approach results in savings with respect to bandwidth consumption while still providing a high QoE for users. The approach is evaluated subjectively with a crowdsourcing study. Additionally, we highlight the benefits of our approach, by providing a case study that extrapolates possible savings for providers.}, address = {New York, USA}, doi = {10.1109/TMM.2016.2629761}, keywords = {Adaptive Video Streaming, Quality of Experience, MPEG-DASH}, language = {EN}, publisher = {IEEE}, url = {http://ieeexplore.ieee.org/document/7745907/} } @Article{Posch2017a, author = {Posch, Daniel and Rainer, Benjamin and Hellwagner, Hermann}, journal = {IEEE/ACM Transactions on Networking}, title = {SAF: Stochastic Adaptive Forwarding in Named Data Networking}, year = {2017}, month = {apr}, number = {2}, pages = {14}, volume = {25}, abstract = {Forwarding decisions in classical IP-based networks are predetermined by routing. This is necessary to avoid loops, inhibiting opportunities to implement an adaptive and intelligent forwarding plane. Consequently, content distribution efficiency is reduced due to a lack of inherent multi-path transmission. In Named Data Networking (NDN) instead, routing shall hold a supporting role to forwarding, providing sufficient potential to enhance content dissemination at the forwarding plane. In this paper we design, implement, and evaluate a novel probability-based forwarding strategy, called Stochastic Adaptive Forwarding (SAF) for NDN. SAF imitates a self-adjusting water pipe system, intelligently guiding and distributing Interests through network crossings circumventing link failures and bottlenecks. Just as real pipe systems, SAF employs overpressure valves enabling congested nodes to lower pressure autonomously. Through an implicit feedback mechanism it is ensured that the fraction of the traffic forwarded via congested nodes decreases. By conducting simulations we show that our approach outperforms existing forwarding strategies in terms of the Interest satisfaction ratio in the majority of the evaluated scenarios. This is achieved by extensive utilization of NDN's multipath and content-lookup capabilities without relying on the routing plane. SAF explores the local environment by redirecting requests that are likely to be dropped anyway. This enables SAF to identify new paths to the content origin or to cached replicas, circumventing link failures and resource shortages without relying on routing updates.}, address = {New York, USA}, doi = {10.1109/TNET.2016.2614710}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/saf.pdf}, publisher = {IEEE}, url = {https://dx.doi.org/10.1109/TNET.2016.2614710} } @Article{Posch2017, author = {Posch, Daniel and Rainer, Benjamin and Hellwagner, Hermann}, journal = {Computer Communication Review}, title = {Towards a Context-Aware Forwarding Plane in Named Data Networking supporting QoS}, year = {2017}, month = {jan}, number = {1}, pages = {9}, volume = {47}, abstract = {The emergence of Information-Centric Networking (ICN) provides considerable opportunities for context-aware data distribution in the network's forwarding plane. While packet forwarding in classical IP-based networks is basically predetermined by routing, ICN foresees an adaptive forwarding plane considering the requirements of network applications. As research in this area is still at an early stage, most of the work so far focused on providing the basic functionality, rather than on considering the available context information to improve Quality of Service (QoS). This article investigates to which extent existing forwarding strategies take account of the available context information and can therefore increase service quality. The article examines a typical scenario encompassing different user applications (Voice over IP, video streaming, and classical data transfer) with varying demands (context), and evaluates how well the applications' requirements are met by the existing strategies.}, address = {New York, USA}, doi = {10.1145/3041027.3041029}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/ccr.pdf}, publisher = {ACM SIGCOMM}, url = {https://dl.acm.org/citation.cfm?doid=3041027.3041029} } @Article{Pinheiro2017, author = {Pinheiro, Antonio and Timmerer, Christian}, journal = {SIGMultimedia Records}, title = {Standards Column: JPEG and MPEG}, year = {2017}, issn = {1947-4598}, month = {oct}, number = {1}, pages = {N.N.}, volume = {9}, address = {New York, NY, USA}, doi = {10.1145/3149647.3149648}, language = {EN}, publisher = {ACM}, url = {http://doi.acm.org/10.1145/3149647.3149648} } @Article{Petscharnig2017, author = {Petscharnig, Stefan and Schoeffmann, Klaus}, journal = {Multimedia Tools and Applications}, title = {Learning laparoscopic video shot classification for gynecological surgery}, year = {2017}, issn = {1573-7721}, month = {apr}, pages = {1-19}, abstract = {Videos of endoscopic surgery are used for education of medical experts, analysis in medical research, and documentation for everyday clinical life. Hand-crafted image descriptors lack the capabilities of a semantic classification of surgical actions and video shots of anatomical structures. In this work, we investigate how well single-frame convolutional neural networks (CNN) for semantic shot classification in gynecologic surgery work. Together with medical experts, we manually annotate hours of raw endoscopic gynecologic surgery videos showing endometriosis treatment and myoma resection of over 100 patients. The cleaned ground truth dataset comprises 9 h of annotated video material (from 111 different recordings). We use the well-known CNN architectures AlexNet and GoogLeNet and train these architectures for both, surgical actions and anatomy, from scratch. Furthermore, we extract high-level features from AlexNet with weights from a pre-trained model from the Caffe model zoo and feed them to an SVM classifier. Our evaluation shows that we reach an average recall of .697 and .515 for classification of anatomical structures and surgical actions respectively using off-the-shelf CNN features. Using GoogLeNet, we achieve a mean recall of .782 and .617 for classification of anatomical structures and surgical actions respectively. With AlexNet the achieved recall is .615 for anatomical structures and .469 for surgical action classification respectively. The main conclusion of our work is that advances in general image classification methods transfer to the domain of endoscopic surgery videos in gynecology. This is relevant as this domain is different from natural images, e.g. it is distinguished by smoke, reflections, or a limited amount of colors.}, address = {Berlin, Heidelberg, New York}, doi = {10.1007/s11042-017-4699-5}, keywords = {Video classification, Deep learning, Convolutional Neural Network}, language = {EN}, publisher = {Springer}, url = {http://dx.doi.org/10.1007/s11042-017-4699-5} } @Article{Muenzer2017, author = {Münzer, Bernd and Schoeffmann, Klaus and Böszörmenyi, Laszlo}, journal = {Multimedia Tools and Applications}, title = {Content-based processing and analysis of endoscopic images and videos: A survey}, year = {2017}, month = {jan}, pages = {1-40}, abstract = {In recent years, digital endoscopy has established as key technology for medical screenings and minimally invasive surgery. Since then, various research communities with manifold backgrounds have picked up on the idea of processing and automatically analyzing the inherently available video signal that is produced by the endoscopic camera. Proposed works mainly include image processing techniques, pattern recognition, machine learning methods and Computer Vision algorithms. While most contributions deal with real-time assistance at procedure time, the post-procedural processing of recorded videos is still in its infancy. Many post-processing problems are based on typical Multimedia methods like indexing, retrieval, summarization and video interaction, but have only been sparsely addressed so far for this domain. The goals of this survey are (1) to introduce this research field to a broader audience in the Multimedia community to stimulate further research, (2) to describe domain-specific characteristics of endoscopic videos that need to be addressed in a pre-processing step, and (3) to systematically bring together the very diverse research results for the first time to provide a broader overview of related research that is currently not perceived as belonging together.}, address = {Berlin, Heidelberg, New York}, doi = {10.1007/s11042-016-4219-z}, language = {EN}, publisher = {Springer}, url = {https://link.springer.com/article/10.1007/s11042-016-4219-z} } @Article{HHmartina2017, author = {Zhu, X and Mao, S and Hassan, M Hassan and Hellwagner, Hermann}, journal = {IEEE Transactions on Multimedia}, title = {Guest Editorial: Video Over Future Networks}, year = {2017}, issn = {1941-0077}, month = {oct}, number = {10}, pages = {2133 - 2135}, volume = {19}, abstract = {The papers in this special issue focus on the deployment of video over future networks. The past decade has seen how major improvements in broadband and mobile networks have led to widespread popularity of video streaming applications, and how the latter now becomes the major driving force behind exponentially growing Internet traffic. This special issue seeks to investigate these future Internet technologies through the prism of its most prevalent application, that of video communications. video.}, address = {Piscataway, NJ}, doi = {10.1109/TMM.2017.2743638}, keywords = {Special issues and sections, Streaming media, Mobile communication, Network architecture, Quality of experience, Ultra-high definition video}, language = {EN}, publisher = {IEEE}, url = {http://ieeexplore.ieee.org/document/8038904/} } @Article{timmerer2016_cn, author = {Timmerer, Christian}, journal = {Computing Now}, title = {The Future of Multimedia on the Internet}, year = {2016}, month = {nov}, pages = {1}, address = {Los Alamitos, CA, USA}, language = {EN}, publisher = {IEEE Computer Society [online]}, url = {https://www.computer.org/web/computingnow/archive/future-of-multimedia-on-the-internet-november-2016-introduction} } @Article{Westphal2016_jsac, author = {Westphal, Cedric and Melodia, Tommaso and Zhu, Wenww and Timmerer, Christian}, journal = {IEEE Journal on Selected Areas in Communications}, title = {Guest Editorial Video Distribution Over Future Internet}, year = {2016}, month = {aug}, number = {8}, pages = {2061-2062}, volume = {34}, address = {New York}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/JSAC2016_GE.pdf}, publisher = {IEEE Communications Society} } @Article{TimmererMR2016, author = {Timmerer, Christian and Maiero, Matteo and Rainer, Benjamin}, journal = {arXiv.org [cs.MM]}, title = {Which Adaptation Logic? An Objective and Subjective Performance Evaluation of HTTP-based Adaptive Media Streaming Systems}, year = {2016}, month = {jun}, pages = {11}, volume = {abs/1606.00341}, address = {N.N.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1606.00341.pdf}, publisher = {N.N.}, url = {http://arxiv.org/abs/1606.00341} } @Article{TimmererB2016, author = {Timmerer, Christian and Bertoni, Alan}, journal = {arXiv.org [cs.MM]}, title = {Advanced Transport Options for the Dynamic Adaptive Streaming over HTTP}, year = {2016}, month = {jun}, pages = {6}, volume = {abs/1606.00264}, address = {N.N.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1606.00264.pdf}, publisher = {N.N.}, url = {http://arxiv.org/abs/1606.00264} } @Article{Taschwer2016a, author = {Taschwer, Mario and Marques, Oge}, journal = {Multimedia Tools and Applications}, title = {Automatic Separation of Compound Figures in Scientific Articles}, year = {2016}, issn = {1573-7721}, month = {dec}, pages = {1--30}, abstract = {Content-based analysis and retrieval of digital images found in scientific articles is often hindered by images consisting of multiple subfigures (compound figures). We address this problem by proposing a method (ComFig) to automatically classify and separate compound figures, which consists of two main steps: (i) a supervised compound figure classifier (ComFig classifier) discriminates between compound and non-compound figures using task-specific image features; and (ii) an image processing algorithm is applied to predicted compound images to perform compound figure separation (ComFig separation). The proposed ComFig classifier is shown to achieve state-of-the-art classification performance on a published dataset. Our ComFig separation algorithm shows superior separation accuracy on two different datasets compared to other known automatic approaches. Finally, we propose a method to evaluate the effectiveness of the ComFig chain combining classifier and separation algorithm, and use it to optimize the misclassification loss of the ComFig classifier for maximal effectiveness in the chain.}, address = {New York}, doi = {10.1007/s11042-016-4237-x}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/fig-separation-mtap.pdf}, publisher = {Springer} } @Article{SchoeffmannBurgstaller2016, author = {Schoeffmann, Klaus and Burgstaller, Lukas}, journal = {International Journal of Multimedia Data Engineering and Management}, title = {A Convenient Interface for Video Navigation on Smartphones}, year = {2016}, month = {jun}, number = {3}, pages = {1-16}, volume = {7}, address = {Hershey, PA, USA}, language = {EN}, publisher = {IGI Pub} } @Article{Rainer2016a, author = {Rainer, Benjamin and Posch, Daniel and Leibetseder, Andreas and Theuermann, Sebastian and Hellwagner, Hermann}, journal = {Communications Magazine, IEEE}, title = {A Low-Cost NDN Testbed on Banana Pi Routers}, year = {2016}, month = sep, number = {9}, pages = {6}, volume = {54}, abstract = {The computer communication research community shows significant interest in the paradigm of Information-Centric Networking (ICN). Continuously, new proposals for ICN-related challenges (caching, forwarding, etc.) are published. However, due to a lack of a readily available testbed, the majority of these proposals is evaluated either by theoretical analysis and/or by conducting network simulations potentially masking further challenges that are not observable in synthetic environments. Therefore, this article presents a framework for an ICN testbed using low-budget physical hardware with little deployment and maintenance effort for the individual researcher; specifically, Named Data Networking is considered. The employed hardware and software are powerful enough for most research projects, but extremely resource intensive tasks may push both components towards their limits. The testbed framework is based on well established open source software and provides the tools to readily investigate important ICN characteristics on physical hardware emulating arbitrary network topologies. The article discusses the testbed architecture and provides first results obtained from emulations that investigate the performance of various forwarding strategies. The results indicate that further challenges have to be overcome when heading towards a real-world deployment of ICN-based communication.}, address = {New York, USA}, keywords = {ICN}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/commmagRainer.pdf}, publisher = {IEEE} } @Article{Rainer2016, author = {Rainer, Benjamin and Posch, Daniel and Hellwagner, Hermann}, journal = {Journal on Selected Areas in Communications}, title = {Investigating the Performance of Pull-based Dynamic Adaptive Streaming in NDN}, year = {2016}, issn = {1558-0008}, month = {aug}, number = {8}, pages = {11}, volume = {34}, abstract = {Adaptive content delivery is the state-of-the-art in real-time multimedia streaming. Leading streaming approaches, e.g., MPEG-DASH and Apple HLS, have been developed for classical IP-based networks, providing effective streaming by means of pure client-based control and adaptation. However, the research activities of the Future Internet community adopt a new course that is different from today's host-based communication model. So-called Information-Centric Networks are of considerable interest and are advertised as enablers for intelligent networks, where effective content delivery is to be provided as an inherent network feature. This paper investigates the performance gap between pure client-driven adaptation and the theoretical optimum in the promising Future Internet architecture Named Data Networking (NDN). The theoretical optimum is derived by modeling multimedia streaming in NDN as a fractional Multi-Commodity Flow Problem and by extending it taking caching into account. We investigate the multimedia streaming performance under different forwarding strategies, exposing the interplay of forwarding strategies and adaptation mechanisms. Furthermore, we examine the influence of network inherent caching on the streaming performance by varying the caching polices and the cache sizes.}, address = {New York, USA}, doi = {10.1109/JSAC.2016.2577365}, keywords = {Information-Centric Networking; Named Data Networking; Multimedia; Dynamic Adaptive Streaming.}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/jsac.pdf}, publisher = {IEEE} } @Article{PorJonsson2016, author = {Por Jonsson, Björn and Gurrin, Cathal and Schoeffmann, Klaus}, journal = {ACM SIGMultimedia Records}, title = {Report from the MMM Special Session Perspectives on Multimedia Analytics}, year = {2016}, month = {may}, number = {2}, pages = {1-2}, volume = {2016}, abstract = {This report summarizes the presentations and discussions of the special session entitled “Perspectives on Multimedia Analytics” at MMM 2016, which was held in Miami, Florida on January 6, 2016. The special session consisted of four brief paper presentations, followed by a panel discussion with questions from the audience. The session was organized by Björn Þór Jónsson and Cathal Gurrin, and chaired and moderated by Klaus Schoeffmann. The goal of this report is to record the conclusions of the special session, in the hope that it may serve members of our community who are interested in Multimedia Analytics.}, address = {New York, NY, USA}, language = {EN}, publisher = {ACM} } @Article{timmerer2015_computer, author = {Timmerer, Christian and Ebrahimi, Touradj and Pereira, Fernando}, journal = {IEEE Computer}, title = {Toward a New Assessment of Quality}, year = {2015}, issn = {0018-9162}, month = {mar}, number = {3}, pages = {108-110}, volume = {48}, abstract = {A convergence of trends is shifting the focus of quality assessment from compliance with system design goals to fulfillment of user needs or expectations in different contexts.}, address = {Los Alamitos, CA, USA}, keywords = {Quality of Experience, Quality of Sensory Experience, Quality of Life}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/07063175.pdf}, publisher = {IEEE Computer Society} } @Article{martina_for_HH, author = {Sterca, Adrian and Hellwagner, Hermann and Boian, Florian and Vancea, Alexandru}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, title = {Media-friendly and TCP-friendly Rate Control Protocols for Multimedia Streaming}, year = {2015}, month = {aug}, number = {1}, pages = {15}, volume = {1}, abstract = {This paper describes a design framework for TCPfriendly and media-friendly rate control algorithms for multimedia streaming applications. The idea of this framework is to start from TFRC’s (TCP-Friendly Rate Control) transmission rate and then alter this transmission rate so that it tracks the media characteristics of the stream (e.g., bitrate) or other application characteristics like the client buffer fill level. In this way, the media-friendly property of the algorithm is achieved. We give three rules that guide how the TFRC throughput should track the evolution of the stream’s media characteristics and remain TCPfriendly in the long term. We also present, as proof of concept, four simple media-friendly and TCP-friendly congestion control algorithms built using the aforementioned framework. These congestion control algorithms are better suited for multimedia streaming applications than traditional TCP congestion control or smooth congestion control algorithms like TFRC. We have performed evaluations of two of the four proposed media-friendly and TCP-friendly congestion control algorithms under various network conditions and validated that they represent viable transport solutions, better than TFRC, for variable bitrate video streams. More specifically, our two media-friendly and TCPfriendly congestion control algorithms maintained a TCP-friendly throughput in the long term in all experiments and avoided an empty buffer at the client side in situations when TFRC could not achieve this.}, address = {USA}, doi = {10.1109/TCSVT.2015.2469075}, keywords = {TCP-friendly congestion control, media-friendly, multimedia streaming, Bandwidth, Multimedia communication}, language = {EN}, publisher = {IEEE}, url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=7206573&sortType%3Dasc_p_Sequence%26filter%3DAND%28p_Publication_Number%3A76%29%26rowsPerPage%3D100} } @Article{Zaharieva_IEEEMM2015, author = {Zaharieva, Maia and Del Fabro, Manfred and Zeppelzauer, Matthias}, journal = {IEEE MultiMedia}, title = {Cross-Platform Social Event Detection}, year = {2015}, month = {jun}, number = {99}, pages = {1--15}, volume = {PP}, address = {New York, NY, USA}, language = {EN}, publisher = {IEEE} } @Article{Timmerer2015_ELetterNov, author = {Timmerer, Christian and Weinberger, Daniel and Smole, Martin and Grandl, Reinhard and Mueller, Christopher and Lederer, Stefan}, journal = {IEEE Multimedia Communications Technical Committee E-Letter}, title = {Cloud-based Transcoding and Adaptive Video Streaming-as-a-Service}, year = {2015}, month = {nov}, pages = {7--11}, address = {New York, NY, USA}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/MMTC_bitcodin+bitdash.pdf}, publisher = {IEEE Communications Society [online]} } @Article{Timmerer2015_ELetter, author = {Timmerer, Christian and Maiero, Matteo and Rainer, Benjamin and Petscharnig, Stefan and Weinberger, Daniel and Mueller, Christopher and Lederer, Stefan}, journal = {IEEE Multimedia Communications Technical Committee E-Letter}, title = {Quality of Experience of Adaptive HTTP Streaming in Real-World Environments}, year = {2015}, month = {may}, pages = {6-9}, address = {New York, NY, USA}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/QoE-DASH.pdf}, publisher = {IEEE Communications Society [online]}, talktype = {registered} } @Article{Rainer2015_MNA, author = {Rass, Stefan and Rainer, Benjamin and Vavti, Matthias and Göllner, Johannes and Peer, Andreas and Schauer, Stefan}, journal = {Mobile Networks and Applications}, title = {Secure Communication over Software-Defined Networks}, year = {2015}, month = {jan}, pages = {105--110}, address = {Springer US}, language = {EN}, publisher = {Springer}, talktype = {none} } @Article{Pohl2015b, author = {Pohl, Daniela and Bouchachia, Abdelhamid and Hellwagner, Hermann}, journal = {Neurocomputing}, title = {Online Indexing and Clustering of Social Media Data for Emergency Management}, year = {2015}, month = {jan}, pages = {168-179}, abstract = {Social media becomes a vital part in our daily communication practice, creating a huge amount of data and covering different real-world situations. Currently, there is a tendency in making use of social media during emergency management and response. Most of this effort is performed by a huge number of volunteers browsing through social media data and preparing maps that can be used by professional first responders. Automatic analysis approaches are needed to directly support the response teams in monitoring and also understanding the evolution of facts in social media during an emergency situation. In this paper, we investigate the problem of real-time sub-events identification in social media data (i.e., Twitter, Flickr and YouTube) during emergencies. A processing framework is presented serving to generate situational reports/summaries from social media data. This framework relies in particular on online indexing and online clustering of media data streams. Online indexing aims at tracking the relevant vocabulary to capture the evolution of sub-events over time. Online clustering, on the other hand, is used to detect and update the set of sub-events using the indices built during online indexing. To evaluate the framework, social media data related to Hurricane Sandy 2012 was collected and used in a series of experiments. In particular some online indexing methods have been tested against a proposed method to show their suitability. Moreover, the quality of online clustering has been studied using standard clustering indices. Overall the framework provides a great opportunity for supporting emergency responders as demonstrated in real-world emergency exercises.}, address = {Amsterdam, Netherlands}, doi = {10.1016/j.neucom.2015.01.084}, language = {EN}, publisher = {Elsevier} } @Article{timmerer2014_jsac, author = {Timmerer, Christian and Griwodz, Carsten and Begen, Ali Cengiz and Stockhammer, Thomas and Girod, Bernd}, journal = {IEEE Journal on Selected Areas in Communications}, title = {Guest Editorial: Adaptive Media Streaming}, year = {2014}, month = {apr}, number = {4}, pages = {681-683}, volume = {32}, address = {New York, NY, USA}, keywords = {Adaptive Media Streaming, DASH}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/06774588.pdf}, publisher = {IEEE Communications Society} } @Article{timmerer2014_computer, author = {Timmerer, Christian and Rainer, Benjamin}, journal = {IEEE Computer}, title = {The Social Multimedia Experience}, year = {2014}, issn = {0018-9162}, month = {mar}, number = {3}, pages = {67-69}, volume = {47}, abstract = {Inter-destination multimedia synchronization and quality of experience are critical to the success of social TV, which integrates television viewing with social networking.}, address = {Los Alamitos, CA, USA}, keywords = {Quality of Experience, Inter-Destination Media Synchronization, Social TV, DASH, IDMS, QoE}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/timmerer-sme-mar13.pdf}, publisher = {IEEE Computer Society} } @Article{Timmerer2014_MPEGColumnMar, author = {Timmerer, Christian}, journal = {ACM SIGMultimedia Records}, title = {MPEG Column: 107th MPEG Meeting}, year = {2014}, issn = {1947-4598}, month = {mar}, number = {1}, pages = {1-2}, volume = {6}, address = {New York, NY, USA}, language = {EN}, publisher = {ACM}, url = {http://records.sigmm.ndlab.net/2014/02/mpeg-column-107th-mpeg-meeting/} } @Article{Timmerer2014_MMC, author = {Timmerer, Christian and Waltl, Markus and Rainer, Benjamin and Lederer, Stefan and Hellwagner, Hermann}, journal = {IEEE Multimedia Communications Technical Committee E-Letter}, title = {Enhancing 3D Video to enable a Fully Immersive Sensory Experiences}, year = {2014}, month = {jan}, number = {1}, pages = {23-26}, volume = {9}, address = {New York, NY, USA}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/E-Letter-Jan2014.pdf}, publisher = {IEEE Communications Society [online]}, url = {http://committees.comsoc.org/mmc/e-news/E-Letter-Jan2014.pdf} } @Article{SchoeffmannTMM2014, title = {3-D Interfaces to Improve the Performance of Visual Known-Item Search}, author = {Schoeffmann, Klaus and Ahlstrom, David and Hudelist, Marco Andrea}, journal = {Multimedia, IEEE Transactions on}, year = {2014}, month = {dec}, number = {7}, pages = {10}, volume = {16}, address = {Los Alamitos, CA, USA}, doi = {10.1109/TMM.2014.2333666}, issn = {1520-9210}, keywords = {Browsers;Image color analysis;Layout;Navigation;Smart phones;Three-dimensional displays;Visualization}, language = {EN}, publisher = {IEEE} } @Article{SchoeffmannMTAP2014, title = {Keyframe extraction in endoscopic video}, author = {Schoeffmann, Klaus and Del Fabro, Manfred and Szkaliczki, Tibor and Böszörmenyi, Laszlo and Keckstein, Jörg}, journal = {Multimedia Tools and Applications}, year = {2014}, month = {aug}, pages = {1-20}, address = {New York}, doi = {10.1007/s11042-014-2224-7}, issn = {1380-7501}, keywords = {Keyframe extraction; Video segmentation; Endoscopy; Medical imaging}, language = {English}, publisher = {Springer US}, url = {http://dx.doi.org/10.1007/s11042-014-2224-7} } @Article{SchoeffmannIEEEMM2014, author = {Schoeffmann, Klaus}, journal = {IEEE MultiMedia}, title = {A User-Centric Media Retrieval Competition: The Video Browser Showdown 2012-2014}, year = {2014}, month = {dec}, number = {4}, pages = {8-13}, volume = {21}, address = {Los Alamitos, CA, USA}, language = {EN}, publisher = {IEEE} } @Article{Rainer2014_AUTI, author = {Rainer, Benjamin and Timmerer, Christian}, journal = {ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)}, title = {A Generic Utility Model Representing the Quality of Sensory Experience}, year = {2014}, month = {oct}, pages = {14:1--14:17}, address = {New York, NY, USA}, booktitle = {ACM Trans. Multimedia Comput. Commun. Appl.}, editor = {Steinmetz, Ralf and Ghinea, Gheorghita and Timmerer, Christian and Lin, Weisi and Gulliver, Stephen and Zha, Zheng-Jun and Zhang, Lei and M\"{u}hlh\"{a}user, Max and Smeaton, Alan}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/TOMCCAP-SE-Model.pdf}, publisher = {ACM}, talktype = {none} } @Article{Pohl2014b, author = {Pohl, Daniela}, journal = {E-Letter on Social Media Analysis for Crisis Management}, title = {Social Media Analysis for Crisis Management: A Brief Survey}, year = {2014}, month = {mar}, number = {1}, pages = {1-10}, volume = {2}, address = {http://stcsn.ieee.net/e-letter/vol-2-no-1}, language = {EN}, publisher = {IEEE Computer Society Special Technical Community on Social Networking (STCSN)}, url = {http://stcsn.ieee.net/e-letter/vol-2-no-1/social-media-analysis-for-crisis-management-a-brief-survey} } @Article{Pohl2014a, author = {Pohl, Daniela and Bouchachia,Abdelhamid and Hellwagner, Hermann}, journal = {E-Letter on Social Media Analysis for Crisis Management}, title = {Crisis-related Sub-Event Detection Based on Clustering}, year = {2014}, month = {mar}, note = {IEEE Computer Society Special Technical Community on Social Networking E-Letter}, number = {1}, pages = {1-10}, volume = {2}, address = {http://stcsn.ieee.net/e-letter/vol-2-no-1}, howpublished = {http://stcsn.ieee.net/e-letter/vol-2-no-1/crisis-related-sub-event-detection-based-on-clustering}, language = {EN}, publisher = {IEEE Computer Society Special Technical Community on Social Networking (STCSN)}, url = {http://stcsn.ieee.net/e-letter/vol-2-no-1/crisis-related-sub-event-detection-based-on-clustering} } @Article{HudelistIJSC2014, author = {Hudelist, Marco Andrea and Schoeffmann, Klaus and Ahlström, David}, journal = {International Journal of Semantic Computing}, title = {Evaluating Alternatives to the 2D Grid Interface for Mobile Image Browsing}, year = {2014}, month = {sep}, pages = {25}, address = {Singapore}, doi = {10.1142/S1793351X14400042}, language = {EN}, publisher = {World Scientific}, url = {http://www.worldscientific.com/doi/abs/10.1142/S1793351X14400042?src=recsys&journalCode=ijsc} } @Article{Hossfeld2014_Computer, author = {Ho{\ss}feld, Tobias and Keimel, Christian and Timmerer, Christian}, journal = {Computer}, title = {Crowdsourcing Quality-of-Experience Assessments}, year = {2014}, month = {sep}, number = {9}, pages = {98--102}, volume = {47}, abstract = {Crowdsourced quality-of-experience (QoE) assessments are more cost-effective and flexible than traditional in-lab evaluations but require careful test design, innovative incentive mechanisms, and technical expertise to address various implementation challenges.}, address = {Los Alamitos, CA, USA}, doi = {10.1109/MC.2014.245}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/mco2014090098.pdf}, publisher = {IEEE Computer Society} } @Article{Hellwagner2014c, author = {Lederer, Stefan and Mueller, Christopher and Timmerer, Christian and Hellwagner, Hermann}, journal = {IEEE Network}, title = {Adaptive Multimedia Streaming in Information-Centric Networks}, year = {2014}, month = {nov}, number = {6}, pages = {91-96}, volume = {28}, abstract = {ICN has received a lot of attention in recent years, and is a promising approach for the Future Internet design. As multimedia is the dominating traffic in today's and (most likely) the Future Internet, it is important to consider this type of data transmission in the context of ICN. In particular, the adaptive streaming of multimedia content is a promising approach for usage within ICN, as the client has full control over the streaming session and has the possibility to adapt the multimedia stream to its context (e.g. network conditions, device capabilities), which is compatible with the paradigms adopted by ICN. In this article we investigate the implementation of adaptive multimedia streaming within networks adopting the ICN approach. In particular, we present our approach based on the recently ratified ISO/IEC MPEG standard Dynamic Adaptive Streaming over HTTP and the ICN representative Content-Centric Networking, including baseline evaluations and open research challenges.}, address = {IEEE Communications Society}, language = {EN}, publisher = {IEEE} } @Article{Hellwagner2014b, author = {Andre, Torsten and Hummel, Karin Anna and Schoellig, Angela and Yanmaz, Evsen and Asadpour, Mahdi and Bettstetter, Christian and Grippa, Pasquale and Hellwagner, Hermann and Sand, Stephan and Zhang, Siwei}, journal = {IEEE Communications Magazine}, title = {Application-Driven Design of Aerial Communication Networks}, year = {2014}, month = {may}, number = {5}, pages = {129-137}, volume = {52}, abstract = {Networks of micro aerial vehicles (MAVs) equipped with various sensors are increasingly used for civil applications, such as monitoring, surveillance, and disaster management. In this article, we discuss the communication requirements raised by applications in MAV networks. We propose a novel system representation that can be used to specify different application demands. To this end, we extract key functionalities expected in an MAV network. We map these functionalities into building blocks to characterize the expected communication needs. Based on insights from our own and related real-world experiments, we discuss the capabilities of existing communications technologies and their limitations to implement the proposed building blocks. Our findings indicate that while certain requirements of MAV applications are met with available technologies, further research and development is needed to address the scalability, heterogeneity, safety, quality of service, and security aspects of multi-MAV systems.}, address = {IEEE Communications Society}, language = {EN}, publisher = {IEEE} } @Article{Hellwagner2014a, author = {Hellwagner, Hermann}, journal = {E-Letter on Social Media Analysis for Crisis Management}, title = {The BRIDGE Project - Bridging Resources and Agencies in Large-Scale Emergency Management}, year = {2014}, month = {mar}, note = {IEEE Computer Society Special Technical Community on Social Networking E-Letter}, number = {1}, pages = {1-10}, volume = {2}, abstract = {BRIDGE is a European collaborative project established within the Security Research sector of the European Commission. The basic goal of BRIDGE is to contribute to the safety of citizens by developing technical and organisational solutions that improve crisis and emergency management in EU member states. A (middleware) platform is being developed that is to provide technical support for multi-agency collaboration in large-scale emergency relief efforts. Several tools and software systems are being implemented and tested to support first responders in their efforts. Beyond technical considerations, organisational measures are being explored to ensure interoperability and cooperation among involved parties; social, ethical and legal issues are being investigated as well. A focus of the project is to demonstrate and validate its results in the course of real-world emergency response exercises. Since most of the BRIDGE work is beyond the scope of this e-letter on social networking, only a brief overview of the BRIDGE goals and work will be given. However, one thread of work is relevant in the context of social networking and deserves to be covered more closely: automatic detection of notable sub-events of a crisis from social networks. This activity makes use of crisis-related information coming from citizens via social networks and thus contributes to building an improved operational picture in a crisis situation and to better planning and performing crisis response tasks.}, address = {http://stcsn.ieee.net/e-letter/vol-2-no-1}, howpublished = {http://stcsn.ieee.net/e-letter/vol-2-no-1/the-bridge-project}, language = {EN}, publisher = {IEEE Computer Society Special Technical Community on Social Networking (STCSN)}, url = {http://stcsn.ieee.net/e-letter/vol-2-no-1/the-bridge-project} } @Article{Ghinea2014_Tutorial, author = {Ghinea, Gheorghita and Timmerer, Christian and Lin, Weisi and Gulliver, Stephen}, journal = {ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)}, title = {Mulsemedia: State of the Art, Perspectives, and Challenges}, year = {2014}, issn = {1551-6857}, month = {sep}, number = {1s}, pages = {17:1--17:23}, volume = {11}, abstract = {Mulsemedia—multiple sensorial media—captures a wide variety of research efforts and applications. This article presents a historic perspective on mulsemedia work and reviews current developments in the area. These take place across the traditional multimedia spectrum—from virtual reality applications to computer games—as well as efforts in the arts, gastronomy, and therapy, to mention a few. We also describe standardization efforts, via the MPEG-V standard, and identify future developments and exciting challenges the community needs to overcome.}, address = {New York, NY, USA}, keywords = {Mulsemedia, contour perception, flow visualization, multisensory, perceptual theory, visual cortex, visualization}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/a17-ghinea.pdf}, publisher = {ACM} } @Article{Ghinea2014_Intro, author = {Ghinea, Gheorghita and Timmerer, Christian and Lin, Weisi and Gulliver, Stephen}, journal = {ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)}, title = {Guest Editorial: Special Issue on Multiple Sensorial (MulSeMedia) Multimodal Media: Advances and Applications}, year = {2014}, issn = {1551-6857}, month = {sep}, number = {1s}, pages = {9:1--9:2}, volume = {11}, address = {New York, NY, USA}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/a9-ghinea.pdf}, publisher = {ACM} } @Article{raey, author = {Stegmaier, Florian and Kosch, Harald and Klamma, Ralf and Lux, Mathias and Damiani, Ernesto}, journal = {Multimedia Tools and Applications}, title = {Multimedia on the web - editorial}, year = {2013}, issn = {1380-7501}, month = {jan}, pages = {1-6}, address = {New York, USA}, doi = {10.1007/s11042-013-1729-9}, language = {English}, publisher = {Springer US}, url = {http://dx.doi.org/10.1007/s11042-013-1729-9} } @Article{lux2013visual, author = {Lux, Mathias and Marques, Oge}, journal = {Synthesis Lectures on Information Concepts, Retrieval, and Services}, title = {Visual Information Retrieval Using Java and LIRE}, year = {2013}, month = {jan}, number = {1}, pages = {1-112 pp.}, volume = {5}, abstract = {Visual information retrieval (VIR) is an active and vibrant research area, which attempts at providing means for organizing, indexing, annotating, and retrieving visual information (images and videos) from large, unstructured repositories. The goal of VIR is to retrieve matches ranked by their relevance to a given query, which is often expressed as an example image and/or a series of keywords. During its early years (1995-2000), the research efforts were dominated by content-based approaches contributed primarily by the image and video processing community. During the past decade, it was widely recognized that the challenges imposed by the lack of coincidence between an image's visual contents and its semantic interpretation, also known as semantic gap, required a clever use of textual metadata (in addition to information extracted from the image's pixel contents) to make image and video retrieval solutions efficient and effective. The need to bridge (or at least narrow) the semantic gap has been one of the driving forces behind current VIR research. Additionally, other related research problems and market opportunities have started to emerge, offering a broad range of exciting problems for computer scientists and engineers to work on. In this introductory book, we focus on a subset of VIR problems where the media consists of images, and the indexing and retrieval methods are based on the pixel contents of those images -- an approach known as content-based image retrieval (CBIR). We present an implementation-oriented overview of CBIR concepts, techniques, algorithms, and figures of merit. Most chapters are supported by examples written in Java, using Lucene (an open-source Java-based indexing and search implementation) and LIRE (Lucene Image REtrieval), an open-source Java-based library for CBIR.}, address = {USA}, doi = {10.2200/S00468ED1V01Y201301ICR025}, language = {EN}, publisher = {Morgan \& Claypool Publishers} } @Article{delfabro_mmsj2013, author = {Del Fabro, Manfred and Böszörmenyi, Laszlo}, journal = {Multimedia Systems}, title = {State-of-the-art and future challenges in video scene detection: a survey}, year = {2013}, issn = {0942-4962}, month = {feb}, number = {5}, pages = {427-454}, volume = {19}, address = {Berlin, Heidelberg, New York}, language = {EN}, publisher = {Springer-Verlag} } @Article{Waltl2012_MPEGVSI, author = {Waltl, Markus and Rainer, Benjamin and Timmerer, Christian and Hellwagner, Hermann}, journal = {Signal Processing: Image Communication}, title = {An End-to-End tool chain for sensory experience based on MPEG-V}, year = {2013}, month = {feb}, number = {2}, pages = {136--150}, volume = {28}, abstract = {This paper provides an overview of our research conducted in the area of Sensory Experience including our implementations using MPEG-V Part 3 entitled ”Sensory Information”. MPEG-V Part 3 introduces Sensory Experience as a tool to increase the Quality of Experience by annotating traditional multimedia data with sensory effects. These sensory effects are rendered on special devices like fans, vibration chairs, ambient lights, scent disposers, water sprayers, or heating/cooling devices stimulating senses beyond the traditional ones. The paper's main focus is on the end-to-end aspects including the generation, transmission, and synchronized rendering of sensory effects with the traditional multimedia data taking movie clips as an example. Therefore, we present in this paper an open source tool chain that provides a complete end-to-end sensory effect generation and consumption framework. Furthermore, we summarize results from various subjective quality assessments conducted in this area. Finally, we point out research challenges that may encourage further research within this emerging domain.}, address = {Amsterdam, Netherlands}, doi = {10.1016/j.image.2012.10.009}, keywords = {Quality of Experience; Sensory Experience; Subjective Quality Assessment; Experimental Results; MPEG-V; Annotation Tool; Simulation Tool; Web Browser Plug-in; Sensory Information}, language = {EN}, publisher = {Elsevier}, url = {http://dx.doi.org/10.1016/j.image.2012.10.009} } @Article{Timmerer2013_MPEGColumnSep, author = {Timmerer, Christian}, journal = {ACM SIGMultimedia Records}, title = {MPEG Column: 105th MPEG Meeting}, year = {2013}, issn = {1947-4598}, month = {sep}, number = {3}, pages = {1-2}, volume = {5}, address = {New York, NY, USA}, language = {EN}, publisher = {ACM}, url = {http://records.sigmm.ndlab.net/2013/08/mpeg-column-105th-mpeg-meeting/} } @Article{Timmerer2013_MPEGColumnMar, author = {Timmerer, Christian}, journal = {ACM SIGMultimedia Records}, title = {MPEG column: 103rd MPEG meeting}, year = {2013}, issn = {1947-4598}, month = {mar}, number = {1}, pages = {1-3}, volume = {5}, address = {New York, NY, USA}, language = {EN}, publisher = {ACM}, url = {http://records.sigmm.ndlab.net/2013/01/mpeg-column-103rd-mpeg-meeting/} } @Article{Timmerer2013_MPEGColumnDec, author = {Timmerer, Christian}, journal = {ACM SIGMultimedia Records}, title = {MPEG Column: 106th MPEG Meeting}, year = {2013}, issn = {1947-4598}, month = {dec}, number = {4}, pages = {1-2}, volume = {5}, address = {New York, NY, USA}, language = {EN}, publisher = {ACM}, url = {http://records.sigmm.ndlab.net/2014/01/mpeg-column-106th-mpeg-meeting/} } @Article{Timmerer2013_CN, author = {Timmerer, Christian and Vetro, Anthony}, journal = {Computing Now}, title = {Recent MPEG Standards for Future Media Ecosystems}, year = {2013}, month = {oct}, number = {10}, pages = {1}, volume = {6}, address = {Los Alamitos, CA, USA}, language = {EN}, publisher = {IEEE Computer Society [online]}, url = {http://www.computer.org/portal/web/computingnow/archive/october2013} } @Article{Szkaliczki2013, author = {Szkaliczki, Tibor and Eberhard, Michael and Hellwagner, Hermann and Szobonya, László}, journal = {Discrete Applied Mathematics}, title = {Piece selection algorithms for layered video streaming in P2P networks}, year = {2013}, month = {nov}, pages = {11}, address = {Amsterdam, The Netherlands}, language = {EN}, publisher = {Elsevier}, url = {http://dx.doi.org/10.1016/j.dam.2013.11.007} } @Article{SchoeffmannIJMIR2013, author = {Schoeffmann, Klaus and Ahlström, David and Bailer, Werner and Cobarzan, Claudiu and Hopfgartner, Frank and McGuinness, Kevin and Gurrin, Cathal and Frisson, Christian and Le, Duy-Dinh and Del Fabro, Manfred and Bai, Hongliang and Weiss, Wolfgang}, journal = {International Journal of Multimedia Information Retrieval}, title = {The Video Browser Showdown: a live evaluation of interactive video search tools}, year = {2013}, month = {dec}, pages = {1-15}, address = {Berlin, Germany}, language = {EN}, publisher = {Springer} } @Article{Pohl2013d, author = {Pohl, Daniela and Bouchachia, Abdelhamid and Hellwagner, Hermann}, journal = {Multimedia Tools and Applications}, title = {Social Media for Crisis Management: Clustering Approaches for Sub-Event Detection}, year = {2013}, month = {dec}, pages = {1-32}, address = {Springer, NY, US}, language = {EN}, publisher = {Springer US} } @Article{Pohl2013b, author = {Pohl, Daniela and Bouchachia, Abdelhamid and Hellwagner, Hermann}, journal = {International Journal of Information Systems for Crisis Response and Management (IJISCRAM)}, title = {Supporting Crisis Management via Detection of Sub-Events in Social Networks}, year = {2013}, month = {jul}, number = {3}, pages = {20-36}, volume = {5}, address = {Hershey, PA, USA}, language = {EN}, publisher = {IGI Global} } @Article{Mueller2013_MMC, author = {Mueller, Christopher and Lederer, Stefan and Timmerer, Christian}, journal = {IEEE Multimedia Communications Technical Committee E-Letter}, title = {Fair Share Dynamic Adaptive Streaming over HTTP}, year = {2013}, month = {mar}, number = {2}, pages = {30-33}, volume = {8}, abstract = {Multimedia delivery over the Hypertext Transfer Protocol (HTTP) is currently very popular and with MPEGs' Dynamic Adaptive Streaming over HTTP (DASH) a standard is available to provide interoperability and enable large-scale deployments using existing infrastructures (servers, proxies, caches, etc.). This paper identifies some issue when multiple DASH clients compete for a bandwidth bottleneck when transparent proxy caches are deployed. Therefore, we propose a fair share adaptation scheme to be included within the client which – through experimental results – achieve a more efficient utilization of the bottleneck bandwidth and less quality switches.}, address = {New York, NY, USA}, keywords = {Dynamic Adaptive Streaming over HTTP, DASH, Fair Adaptation, Proxy Cache, Multimedia}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/E-Letter-March13.pdf}, publisher = {IEEE Communications Society [online]}, url = {http://committees.comsoc.org/mmc/e-news/E-Letter-March13.pdf} } @Article{Lux_Aljosa_2013, author = {Lux, Mathias}, journal = {ACM SIGMultimedia Records}, title = {An Interview with Aljosa Smolic}, year = {2013}, issn = {1947-4598}, month = sep, number = {3}, pages = {4-5}, volume = {5}, abstract = {Dr. Aljosa Smolic joined Disney Research Zürich, Switzerland in 2009, as Senior Research Scientist and Head of the "Advanced Video Technology" group. Before he was Scientific Project Manager at the Fraunhofer Institute for Telecommunications, Heinrich- Hertz-Institut (HHI), Berlin, also heading a research group. He has been involved in several national and international research projects, where he conducted research in various fields of video processing, video coding, computer vision and computer graphics and published more than 100 refereed papers in these fields. In current projects he is responsible for research in 2D video, 3D video and free viewpoint video processing and coding.}, address = {New York, USA}, doi = {10.1145/2552972.2552981}, language = {EN}, publisher = {ACM}, url = {http://doi.acm.org/10.1145/2552972.2552981} } @Article{Lederer2013_MMC, author = {Lederer, Stefan and Mueller, Christopher and Grandl, Reinhard and Timmerer, Christian}, journal = {IEEE Multimedia Communications Technical Committee E-Letter}, title = {Adaptive Multimedia Streaming over Information-Centric Networks in Mobile Networks using Multiple Mobile Links}, year = {2013}, month = {nov}, number = {6}, pages = {38-41}, volume = {8}, address = {New York, NY, USA}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/E-Letter-Nov2013.pdf}, publisher = {IEEE Communications Society [online]}, url = {http://committees.comsoc.org/mmc/e-news/E-Letter-Nov2013.pdf} } @Article{Kud2013_SPIC, author = {Kudumakis, Panos and Sandler, Mark and Anadiotis, Angelos-Christos G and Venieris, Iakovos S and Difino, Angelo and Wang, Xin and Tropea, Giuseppe and Grafl, Michael and Rodríguez-Doncel, Víctor and Llorente, Silvia and Delgado, Jaime}, journal = {Signal Processing: Image Communication}, title = {MPEG-M: A Digital Media Ecosystem for Interoperable Applications}, year = {2013}, issn = {09235965}, month = {dec}, pages = {24}, abstract = {MPEG-M is a suite of ISO/IEC standards (ISO/IEC 23006) that has been developed under the auspices of Moving Picture Experts Group (MPEG). MPEG-M, also known as Multimedia Service Platform Technologies (MSPT), facilitates a collection of multimedia middleware APIs and elementary services as well as service aggregation so that service providers can offer users a plethora of innovative services by extending current IPTV technology toward the seamless integration of personal content creation and distribution, e-commerce, social networks and Internet distribution of digital media.}, address = {Amsterdam, Netherlands}, doi = {10.1016/j.image.2013.10.006}, language = {EN}, publisher = {Elsevier}, url = {http://dx.doi.org/10.1016/j.image.2013.10.006} } @Article{Grafl2013_ComCom, author = {Grafl, Michael and Timmerer, Christian and Hellwagner, Hermann and Cherif, Wael and Ksentini, Adlen}, journal = {Computer Communications}, title = {Hybrid Scalable Video Coding for {HTTP}-based Adaptive Media Streaming with High-Definition Content}, year = {2013}, issn = {01403664}, month = {dec}, pages = {11}, 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 establish encoding recommendations and 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.}, address = {Amsterdam, Netherlands}, language = {EN}, publisher = {Elsevier} } @Article{Grafl2012_MM, author = {Grafl, Michael and Timmerer, Christian and Hellwagner, Hermann and Xilouris, George and Gardikis, Georgios and Renzi, Daniele and Battista, Stefano and Borcoci, Eugen and Negru, Daniel}, journal = {IEEE MultiMedia}, title = {Scalable Media Coding enabling Content-Aware Networking}, year = {2013}, issn = {1070-986X}, month = {apr}, number = {2}, pages = {30-41}, volume = {20}, abstract = {Given that multimedia services are becoming increasingly popular, they are expected to play a dominant role for the Future Internet. In this context, it is essential that Content-Aware Networking (CAN) architectures, as envisaged in the frame of the Future Internet, explicitly address the efficient delivery and processing of multimedia content. This article proposes adopting a content-aware approach into the network infrastructure, thus making it capable of identifying, processing, and manipulating (i.e., adapting, caching, etc.) media streams and objects in real time towards Quality of Service/Experience (QoS/QoE) maximization. Our proposal is built upon the exploitation of scalable media coding technologies within such a content-aware networking environment and is discussed based on four representative use cases for media delivery (unicast, multicast, peer-to-peer, and adaptive HTTP streaming) and with respect to a selection of CAN challenges, specifically flow processing, caching/buffering, and QoS/QoE management.}, address = {Los Alamitos, CA, USA}, doi = {http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.57}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/SMC_enabling_CAN.pdf}, publisher = {IEEE Computer Society} } @Article{chatzichristofis2012image, author = {Chatzichristofis, Sawas and Marques, Oge and Lux, Mathias and Boutalis, Yiannis}, journal = {Cellular Automata}, title = {Image Encryption Using the Recursive Attributes of the eXclusive-OR Filter on Cellular Automata}, year = {2012}, month = {jan}, pages = {340-350}, abstract = {A novel visual multimedia content encryption method based on cellular automata (CA) is presented in this paper. The proposed algorithm is based on an attribute of the eXclusive-OR (XOR) logic gate, according to which, its application to a square-sized CA has the ability to reconstruct the original content of a CA after a preset number of iterations. The resulted encrypted image is a lossless representation of the original/plaintext image, i.e. there is no loss of either resolution or contrast. Experimental results indicate that the encrypted image does not contain any statistical information able to reveal the original image.}, address = {Berlin, Heidelberg}, doi = {10.1007/978-3-642-33350-7_35}, isbn10 = {978-3-642-33349-1}, isbn13 = {978-3-642-33350-7}, language = {EN}, publisher = {Springer}, subtitle = {10th International Conference on Cellular Automata for Research and Industry, ACRI 2012, Santorini Island, Greece, September 24-27, 2012. Proceedings} } @Article{Waltl2012_MTAP, author = {Waltl, Markus and Timmerer, Christian and Rainer, Benjamin and Hellwagner, Hermann}, journal = {Multimedia Tools and Applications}, title = {Sensory Effects for Ambient Experiences in the World Wide Web}, year = {2012}, month = {may}, number = {-}, pages = {1--20}, volume = {-}, abstract = {More and more content in various formats becomes available via the WorldWideWeb (WWW). Currently availableWeb browsers are able to access and interpret these contents (i.e., Web videos, text, image, and audio). These contents stimulate only senses like audition 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 to enhance the ambient experience by providing effects such as light, wind, vibration, etc. The effects are represented as Sensory Effect Metadata (SEM) description which is associated to multimedia content and is rendered on devices like fans, vibration chairs, or lamps. In this paper we present two subjective quality assessments which comprise sensory effects, such as light, in the area of the WWW and their results achieved. The first assessment evaluates the influence of light effects on the Quality of Experience (QoE). The second assessment measures the impact of different settings for the color calculation on the viewing experience. Furthermore, we describe a Web browser plug-in for Mozilla Firefox which is able to render such sensory effects that are provided via the WWW.}, address = {Berlin, Heidelberg, New York}, doi = {10.1007/s11042-012-1099-8}, keywords = {World Wide Web, MPEG-V, Subjective quality assessment, Sensory effects, Quality of multimedia experience}, language = {EN}, publisher = {Springer Verlag}, url = {http://dx.doi.org/10.1007/s11042-012-1099-8} } @Article{Timmerer2012_MPEGColumnSep, author = {Timmerer, Christian}, journal = {ACM SIGMultimedia Records}, title = {MPEG column: 101st MPEG meeting}, year = {2012}, issn = {1947-4598}, month = {sep}, number = {3}, pages = {9-11}, volume = {4}, address = {New York, NY, USA}, language = {EN}, publisher = {ACM}, url = {http://records.sigmm.ndlab.net/2012/11/mpeg-column-101st-mpeg-meeting/} } @Article{Timmerer2012_MPEGColumnJun, author = {Timmerer, Christian}, journal = {ACM SIGMultimedia Records}, title = {MPEG column: 100th MPEG meeting}, year = {2012}, issn = {1947-4598}, month = {jun}, number = {2}, pages = {2-3}, volume = {4}, address = {New York, NY, USA}, language = {EN}, publisher = {ACM}, url = {http://records.sigmm.ndlab.net/2012/06/mpeg-column-100th-mpeg-meeting/} } @Article{Timmerer2012_MPEGColumnDec, author = {Timmerer, Christian}, journal = {ACM SIGMultimedia Records}, title = {MPEG column: 102nd MPEG meeting}, year = {2012}, issn = {1947-4598}, month = {dec}, number = {4}, pages = {1-2}, volume = {4}, address = {New York, NY, CUSA}, language = {EN}, publisher = {ACM}, url = {http://records.sigmm.ndlab.net/2012/12/mpeg-column-102nd-mpeg-meeting/} } @Article{Timmerer2012909, author = {Timmerer, Christian and Waltl, Markus and Rainer, Benjamin and Hellwagner, Hermann}, journal = {Signal Processing: Image Communication}, title = {Assessing the quality of sensory experience for multimedia presentations}, year = {2012}, month = {sep}, number = {8}, pages = {909--916}, volume = {27}, abstract = {This paper introduces the concept of sensory experience by utilizing sensory effects such as wind or lighting as another dimension which contributes to the quality of the user experience. In particular, we utilize a representation format for sensory effects that are attached to traditional multimedia resources such as audio, video, and image contents. Sensory effects (e.g., wind, lighting, explosion, heat, cold) are rendered on special devices (e.g., fans, ambient lights, motion chair, air condition) in synchronization with the traditional multimedia resources and shall stimulate other senses than audition and vision (e.g., mechanoreception, equilibrioception, thermoreception), with the intention to increase the users Quality of Experience (QoE). In particular, the paper provides a comprehensive introduction into the concept of sensory experience, its assessment in terms of the QoE, and related standardization and implementation efforts. Finally, we will highlight open issues and research challenges including future work.}, address = {Amsterdam, Netherlands}, doi = {10.1016/j.image.2012.01.016}, keywords = {Quality of Experience, Sensory experience, Subjective quality assessment, Experimental results, MPEG-V}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1-s2.0-S0923596512000252-main.pdf}, publisher = {Elsevier}, url = {http://dx.doi.org/10.1016/j.image.2012.01.016} } @Article{SchoeffmannSIGMMR2012, author = {Schoeffmann, Klaus and Bailer,Werner}, journal = {ACM SIGMultimedia Records}, title = {Video Browser Showdown}, year = {2012}, month = {jun}, number = {2}, pages = {2}, volume = {4}, address = {N/A}, language = {EN}, publisher = {ACM} } @Article{SchoeffmannIJMDEM12, author = {Schoeffmann, Klaus and Ahlström, David}, journal = {International Journal of Multimedia Data Engineering and Management}, title = {An Evaluation of Color Sorting for Image Browsing}, year = {2012}, month = {mar}, number = {1}, pages = {49-62}, volume = {3}, address = {701 E. Chocolate Ave., Hershey, PA 17033, USA}, language = {EN}, publisher = {IGI Publishing} } @Article{Milojicic2012, author = {Milojicic, Dejan and Arlitt, Martin and Seligmann, Doree Duncan and Thiruvathukal, George and Timmerer, Christian}, journal = {Computer}, title = {Innovation Mashups: Academic Rigor Meets Social Networking Buzz}, year = {2012}, issn = {0018-9162}, month = {sep}, number = {9}, pages = {101-105}, volume = {45}, abstract = {Exploring new options for publishing and content delivery offers an enormous opportunity to improve the state of the art and further modernize academic and professional publications.}, address = {Los Alamitos, CA, USA}, doi = {http://doi.ieeecomputersociety.org/10.1109/MC.2012.313}, keywords = {STCs, IEEE Computer Society, mashups, Computing Now}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/mco2012090101.pdf}, publisher = {IEEE Computer Society} } @Article{Hossfeld2012, author = {Ho{\ss}feld, Tobias and Schatz, Raimund and Varela, Martin and Timmerer, Christian}, journal = {Communications Magazine, IEEE}, title = {Challenges of QoE Management for Cloud Applications}, year = {2012}, month = {apr}, number = {4}, pages = {28-36}, volume = {50}, abstract = {Cloud computing is currently gaining enormous momentum due to a number of promised benefits: ease of use in terms of deployment, administration, and maintenance, along with high scalability and flexibility to create new services. However, as more personal and business applications migrate to the cloud, service quality will become an important differentiator between providers. In particular, quality of experience as perceived by users has the potential to become the guiding paradigm for managing quality in the cloud. In this article, we discuss technical challenges emerging from shifting services to the cloud, as well as how this shift impacts QoE and QoE management. Thereby, a particular focus is on multimedia cloud applications. Together with a novel QoE-based classification scheme of cloud applications, these challenges drive the research agenda on QoE management for cloud applications.}, address = {New York, NY, USA}, doi = {10.1109/MCOM.2012.6178831}, keywords = {cloud computing, multimedia computing, software quality, QoE management, QoE-based classification scheme, multimedia cloud applications, quality management, quality of experience, service quality, Cloud computing, Multimedia communication, Quality of service, Streaming media}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/06178831.pdf}, publisher = {IEEE Communications Society} } @Article{Tusch2011, author = {Tusch, Roland and Mariacher, Thomas and Pletzer, Felix and Böszörmenyi, Laszlo and Rinner, Bernhard and Harrer, Manfred}, journal = {ASFINAG R\&D Series Issue No. 4}, title = {LOOK2 PROJECT STUDY - How multimedia data contributes to improving the accuracy of traffic news.}, year = {2011}, month = {jul}, pages = {38-41}, address = {Rotenturmstraße 5-9, Vienna}, language = {EN}, publisher = {ASFINAG – The Innovative Motorway Operator} } @Article{Hellwagner2011a, author = {Hellwagner, Hermann and Hofbauer, Heinz and Kuschnig, Robert and Stütz, Thomas and Uhl, Andreas}, journal = {Journal on Signal Processing: Image Communication}, title = {Secure transport and adaptation of MC-EZBC video utilizing H.264-based transport protocols}, year = {2011}, issn = {0923-5965}, month = {nov}, pages = {30}, abstract = {Universal Multimedia Access (UMA) calls for solutions where content is created once and subsequently adapted to given requirements. With regard to UMA and scalability, which is required often due to a wide variety of end clients, the best suited codecs are wavelet based (like the MC-EZBC) due to their inherent high number of scaling options. However, most transport technologies for delivering videos to end clients are targeted toward the H.264/AVC standard or, if scalability is required, the H.264/SVC. In this paper we will introduce a mapping of the MC-EZBC bitstream to existing H.264/SVC based streaming and scaling protocols. This enables the use of highly scalable wavelet based codecs on the one hand and the utilization of already existing network technologies without accruing high implementation costs on the other hand. Furthermore, we will evaluate different scaling options in order to choose the best option for given requirements. Additionally, we will evaluate different encryption options based on transport and bitstream encryption for use cases where digital rights management is required.}, address = {Amsterdam, Netherlands}, doi = {10.1016/j.image.2011.11.002}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Elsevier_SPIC_Hellwagner11a.pdf}, publisher = {Elsevier B.V.} } @Article{Eberhard2011a, author = {Eberhard, Michael and Kumar, Amit and Mignanti, Silvano and Petrocco, Riccardo and Uitto, Mikko}, journal = {International Journal on Advances in Internet Technology}, title = {A Framework for Distributing Scalable Content over Peer-to-Peer Networks}, year = {2011}, month = {sep}, number = {1\&2}, pages = {1-13}, volume = {4}, 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 network is a very actual research topic. This paper presents a framework 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. Additionally, an evaluation of the system’s performance in different scenarios is provided. The test series in the evaluation section assess the performance of our layered piece-picking core and provide a comparison of the performance of our system’s multi layer and single layer implementations. The presented system is to our knowledge the first open-source Peer-to-Peer network with full Scalable Video Coding support.}, address = {N/A}, keywords = {Peer-to-Peer; Scalable Video Coding; Packetizing; Error Concealment; Performance Evaluation}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/svc_framework_iaria.pdf}, publisher = {IARIA} } @Article{Boszormenyi2011, author = {Böszörmenyi, Laszlo and del Fabro, Manfred and Kogler, Marian and Lux, Mathias and Marques, Oge and Sobe, Anita}, journal = {Multimedia Tools and Applications}, title = {Innovative directions in self-organized distributed multimedia systems}, year = {2011}, issn = {1380-7501}, month = {jan}, note = {10.1007/s11042-010-0622-z}, pages = {525-553}, volume = {51}, abstract = {The way by which multimedia contents are produced, delivered across networks, and consumed by intended users have shifted significantly during the past 10 years. In this paper we postulate that, in the near future, flexible and self-organizing facilities will play a dominating role in distributed multimedia systems. We discuss how such systems can be designed, using a three-layer (sensor, distribution, and user layer) architecture, SOMA (Self Organizing Multimedia Architecture), as an example. We also present innovative directions in three main aspects of self-organized multimedia systems: (i) the self-organizing aspects of multimedia user communities, e.g., the wisdom, intentions, and needs of users; (ii) a fresh look at video streams that treat them as a collection of units that can be composed taking user and network aspects into account; and (iii) new delivery paradigms and how self-organization and multimedia delivery can be combined.}, address = {Berlin, Heidelberg, New York}, doi = {10.1007/s11042-010-0622-z}, language = {EN}, publisher = {Springer Verlag} } @Article{Timmerer2010_MXM_IEEEMM, author = {Timmerer, Christian and Chiariglione, Filippo and Preda, Marius and Doncel, Victor Rodriguez}, journal = {IEEE Multimedia}, title = {Accelerating Media Business Developments with the MPEG Extensible Middleware}, year = {2010}, issn = {1070-986X}, month = {sep}, number = {3}, pages = {74--78}, volume = {17}, abstract = {Editor’s Note: Media applications are becoming increasingly complex. They handle many data formats, run across multiple platforms, and support a wide range of functions. This article describes a standardized set of protocols and APIs that provides efficient access to individual system components, enables rapid deployment of new applications, and improves portability. —Anthony Vetro}, address = {Los Alamitos, CA, USA}, doi = {10.1109/MMUL.2010.52}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/mmu2010030074.pdf}, publisher = {IEEE}, url = {http://doi.ieeecomputersociety.org/10.1109/MMUL.2010.52} } @Article{Timmerer2010_DeliveryContextDescriptionFormats, author = {Timmerer, Christian and Jaborning, Johannes and Hellwagner, Hermann}, journal = {Journal of Digital Information Management}, title = {A Survey on Delivery Context Description Formats - A Comparison and Mapping Model}, year = {2010}, month = {feb}, number = {1}, pages = {16-27}, volume = {8}, 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 small-sized 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, net- work 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).}, address = {Chennai, India}, keywords = {CC/PP, DCO, Delivery Context, Metadata, UAProf, UED}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/A Survey on Delivery Context Description Formats – A Comparison and Mapping Model.pdf}, publisher = {Digital Information Research Foundation} } @Article{Szkaliczki2010, author = {Szkaliczki, Tibor and Eberhard, Michael and Hellwagner, Hermann and Szobonya, László}, journal = {Electronic Notes in Discrete Mathematics}, title = {Piece Selection Algorithm for Layered Video Streaming in P2P Networks}, year = {2010}, issn = {1571-0653}, month = {aug}, note = {ISCO 2010 - International Symposium on Combinatorial Optimization}, pages = {1265-1272}, volume = {36}, abstract = {This paper introduces the piece selection problem that arises when streaming layered video content over peer-to-peer networks. The piece selection algorithm decides periodically which pieces to request from other peers (network nodes) for download. The main goal of the piece selection algorithm is to provide the best possible quality for the available bandwidth. Our recommended solution approaches are related to the typical problems and solutions in the knapsack problem.}, address = {New York, USA}, doi = {10.1016/j.endm.2010.05.160}, keywords = {streaming, layered video, knapsack problem}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/ISCO'10_Eberhard.pdf}, publisher = {Elsevier Inc.}, url = {http://www.sciencedirect.com/science/article/B75GV-50JJF7F-5P/2/7d978923400f50d4c42165003c64c351} } @Article{Sobe2010, author = {Sobe, Anita and Böszörmenyi, Laszlo and Taschwer, Mario}, journal = {International Journal on Advances in Software}, title = {{Video Notation (ViNo): A Formalism for Describing and Evaluating Non-sequential Multimedia Access}}, year = {2010}, issn = {1942-2628}, month = {sep}, number = {1 \& 2}, pages = {19-30}, volume = {3}, abstract = {The contributions of this paper are threefold: (1) the extensive introduction of a formal Video Notation (ViNo) that allows for describing different multimedia transport techniques for specifying required QoS; (2) the application of this formal notation to analyzing different transport mechanisms without the need of detailed simulations; (3) further application of ViNo to caching techniques, leading to the introduction of two cache admission policies and one replacement policy supporting nonsequential multimedia access. The applicability of ViNo is shown by example and by analysis of an existing CDN simulation. We find that a pure LRU replacement yields significantly lower hit rates than our suggested popularity-based replacement. The evaluation of caches was done by simulation and by usage of ViNo.}, address = {Valencia, Spain}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Intl_Journal_Advances_Software_2010_Vol3.pdf}, publisher = {International Academy, Research and Industry Association (IARIA)}, url = {http://www.iariajournals.org} } @Article{SchoeffmannBrowsingReview, author = {Schoeffmann, Klaus and Hopfgartner, Frank and Marques, Oge and Böszörmenyi, Laszlo and Jose, Joemon}, journal = {SPIE Reviews}, title = {Video browsing interfaces and applications: a review}, year = {2010}, month = {mar}, number = {1}, pages = {018004}, volume = {1}, address = {","}, doi = {10.1117/6.0000005}, language = {EN}, publisher = {SPIE}, talktype = {registered}, url = {http://link.aip.org/link/?SV2/1/018004/1} } @Article{Lux2010d, author = {Lux, Mathias and Pitman, Arthur and Marques, Oge}, journal = {Future Internet}, title = {Can Global Visual Features Improve Tag Recommendation for Image Annotation?}, year = {2010}, month = {jan}, pages = {341-362}, volume = {3}, abstract = {Recent advances in the fields of digital photography, networking and computing, have made it easier than ever for users to store and share photographs. However without sufficient metadata, e.g., in the form of tags, photos are difficult to find and organize. In this paper, we describe a system that recommends tags for image annotation. We postulate that the use of low-level global visual features can improve the quality of the tag recommendation process when compared to a baseline statistical method based on tag co-occurrence. We present results from experiments conducted using photos and metadata sourced from the Flickr photo website that suggest that the use of visual features improves the mean average precision (MAP) of the system and increases the system's ability to suggest different tags, therefore justifying the associated increase in complexity.}, address = {Basel, Switzerland}, doi = {10.3390/fi2030341}, keywords = {image retrieval; multimedia; metadata; folksonomies; tagging; image annotation; tag recommendation; visual information retrieval}, language = {EN}, publisher = {MDPI} } @Article{Lopez2010, author = {Lopez, Fernando and Jannach, Dietmar and Martínez, Jose Maria and Timmerer, Christian and García, Narciso and Hellwagner, Hermann}, journal = {Journal of Applied Intelligence}, title = {Bounded non-deterministic planning for multimedia adaptation}, year = {2010}, month = {jul}, pages = {32}, abstract = {This paper proposes a novel combination of arti- ficial intelligence planning and other techniques for improv- ing decision-making in the context of multi-step multime- dia content adaptation. In particular, it describes a method that allows decision-making (selecting the adaptation to perform) in situations where third-party pluggable multi- media conversion modules are involved and the multime- dia adaptation planner does not know their exact adapta- tion capabilities. In this approach, the multimedia adapta- tion planner module is only responsible for a part of the required decisions; the pluggable modules make additional decisions based on different criteria. We demonstrate that partial decision-making is not only attainable, but also in- troduces advantages with respect to a system in which these conversion modules are not capable of providing additional decisions. This means that transferring decisions from the multi-step multimedia adaptation planner to the pluggable conversion modules increases the flexibility of the adapta- tion. Moreover, by allowing conversion modules to be only partially described, the range of problems that these modules can address increases, while significantly decreasing both the description length of the adaptation capabilities and the planning decision time. Finally, we specify the conditions under which knowing the partial adaptation capabilities of a set of conversion modules will be enough to compute a proper adaptation plan.}, address = {Springer New York}, doi = {10.1007/s10489-010-0242-3}, keywords = {Bounded non-deterministic multimedia adaptation, Planning, Decision-making, MPEG-7, MPEG-21}, language = {EN}, publisher = {Springer}, url = {http://www.springerlink.com/content/751g123vp1574qt5/} } @Article{Lux2009a, author = {Lux, Mathias and Marques, Oge and Schoeffmann, Klaus and Böszörmenyi, Laszlo and Lajtai, Georg}, journal = {Multimedia Tools and Applications}, title = {A novel tool for summarization of arthroscopic videos}, year = {2009}, month = sep, pages = {521 - 544}, abstract = {Arthroscopic surgery is a minimally invasive procedure that uses a small camera to generate video streams, which are recorded and subsequently archived. In this paper we present a video summarization tool and demonstrate how it can be successfully used in the domain of arthroscopic videos. The proposed tool generates a keyframe-based summary, which clusters visually similar frames based on user-selected visual features and appropriate dissimilarity metrics. We discuss how this tool can be used for arthroscopic videos, taking advantage of several domain-specific aspects, without losing its ability to work on general-purpose videos. Experimental results confirm the feasibility of the proposed approach and encourage extending it to other application domains.}, address = {Berlin, Heidelberg, New York}, language = {EN}, publisher = {Springer}, url = {http://www.springerlink.com/content/u037362581245316/} } @Article{Kosch2009, author = {Kosch, Harald and Timmerer, Christian}, journal = {IEEE Computing Now}, title = {Multimedia Metadata and Semantic Management}, year = {2009}, month = dec, number = {December 2009}, pages = {00}, volume = {Multimedia Metadata and Semantic Management}, address = {Los Alamitos, CA, USA}, language = {EN}, publisher = {IEEE} } @Article{Karpati2009, author = {Karpati, Peter and Szkaliczki, Tibor and Böszörmenyi, Laszlo}, journal = {Multimedia Tools and Applications}, title = {Designing and scaling distributed VoD servers}, year = {2009}, issn = {1380-7501}, month = jan, pages = {55-91}, volume = {Volume 41, Number 1}, abstract = {Planning Video-on-Demand (VoD) services based on the server architecture and the available equipment is always a challenging task. We created a formal model to support the design of distributed video servers that adapt dynamically and automatically to the changing client demands, network and host parameters. The model makes giving estimations about the available throughput possible, and defines evaluation criteria for VoD services relating to utilization and load balance, video usage, client satisfaction and costs. The dynamism of the frame model originates from the possible state transitions which have to be defined in a core model. The core model is responsible for configuration recommendation which determines how clients are served depending on the properties of their requests, system configuration and system load. Furthermore, it decides on the optimal placement of the server components in the network. The usability of the model is illustrated on examples.}, address = {Berlin, Heidelberg, New York}, language = {EN}, publisher = {Springer}, url = {http://www.springerlink.com/content/1153860131r36v13/?p=c2702cc6a0b347749314ae5367dc47f0&pi=0} } @Article{Hellwagner2009, author = {Hellwagner, Hermann and Kuschnig, Robert and Stütz, Thomas and Uhl, Andreas}, journal = {Journal on Signal Processing: Image Communication}, title = {Efficient In-Network Adaptation of Encrypted {H.264/SVC} Content}, year = {2009}, month = {jul}, number = {9}, pages = {740-758}, volume = {24}, abstract = {This paper addresses the efficient adaptation of encrypted scalable video content (H.264/SVC). RTP-based in-network adaptation schemes on a media aware network element (MANE) in an IPTV and VoD scenario are considered. Two basic alternatives to implement encryption and adaptation of H.264/SVC content are investigated: (i) full, format-independent encryption making use of Secure RTP (SRTP); (ii) SVC-specific encryption that leaves the metadata relevant for adaptation (NAL unit headers) unencrypted. The SRTP-based scheme (i) is straightforward to deploy, but requires the MANE to be in the security context of the delivery, i.e., to be a trusted node. For adaptation, the content needs to be decrypted, scaled, and re-encrypted. The SVC-specific approach (ii) enables both full and selective encryption, e.g., of the base layer only. SVC-specific encryption is based on own previous work, which is substantially extended and detailed in this paper. The adaptation MANE can now be an untrusted node; adaptation becomes a low-complexity process, avoiding full decryption and re-encryption of the content. This paper presents the first experimental comparison of these two approaches and evaluates whether multimedia-specific encryption can lead to performance and application benefits. Potential security threats and security properties of the two approaches in the IPTV and VoD scenario are elementarily analyzed. In terms of runtime performance on the MANE our SVC-specific encryption scheme significantly outperforms the SRTP-based approach. SVC-specific encryption is also superior in terms of induced end-to-end delays. The performance can even be improved by selective application of the SVC-specific encryption scheme. The results indicate that efficient adaptation of SVC-encrypted content on low-end, untrusted network devices is feasible.}, address = {Amsterdam}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Elsevier_SPIC_Hellwagner09a.pdf}, publisher = {Elsevier B.V.} } @Article{Eberhard2009a, author = {Eberhard, Michael and Timmerer, Christian and Quacchio, Emanuele and Hellwagner, Hermann}, journal = {IEEE Wireless Communications}, title = {An Interoperable Delivery Framework for Scalable Media Resources}, year = {2009}, month = {oct}, number = {Vol. 16, No. 5}, pages = {58-63}, volume = {Oktober 2009}, abstract = {In this paper, an interoperable framework for the delivery of scalable media resources, e.g., in the standardized Scalable Video Coding (SVC) format, is presented. The framework provides support for Video on Demand (VoD) as well as multicast streaming and performs an efficient, generic, and interoperable adaptation of the streamed content based on MPEG-21 Digital Item Adaptation (DIA). The server as well as the clients of the streaming framework implement the MPEG Extensible Middleware (MXM) and utilize the MPEG Query Format (MPQF) for querying the available media resources. The framework has been fully integrated into the VLC media player. The architecture for both, VoD and multicast is presented in detail. Finally, a comparison in terms of performance of the generic MPEG-21 metadata-based adaptation approach to an SVC-specific adaptation approach is provided.}, address = {Los Alamitos, CA, USA}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/ieeewireless_eberhard.pdf}, publisher = {IEEE} } @Article{Tusch2008, author = {Tusch, Roland and Jakab, Michael and Köpke, Julius and Krätschmer, Armin and Kropfberger, Michael and Kuchler, Sigrid and Ofner, Michael and Hellwagner, Hermann and Böszörmenyi, Laszlo}, journal = {International Journal of Digital Multimedia Broadcasting}, title = {Context-Aware UPnP-AV Services for Adaptive Home Multimedia Systems}, year = {2008}, month = sep, pages = {12}, volume = {Vol. 2008}, abstract = {One possibility to provide mobile multimedia in domestic multimedia systems is the use of Universal Plug and Play Audio Visual (UPnP-AV) devices. In a standard UPnP-AV scenario, multimedia content provided by a Media Server device is streamed to Media Renderer devices by the initiation of a Control Point. However, there is no provisioning of context-aware multimedia content customization. This paper presents an enhancement of standard UPnP-AV services for home multimedia environments regarding context awareness. It comes up with context profile definitions, shows how this context information can be queried from the Media Renderers, and illustrates how a Control Point can use this information to tailor a media stream from the Media Server to one or more Media Renderers. Moreover, since a standard Control Point implementation only queries one Media Server at a time, there is no global view on the content of all Media Servers in the UPnP-AV network. This paper also presents an approach of multimedia content integration on the Media Server side that provides fast search for content on the network. Finally, a number of performance measurements show the overhead costs of our enhancements to UPnP-AV in order to achieve the benefits.}, address = {Cairo}, doi = {doi:10.1155/2008/835438}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Context-Aware UPnP-AV Services for Adaptive Home Multimedia Systems.pdf}, publisher = {Hindawi Publishing Corporation}, url = {http://www.hindawi.com/journals/ijdmb/volume-2008/} } @Article{Timmerer2008g, author = {Timmerer, Christian and Hellwagner, Hermann}, journal = {Informatik Spektrum}, title = {Das MPEG-21 Multimedia Framework}, year = {2008}, month = dec, number = {6}, pages = {576-579}, volume = {31}, address = {Berlin, Heidelberg, New York}, language = {DE}, publisher = {Springer} } @Article{Sobe2008, author = {Sobe, Anita and Böszörmenyi, Laszlo}, journal = {Reports of the Institute of Information Technology, Klagenfurt University, TR/ITEC/12/2.08, Tech. Rep}, title = {Towards self-organizing multimedia delivery}, year = {2008}, month = {jan}, pages = {-}, volume = {-}, address = {Klagenfurt}, language = {EN}, publisher = {Alpen-Adria Universität Klagenfurt} } @Article{Sidibe2008, author = {Sidibe, Mamadou and Koumaras, Harilaos and Kofler, Ingo and Mehaoua, Ahmed and Kourtis, Anastasios and Timmerer, Christian}, journal = {Journal on Signal, Image and Video Processing}, title = {A novel monitoring architecture for media services adaptation based on network QoS to perceived QoS mapping}, year = {2008}, month = dec, number = {4}, pages = {307-320}, volume = {2}, abstract = {One of the future visions of multimedia networking is the provision of multimedia content at a variety of quality and price levels. Of the many approaches to this issue, one of the most predominant techniques is the concept of Perceived Quality of Service (PQoS), which extends the traditional engineering-based QoS concept to the perceptual satisfaction that the user receives from the reception of multimedia content. In this context, PQoS monitoring is becoming crucial to media service providers (SPs) for providing not only quantified PQoS-based services, but also service assurance based on multimedia content adaptation across heterogeneous networks. This work proposes a novel cross-layer monitoring architecture that utilizes a new Network QoS (NQoS) to PQoS mapping framework at the application level. The resulting QoS monitoring should allow the content delivery system to take sophisticated actions for real time media content adaptation, and aims to provide perceived service performance verification with respect to the QoS guarantees that have been specified in contractual agreements between providers and end-users. A subsequent performance evaluation of the proposed model conducted using a real test-bed environment demonstrates both the accuracy and feasibility of the network level measurements, the NQoS to PQoS mapping and the overall feasibility of the proposed end-to-end monitoring solution.}, address = {London, United Kingdom}, doi = {10.1007/s11760-008-0083-2}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/SIVP08_MonitoringArchitecture_Preprint.pdf}, publisher = {Springer} } @Article{Reiterer2008, author = {Reiterer, Bernhard and Concolato, Cyril and Lachner, Janine and Le Feuvre, Jean and Moissinac, Jean-Claude and Lenzi, Stefano and Chessa, Stefano and Ferrá, Enrique Fernández and Menaya, Juan José González and Hellwagner, Hermann}, journal = {The Visual Computer, International Journal of Computer Graphics}, title = {User-centric universal multimedia access in home networks}, year = {2008}, issn = {01782789}, month = jul, number = {7-9}, pages = {837-845}, volume = {24}, abstract = {Much research is currently being conducted towards Universal Multimedia Access, aiming at removing barriers that arise when multimedia content is to be consumed with more and more heterogeneous devices and over diverse networks. We argue that users should be put at the center of the research work to enable user-centric multimedia access. In this paper we present the requirements for a user-centric multimedia access system in a networked home environment. These requirements are easy access to available content repositories, context awareness, content adaptation and session migration. After showing the limits of state-of-the-art technologies, we present the architecture of a system which allows unified access to the home network content, automatically delivered to rendering devices close to the user, adapted according to the rendering device constraints, and which is also capable of session mobility.}, address = {Berlin, Heidelberg, New York}, doi = {10.1007/s00371-008-0265-5}, keywords = {Universal Multimedia Access · Multimedia adaptation · UPnP AV · Context awareness · Content sharing}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/User-centric universal multimedia access in home networks.pdf}, publisher = {Springer}, url = {http://http://www.springerlink.com/content/fpjj19237704788k/} } @Article{Mylonas2008, author = {Mylonas, Phivos and Hellwagner, Hermann and Castells, Pablo and Wallace, Manolis}, journal = {Signal, Image and Video Processing}, title = {Signal, image and video processing (SIVP) special issue on “multimedia semantics, adaptation and personalization” Editorial}, year = {2008}, issn = {1863-1711}, month = oct, number = {4}, pages = {287-288}, volume = {2/2008}, address = {Berlin, Heidelberg, New York}, language = {EN}, publisher = {Springer}, url = {http://www.springerlink.com/content/f672w10742502436/?p=d30247019a4d4df6a6c1ea2a5da5e38d&pi=0} } @Article{Kuschnig2008, author = {Kuschnig, Robert and Kofler, Ingo and Ransburg, Michael and Hellwagner, Hermann}, journal = {Journal of Visual Communication and Image Representation}, title = {Design options and comparison of in-network H.264/SVC adaptation}, year = {2008}, month = dec, number = {8}, pages = {529-542}, volume = {19}, abstract = {This paper explores design options and evaluates implementations of in-network, RTP/RTSP based adaptation MANEs (Media Aware Network Elements) for H.264/SVC content streaming. The obvious technique to be employed by such an adaptation MANE is to perform SVC specific bitstream extraction or truncation. Another mechanism that can be used is description (metadata) driven, coding format independent adaptation based on generic Bitstream Syntax Descriptions (gBSD), as specified within MPEG-21 Digital Item Adaptation (DIA). Adaptation MANE architectures for both approaches are developed and presented, implemented in end-to-end streaming/adaptation prototype systems, and experimentally evaluated and compared. For the gBSD based solution, open issues like the granularity of bitstream descriptions and of bitstream adaptation, metadata overhead, metadata packetization and transport options, and error resilience in case of metadata losses, are addressed. The experimental results indicate that a simple SVC specific adaptation MANE does clearly outperform the gBSD based adaptation variants. Yet, the conceptual advantages of the description driven approach, like coding format independence and flexibility, may outweigh the performance drawbacks in specific applications.}, address = {Amsterdam}, doi = {10.1016/j.jvcir.2008.07.004}, keywords = {Scalable video coding (H.264/SVC), In-network adaptation, RTP/RTSP MANE, MPEG-21 Digital Item Adaptation (DIA), Generic Bitstream Syntax Description (gBSD)}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/JVCIR08_In-network_H.264-AVC_Adaptation.pdf}, publisher = {Elsevier B.V.} } @Article{Kofler2008a, author = {Kofler, Ingo and Seidl, Joachim and Timmerer, Christian and Hellwagner, Hermann and Ahmed, Toufik}, journal = {Journal on Signal, Image and Video Processing}, title = {Using MPEG-21 for Cross-layer Multimedia Content Adaptation}, year = {2008}, month = dec, number = {4}, pages = {355-370}, volume = {2}, abstract = {This paper presents a cross-layer model—formulated using interoperable description formats—for the adaptation of scalable H.264/MPEG-4 AVC (i.e., SVC) content in a video streaming system operating on aWireless LANaccess network without QoS mechanisms.SVCcontent adaptation on the server takes place on the application layer using an adaptation process compliant with the MPEG-21 Digital Item Adaptation (DIA) standard, based on input comprised of MPEG-21 DIA descriptions of content and usage environment parameters. The latter descriptions integrate information from different layers, e.g., device characteristics and packet loss rate, in an attempt to increase the interoperability of this cross-layer model, thus making it applicable to other models. For the sake of deriving model parameters, performance measurements from two wireless access point models were taken in account. Throughout the investigation it emerged that the behavior of the system strongly depends on the access point. Therefore, we investigated the use of end-to-end-based rate control algorithms for steering the content adaptation. Simulations of rate adaptation algorithms were subsequently performed, leading to the conclusion that a TFRC-based adaptation technique (TCP-Friendly Rate Control) performs quite well in adapting to limited bandwidth and varying network conditions. In the paper we demonstrate howTFRC-based content adaptation can be realized using MPEG-21 tools.}, address = {London, United Kingdom}, doi = {10.1007/s11760-008-0088-x}, keywords = {Multimedia content adaptation · Cross-layer design · MPEG-21 Digital Item Adaptation · Rate control}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/SIVP08_CrossLayer_Preprint.pdf}, publisher = {Springer} } @Article{Boeszoermenyi2008c, author = {Böszörmenyi, Laszlo}, journal = {IEEE Annals of the History of Computing}, title = {History of Informatics}, year = {2008}, issn = {10586180}, month = sep, pages = {4-7}, address = {Los Alamitos, CA, USA}, language = {EN}, publisher = {IEEE}, url = {http://www.computer.org/portal/site/annals/index.jsp} } @Article{Rollett2007, author = {Rollett, Herwig and Lux, Mathias and Strohmaier, Markus and Dösinger, Gisela and Tochtermann, Klaus}, journal = {International Journal of Learning Technology (IJLT)}, title = {The Web 2.0 way of learning with technologies}, year = {2007}, issn = {1477-8386}, month = jan, pages = {87–107}, volume = {Vol. 3, No. 1}, abstract = {While there is a lot of hype around various concepts associated with the term Web 2.0 in industry, little academic research has so far been conducted on the implications of this new approach for the domain of education. Much of what goes by the name of Web 2.0 can, in fact, be regarded as new kinds of learning technologies, and can be utilised as such. This paper explains the background of Web 2.0, investigates the implications for knowledge transfer in general, and then discusses its particular use in eLearning contexts with the help of short scenarios. The main challenge in the future will be to maintain essential Web 2.0 attributes, such as trust, openness, voluntariness and self-organisation, when applying Web 2.0 tools in institutional contexts.}, address = {Geneva, Switzerland}, language = {EN}, publisher = {Inderscience Publishers}, url = {http://www.inderscience.com/browse/index.php?journalID=87} } @Article{Prangl2007a, author = {Prangl, Martin and Szkaliczki, Tibor and Hellwagner, Hermann}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, title = {A Framework for Utility-Based Multimedia Adaptation}, year = {2007}, issn = {1051-8215}, month = jun, number = {6}, pages = {719-728}, volume = {17/2007}, abstract = {Content adaptation is an important issue of multimedia frameworks in order to achieve universal multimedia access (UMA), i.e., to enable consumption of 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 targeting the UMA vision do not consider utility aspects in their adaptation decisions. This paper focuses on a generic semantic-based audio–visual utility model for DIA that aims to enhance the multimedia experience for the user. Our proposed model is able to take the semantics and the perceptual features of the content as well as the users' specific utility aspects into account. Based on a detailed analysis of these constraints, we will show how the model reacts on individual input data. For choosing the best adaptation decision considering resource limitations on client and server sides as well as network characteristics, we evaluate four algorithms for performing this adaptation decision taking task. We will discuss results according to some use case scenarios.}, address = {Los Alamitos, CA, USA}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/A Framework for Utility-Based Multimedia Adaptation.pdf}, publisher = {IEEE} } @Article{Lux2007c, author = {Lux, Mathias and Dösinger, Gisela}, journal = {International Journal of Knowledge and Learning}, title = {From folksonomies to ontologies: employing wisdom of the crowds to serve learning purposes}, year = {2007}, month = oct, number = {No. 4/5}, pages = {515-528}, volume = {Vol 3}, abstract = {Is Web 2.0 just hype or just a buzzword, which might disappear in the near future One way to find answers to these questions is to investigate the actual benefit of the Web 2.0 for real use cases. Within this contribution we study a very special aspect of the Web 2.0 the folksonomy and its use within self-directed learning. Guided by conceptual principles of emergent computing we point out methods, which might be able to let semantics emerge from folksonomies and discuss the effect of the results in self-directed learning.}, address = {NA}, doi = {10.1504/IJKL.2007.016709}, language = {EN}, publisher = {Inderscience Publishers}, url = {http://www.ingentaconnect.com/content/ind/ijkl/2008/00000003/F0020004/art00009} } @Article{Lux2007a, author = {Lux, Mathias}, journal = {ÖGAI Journal}, title = {Web 2.0: Die soziale Komponente im World Wide Web}, year = {2007}, issn = {0254-4326}, month = mar, pages = {14-18}, address = {Wien}, language = {DE}, publisher = {Österreichische Gesellschaft für Artificial Intelligence} } @Article{Jannach2007, author = {Jannach, Dietmar and Leopold, Klaus}, journal = {Journal of Network and Computer Applications}, title = {Knowledge-based Multimedia Adaptation for Ubiquitous Multimedia Consumption}, year = {2007}, month = aug, number = {Special issue on "Intelligence-based adaptation for ubiquitous multimedia communications"}, pages = {958-982}, volume = {Vol. 30 (3)}, abstract = {Intelligent, server-side adaptation of multimedia resources is becoming increasingly important and challenging for two reasons. First, the market continuously brings up new mobile end-user devices to which the content has to be adapted as these devices support different display formats and operate on various types of networks. On the other hand, with the help of metadata annotations which are now available in the MPEG-7 and MPEG-21 standard, advanced forms of resource adaptations on the content level become possible. As none of the existing multimedia transformation tools and libraries can support all these different forms of basic and advanced adaptation operations, an intelligent multimedia adaptation server has to integrate such external tools and algorithms and perform an adequate sequence of adaptation operations on the original resource before sending it to the client. In this paper we present the results of the ISO/IEC MPEG core experiment on using Semantic Web Services technology as a tool for declaratively describing the semantics of adaptation services and constructing multi-step adaptation sequences in an open and extensible multimedia adaptation framework. We show how the semantics of adaptation operations can be captured in the form of input, output, precondition, and effects, how the problem of finding adequate adaptation sequences can be viewed as an Artificial Intelligence planning problem, and finally, how the existing MPEG standards are technically integrated into the service descriptions and how they serve as the shared ontology of the domain. Our approach both introduces declarative, knowledge-based technology into the involved multimedia communities and on the other hand broadens the application scope of Semantic Web Service technology in the area of general semantic service descriptions and automated program construction.}, address = {NA}, language = {EN}, publisher = {NA}, url = {http://www.elsevier.com/wps/find/journaldescription.cws_home/622893/description#description} } @Article{Boeszoermenyi2007a, author = {Böszörmenyi, Laszlo and Hellwagner, Hermann and Schojer, Peter}, journal = {Multimedia Systems}, title = {Metadata-driven optimal transcoding in a multimedia proxy}, year = {2007}, month = jul, number = {Issue 1}, pages = {51-68}, volume = {Vol. 13}, 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 mainly in the decompressed domain. A cost model is presented which incorporates user requirements, terminal capabilities, and 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 YouGet (WYNIWYG) video services, which deliver videos to users in exactly the 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.}, address = {Berlin, Heidelberg, New York}, doi = {9780769530406}, keywords = {Video proxy · Video caching · Media gateway · Media adaptation · Metadata · MPEG-7 · MPEG-21 · Cache replacement}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Metadata-driven optimal transcoding in a multimedia proxy.pdf}, publisher = {Springer} } @Article{Tochtermann2006, author = {Tochtermann, Klaus and Lux, Mathias}, journal = {WISU - Das Wirtschaftsstudium}, title = {Suchen mithilfe semantischer Metadaten}, year = {2006}, issn = {0340-3084}, month = dec, pages = {1557 - 1563}, volume = {12/06}, abstract = {Daten zu Daten werden Metadaten genannt. Sie ermöglichen die effektive Organisation, Administration und Suche nach Daten aller Arten. Demgegenüber erlaufebn Ontologen die Formalisierung der Fakten und die detailgenaue Beschreibung von Domänenwissen. In vielen Anwendungsbereichen haben sich die klassischen Metadatenformate als zu einfach und Ontologien als zu komplex erwiesen, was zu neuen Formaten führte. Hier wird ein gemeinsames Modell für solche Formate vorgestellt, das sich zur Datensuche eignet.}, address = {NA}, language = {DE}, publisher = {NA}, url = {http://www.wisu.de} } @Article{Lux2006b, author = {Lux, Mathias and Klieber, Werner and Granitzer, Michael}, journal = {Journal of Universal Knowledge Management}, title = {On the Complexity of Annotation with the High Level Metadata}, year = {2006}, month = aug, number = {1}, pages = {54-58}, volume = {Vol1}, abstract = {High level metadata provides a way to manage, organize and retrieve multimedia data based on the actual content using content descriptions. The MPEG-7 Semantic Description Scheme provides tools for storing expressive and interpretable high level metadata. As it is currently impossible for computers to create high level metadata autonomously, users have to create the annotations manually. Generally the manual annotation of multimedia content is understood as laborious and complex task. Within this publication we assess the complexity of the annotation task for the MPEG-7 Semantic Description Scheme within a small user evaluation and the results of the evaluation are discussed.}, address = {Graz, Austria}, language = {EN}, publisher = {TU Graz \& Know Center}, url = {http://www.google.at/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&ved=0CBwQFjAA&url=http%3A%2F%2Fciteseerx.ist.psu.edu%2Fviewdoc%2Fdownload%3Fdoi%3D10.1.1.108.3864%26rep%3Drep1%26type%3Dpdf&ei=gYlZUJG-GsrftAbKxYHgAQ&usg=AFQjCNGyOPvZO8TUItZ8PcqiLxXprYgQwA&sig2=IBS-1ay5hqskcgp8L2PlHg&cad=rja} } @Article{Lux2006, author = {Lux, Mathias and Jarke, Matthias and Kosch, Harald}, journal = {Journal of Universal Knowledge Management}, title = {MPEG and Multimedia Metadata Community Workshop Results 2005}, year = {2006}, month = aug, number = {1}, pages = {1-3}, volume = {Vol.1}, abstract = {The year 2005 was a successful year for the MPEG and Multimedia Metadata Community. The community was founded within a first workshop in March 2005 in Klagenfurt, Austria, initiated and organized by Harald Kosch. A second workshop, which took place at the I-Know 05, the International Conference for Knowledge Management 2005 in Graz, Austria, was organized by Mathias Lux and Michael Granitzer to enlarge the community and to plan future joint activities. With a third workshop at the RWTH Aachen, Germany, organized by Marc Spaniol and Ralf Klamma, the community grew further, aims of the community were clarified and the schedule for 2006 was developed. Within the three workshops a lot of topics and projects have been discussed. The JUKM special issue on the MPEG and Multimedia Metadata Community Workshop Results 2005 aims to distribute results of community discussions and projects of the community members. The contributions to this issue have been presented by at least one of the authors at one of the above mentioned workshops. The discussion of the community has been integrated and a scientific paper has been generated. The publication has then been peer reviewed by community members. Two different types of contributions have been accepted. Technical notes are smaller in size, but present valuable partial results of ongoing research. Full papers provide more in depth discussion of applications and approaches as well as results and conclusions. From the various presentations of the three workshops in 2005 six topics have been selected for publication, whereas only the last contribution is not a full paper but a technical note.}, address = {Graz, Austria}, language = {EN}, publisher = {TU Graz \& Know Center}, url = {http://www.jucs.org/jukm_1_1/mpeg_and_multimedia_metadata/jukm_01_01_0001_0003_editorial.pdf} } @Article{KoflerVogt2006, author = {Kofler-Vogt, Andrea and Kosch, Harald and Heuer, Jörg}, journal = {EURASIP Journal on Applied Signal Processing}, title = {BeTrIS - an index system for MPEG-7 streams}, year = {2006}, issn = {1110-8657}, month = jan, pages = {1-11}, 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, especially mobile applications that deal with MPEG-7 suffer from limited bandwidth, low computational power and limited battery life. In this document we describe an index system that allows filter mechanisms and random access to encoded MPEG-7 streams and which overcome 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.}, address = {NA}, language = {EN}, publisher = {NA}, url = {http://www.hindawi.com/GetArticle.aspx?doi=10.1155/ASP/2006/15482} } @Article{Jannach2006, author = {Jannach, Dietmar and Leopold, Klaus and Timmerer, Christian and Hellwagner, Hermann}, journal = {Applied Intelligence - Special Issue: Innovations in Applied Artificial Intelligence}, title = {A Knowledge-Based Framework For Multimedia Adaptation}, year = {2006}, issn = {0924-669X}, month = apr, number = {No. 2}, pages = {109-125}, volume = {Vol. 24}, abstract = {Abstract Personalized delivery of multimedia content over the Internet opens new business perspectives for future multimedia applications and thus plays an important role in the ongoing MPEG-7 and MPEG-21 multimedia standardization efforts. Based on these standards, next-generation multimedia services will be able to automatically prepare the digital content before delivery according to the client’s device capabilities, the network conditions, or even the user’s content preferences. However, these services will have to deal with a variety of different end user devices, media formats, as well as with additional metadata when adapting the original media resources. In parallel, an increasing number of commercial or open-source media transformation tools will be available, capable of exploiting such descriptive metadata or dealing with new media formats; thus it is not realistic that a single tool will support all possible transformations. In this paper, we present a novel, fully knowledge-based approach for building such multimedia adaptation services, addressing the above mentioned issues of openness, extensibility, and concordance with existing and upcoming standards. In our approach, the original media is transformed in multiple adaptation steps performed by an extensible set of external tools, where the construction of adequate adaptation sequences is solved in an Artificial Intelligence planning process. The interoperability issue is addressed by exploiting standardized Semantic Web Services technology. This technology allows us to express tool capabilities and execution semantics in a declarative and well-defined form. In this context, existing multimedia standards serve as a shared domain ontology. The presented approach was implemented and successfully evaluated in an official ISO/IEC MPEG (Moving Picture Experts Group) Core Experiment and is currently under further evaluation by the standardization body.}, address = {Berlin, Heidelberg, New York}, language = {EN}, publisher = {Springer}, url = {http://www.springerlink.com/content/w745246635772v97/} } @Article{DeSutter2006a, author = {De Sutter, Robbie and Lerouge, Sam and De Neve, Peter and Timmerer, Christian and Hellwagner, Hermann and Van de Walle, Rik}, journal = {Multimedia Systems}, title = {Comparison of XML serializations: cost benefits versus complexity}, year = {2006}, month = oct, number = {Nr. 2}, pages = {101-115}, volume = {Vol. 12}, abstract = {More and more data are structured, stored, and sent over a networ using the Extensible Markup Language (XML) language. There are, however, concerns about the verbosity of XML in such a way that it may restrain further adoption of the language, especially when exchanging XML-based data over heterogeneous networks, and when it is used within constrained (mobile) devices. Therefore, alternative (binary) serialization formats of the XML data become relevant in order to reduce this overhead. However, using binary-encoded XML should not introduce interoperability issues with existing applications nor add additional complexity to new applications. On top of that, it should have a clear cost reduction over the current plain-text serialization format. A first technology is developed within the ISO/IEC Moving Picture Experts Group, namely the Binary MPEG Format for XML. It provides good compression efficiency, ability to (partially) update existingXMLtrees, and facilitates random access into, and manipulation of, the binary-encoded bit stream. Another technique is based on the Abstract Syntax Notation One specification with the Packed Encoding Rules created by the ITU-T. This paper evaluates both techniques as alternative XML serialization formats and introduces a solution for the interoperability concerns. This solution and the alternative serialization formats are validated against two real-life use cases in terms of processing speed and cost reduction. The efficiency of the alternative serialization formats are compared to a classic plain text compression technique, in particular ZIP compression.}, address = {Berlin, Heidelberg, New York}, doi = {10.1007/s00530-006-0044-y}, keywords = {XML serialization formats · MPEG-B · ASN.1 · Information encoding · Data interchange formats · Multimedia applications}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Comparison of XML serializations_cost benefits versus complexity.pdf}, publisher = {Springer} } @Article{DeSutter2006, author = {De Sutter, Robbie and Lerouge, Sam and De Neve, Peter and Timmerer, Christian and Hellwagner, Hermann and and Van de Walle, Rik}, journal = {ACM Multimedia Systems}, title = {Comparison of XML serializations: cost benefit vs. complexity}, year = {2006}, issn = {0942-4962}, month = aug, number = {No 1}, pages = {1-15}, volume = {Vol 12}, abstract = {More and more data are structured, stored, and sent over a networ using the Extensible Markup Language (XML) language. There are, however, concerns about the verbosity of XML in such a way that it may restrain further adoption of the language, especially when exchanging XML-based data over heterogeneous networks, and when it is used within constrained (mobile) devices. Therefore, alternative (binary) serialization formats of the XML data become relevant in order to reduce this overhead. However, using binary-encoded XML should not introduce interoperability issues with existing applications nor add additional complexity to new applications. On top of that, it should have a clear cost reduction over the current plain-text serialization format. A first technology is developed within the ISO/IEC Moving Picture Experts Group, namely the Binary MPEG Format for XML. It provides good compression efficiency, ability to (partially) update existingXMLtrees, and facilitates random access into, and manipulation of, the binary-encoded bit stream. Another technique is based on the Abstract Syntax Notation One specification with the Packed Encoding Rules created by the ITU-T. This paper evaluates both techniques as alternative XML serialization formats and introduces a solution for the interoperability concerns. This solution and the alternative serialization formats are validated against two real-life use cases in terms of processing speed and cost reduction. The efficiency of the alternative serialization formats are compared to a classic plain text compression technique, in particular ZIP compression.}, address = {London}, language = {EN}, publisher = {Springer} } @Article{Vetro2005, author = {Vetro, Anthony and Timmerer, Christian}, journal = {IEEE Transactions on Multimedia}, title = {Digital Item Adaptation: Overview of Standardization and Research Activities}, year = {2005}, issn = {1520-9210}, month = jun, pages = {418-426}, volume = {Special Issue on MPEG-21}, abstract = {MPEG-21 Digital Item Adaptation (DIA) has recently been finalized as part of the MPEG-21 Multimedia Framework. DIA specifies metadata for assisting the adaptation of Digital Items according to constraints on the storage, transmission and consumption, thereby enabling various types of quality of service management. This paper provides an overview of DIA, describes its use in multimedia applications, and reports on some of the ongoing activities in MPEG on extending DIA for use in rights governed environments.}, address = {Los Alamitos, CA, USA}, doi = {http://dx.doi.org/10.1109/TMM.2005.846795}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/01430717.pdf}, publisher = {IEEE} } @Article{Timmerer2005b, author = {Timmerer, Christian and Hellwagner, Hermann}, journal = {IEEE Multimedia Magazine}, title = {Interoperable Adaptive Multimedia Communication}, year = {2005}, month = jan, number = {1}, pages = {74-79}, volume = {12}, abstract = {Digital Item Adaptation (DIA) has been recently standardized as Part 7 of the MPEG-21 Multimedia Framework. This standard specifies tools enabling interoperable communication and adaptation of so-called Digital Items. The adaptation process becomes ever more difficult due to the heterogeneity of terminals and networks utilizing different types of multimedia contents encoded in various coding formats. Other aspects are the users� preferences and accessibility characteristics as well as the natural environment in which the content is consumed. This article describes how to use the tools within DIA in order to build a device and coding format independent adaptation module enabling interoperable multimedia communication.}, address = {Los Alamitos, USA}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Interoperable Adaptive Multimedia Communication.pdf}, publisher = {IEEE Computer Society} } @Article{Schojer2005, author = {Schojer, Peter and Böszörmenyi, Laszlo and Hellwagner, Hermann}, journal = {Scalable Computing: Practice and Experience}, title = {An Adaptive Standard Meta-data Aware Proxy Cache}, year = {2005}, month = jul, number = {No 2}, pages = {93-104}, volume = {Vol 6}, abstract = {Multimedia is gaining ever more importance on the Internet. This increases the need for intelligent and efficient video caches. 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 cache 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, the MPEG-7 standard to describe the scalability options for a video and the emerging MPEG-21 standard to describe the terminal capabilities. We 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. Key words: Adaptation, MPEG-4, MPEG-7, MPEG-21, adaptive proxy, caching.}, address = {Timisoara, Romania}, language = {EN}, publisher = {SCPE} } @Article{Libsie2005, author = {Libsie, Mulugeta and Kosch, Harald}, journal = {Journal of Digital Information Management}, title = {Content-Aware Segment-Based Video Adaptation}, year = {2005}, issn = {0972-7272}, month = jun, number = {Vol. 2}, pages = {88-94}, volume = {3}, abstract = {Video adaptation is an active research area aiming at delivering heterogeneous content to yet heterogeneous devices under different network conditions. It is an important component of multimedia data management to address the problem of delivering multimedia data in distributed heterogeneous environments. This paper presents a novel method of video adaptation called segment-based adaptation. It aims at applying different reduction methods on different segments based on physical content. The video is first partitioned into homogeneous segments based on physical characteristics. Then optimal reduction methods are selected and applied on each segment with the objective of minimizing quality loss and/or maximizing data size reduction during adaptation. In addition to this new method of variation creation, the commonly used reduction methods are also implemented. To realize variation creation, a unifying framework called the Variation Factory is developed. It is extended to the Multi-Step Variation Factory, which allows intermediary videos to serve as variations and also as sources to further variations. Our proposals are implemented as part of a server component, called the Variation Processing Unit (VaPU) that generates different versions of the source and an MPEG-7 metadata document.}, address = {Chennai, India}, language = {DE}, publisher = {Digital Information Research Foundation}, url = {http://www.dirf.org/jdim/v3i2.asp} } @Article{Kosch2005c, author = {Kosch, Harald and Döller, Mario}, journal = {Datenbank Spektrum}, title = {MPEG: Überblick und Integration in Multimedia-Datenbanken}, year = {2005}, month = nov, pages = {26-35}, volume = {Heft 15/5. Jahrgang}, abstract = {Unser Tutorial gibt einen Überblick über die neuesten MPEG-Standards MPEG-7/21/A/B und streicht ihre Bedeutung für Multimedia-Datenbanken heraus.}, address = {Heidelberg}, language = {DE}, publisher = {Springer} } @Article{Kosch2005a, author = {Kosch, Harald and Böszörmenyi, Laszlo and Döller, Mario and Libsie, Mulugeta and Kofer, Andrea and Schojer, Peter}, journal = {IEEE MultiMedia}, title = {The life-cycle of Multimedia Metadata}, year = {2005}, month = mar, number = {1}, pages = {80-86}, volume = {12}, abstract = {During its lifetime, multimedia content undergoes different stages or cycles fromproduction to consumption. Content is created, processed or modified in a postproduction stage, delivered to users, and finally, consumed. Metadata, or descriptive data about the multimedia content, pass through similar stages but with different time lines.1 Metadata may be produced, modified, and consumed by all actors involved in the content production-consumption chain. At each step of the chain, different kinds of metadata may be produced by highly different methods and of substantially different semantic value.}, address = {Washington}, language = {EN}, publisher = {IEEE} } @Article{Goldschmidt2005, author = {Goldschmidt, Balázs and Tusch, Roland and Böszörmenyi, Laszlo}, journal = {Scalable Computing: Practice and Experience}, title = {A CORBA-based Middleware for an Adaptive Streaming Server}, year = {2005}, month = jul, number = {No 2}, pages = {83-92}, volume = {Vol 6}, address = {Timisoara, Romania}, language = {EN}, publisher = {SCPE} } @Article{Devillers2005, author = {Devillers, Sylvain and Timmerer, Christian and Heuer, Jörg and Hellwagner, Hermann}, journal = {IEEE Transactions on Multimedia}, title = {Bitstream Syntax Description-Based Adaptation in Streaming and Constrained Environments}, year = {2005}, month = jun, number = {No. 3}, pages = {463-470}, volume = {Special Issue on MPEG-21, Vol. 7}, abstract = {The seamless access to rich multimedia content on any device and over an network, usually known as Universal Multimedia Access, requires interoperable description tools and adaptation techniques to be developed. To address the latter issue, MPEG-21 Digital Item Adaptation (DIA) introduces the Bitstream Syntax Description (BSD) framework, which provides tools for adapting multimedia content in a generic (i.e., coding format independent) way. The basic idea is to use the eXtensible Markup Language (XML) to describe the high-level structure of a binary media bitstream, to transform its description (e.g., by means of eXtensible Stylesheet Language Transformations, XSLT), and to construct the adapted media bitstream from the transformed description. This paper presents how this basic BSD framework, initially developed for non-streamed content and suffering from inherent limitations and high memory consumption of XML-related technologies such as XSLT, can be advanced and efficiently implemented in a streaming environment and on resource-constrained devices. Two different attempts to solve the inherent problems are described. The first approach proposes an architecture based on the streamed processing of SAX (Simple Application Programming Interface for XML) events and adopts STX (Streaming Transformations for XML) as an alternative to XSLT, whereas the second approach breaks a BSD up into well-formed fragments called Process Units (PUs) that can be processed individually by a standard XSLT processor. The current status of our work as well as directions for future research are given.}, address = {Piscataway, USA}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Bitstream Syntax Description-based Adaptation in Streaming and Constrained Environments.pdf}, publisher = {IEEE} } @Article{Tusch2004, author = {Tusch, Roland and Böszörmenyi, Laszlo and Goldschmidt, Balázs and Hellwagner, Hermann and Schojer, Peter}, journal = {Computer Science and Information Systems}, title = {Offensive and Defensive Adaptation in Distributed Multimedia Systems}, year = {2004}, month = {jan}, number = {No 1}, pages = {49-77}, volume = {Vol. 1}, abstract = {Adaptation in multimedia systems 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. 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.}, address = {Novi Sad}, language = {EN}, publisher = {ComSIS} } @Article{Kosch2004, author = {Kosch, Harald and Moustefaoui, Ahmed and Böszörmenyi, Laszlo and Brunie, Lionel}, journal = {Multimedia Tools and Applications}, title = {Heuristics for Optimizing Multi-clip Queries in Video Databases}, year = {2004}, month = mar, number = {3}, pages = {235-262}, volume = {22}, abstract = {A multi-clip query requests multiple video clips. In this paper we address the multi-clip query optimization problem. We propose a new heuristics called Restricted Search Interval that maximizes clip sharing between queries and consequently reduces the workload of the video server. An adaptation of our heuristics for optimizing the response time of the query is presented as well. The experimental results show that the suggested heuristics reduces the server workload by about 68% in comparison to a classical heuristic approach.}, address = {Heidelberg, Germany}, language = {EN}, publisher = {Springer} } @Article{Podlipnig2003, author = {Podlipnig, Stefan and Böszörmenyi, Laszlo}, journal = {ACM Computing Surveys (CSUR)}, title = {A survey of Web cache replacement strategies}, year = {2003}, issn = {0360-0300}, month = dec, pages = {374 - 398}, volume = {Volume 35 , Issue 4}, abstract = {Web caching is an important technique to scale the Internet. One important performance factor of Web caches is the replacement strategy. Due to specific characteristics of the World Wide Web, there exist a huge number of proposals for cache replacement. This article proposes a classification for these proposals that subsumes prior classifications. Using this classification, different proposals and their advantages and disadvantages are described. Furthermore, the article discusses the importance of cache replacement strategies in modern proxy caches and outlines potential future research topics.}, address = {New York, USA}, language = {EN}, publisher = {ACM} } @Article{Panis2003, author = {Panis, Gabriel and Hutter, Andreas and Heuer, Jörg and Hellwagner, Hermann and Kosch, Harald and Timmerer, Christian and Devillers, Sylvain and Amielh, Myriam}, journal = {Signal Processing: Image Communication}, title = {Bitstream Syntax Description: A Tool for Multimedia Resource Adaptation within MPEG-21}, year = {2003}, month = {jan}, number = {8}, pages = {721-747}, volume = {Vol. 18, Special Issue on Multimedia Adaptation}, abstract = {In this paper, a generic method is described to allow the adaptation of different multimedia resources by a single, media resource-agnostic processor. This method is based on an XML description of the media resource’s bitstream syntax, which can be transformed to reflect the desired adaptation and then be used to generate an adapted version of the bitstream. Based on this concept, two complementary technologies, BSDL and gBS Schema, are presented. The two technologies provide solutions for parsing a bitstream to generate its XML description, for the generic structuring of this description, and the generation of an adapted bitstream using its transformed description. The two technologies can be used as stand-alone tools; however, a joint approach has been developed in order to harmonise the two solutions and exploit their strengths. Since BSDL has been presented in previous publications, this paper is focusing more on the gBS Schema and the joint BSDL/gBS Schema approach.}, address = {Amsterdam, Netherlands}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/Bitstream syntax description.pdf}, publisher = {Elsevier B.V.} } @Article{Kosch2003, author = {Kosch, Harald and Heuer, Jörg}, journal = {Informatik Spektrum}, title = {MPEG-7 Aktuelles Schlagwort}, year = {2003}, issn = {0170-6012}, month = apr, number = {2}, pages = {164}, volume = {26}, abstract = {Die Moving Picture Experts Group, eine Arbeitsgruppe der ISO SC29, ist seit 1988 aktiv und hat mit ihren MPEG-1/2/4 einen entscheidenden Einfluss auf die Multimedia-Industrie genommen.Mit der Verabschiedung MPEG-7 wurde von der Moving Picture Experts Group (MPEG) im März 2002 als Internationaler Standard verabschiedet. Nach der erfolgreichen Einführung der Standards MPEG-1/2/4 zur audiovisuellen Kodierung von Inhalten ist MPEG-7 ein Standard, der ein Austauschformat für Beschreibungen von multimedialen Inhalten festlegt.}, address = {Heidelberg}, language = {DE}, publisher = {Springer}, url = {http://www.ifi.uni-klu.ac.at/ITEC/Publications/showabs?pnr=2003-0194-HKAJ} } @Article{Boeszoermenyi2003e, author = {Böszörmenyi, Laszlo and Kosch, Harald and Hellwagner, Hermann}, journal = {Parallel Processing Letters}, title = {Best papers of EuroPar 2003}, year = {2003}, issn = {0129-6264}, month = dec, number = {4}, pages = {509-511}, volume = {13}, address = {Heidelberg, Germany}, language = {EN}, publisher = {Springer} } @Article{Boeszoermenyi2003d, author = {Böszörmenyi, Laszlo and Hellwagner, Hermann and Kosch, Harald and Libsie, Mulugeta and Podlipnig, Stefan}, journal = {Signal Processing - Image Communication - Special Issue on Multimedia Adaptation}, title = {Metadata Driven Adaptation in the ADMITS Project}, year = {2003}, issn = {0923-5965}, month = sep, number = {Issue 8}, pages = {749-766}, volume = {Vol. 18}, abstract = {The ADMITS project (Adaptation in Distributed Multimedia IT Systems) is building an experimental distributed multimedia system for investigations into adaptation, which we consider is an increasingly important tool for multimedia systems. A number of possible adaptation entities (server, proxy, clients, routers) are being explored, different algorithms for media, component and application-level adaptations are being implemented and evaluated, and experimental data are being derived to gain insight into when, where and how to adapt, and how individual, distributed adaptation steps interoperate and interact with each other. In this paper the "adaptation-chain" of (MPEG-conforming) metadata based adaptation is described: from the creation stage at the server side, through its usage in the network (actually in a proxy), up to the consumption at the client. The metadata are used to steer the adaptation processes. MPEG-conformant metadata, the so-called variation descriptions, are introduced; an example of a complete MPEG-7 document describing temporal scaling of an MPEG-4 video is given. The meta-database designed to store the metadata is briefly discussed. We describe how the metadata can be extracted from MPEG-4 visual elementary streams and initial results from the temporal video scaling experiment are given. We further present how the metadata can be utilized by enhanced cache replacement algorithms in a proxy server in order to realize quality-based caching; experimental results using these algorithms are also given. Finally, an adaptive query and presentation interface to the meta-.}, address = {Oxford, United Kingdom}, language = {EN}, publisher = {Elsevier}, url = {http://www.sciencedirect.com/science?_ob=PublicationURL&_tockey=%23TOC%235640%232003%23999819991%234} } @Article{Kosch2002c, author = {Kosch, Harald and Moustefaoui, A and Brunie, Lionel}, journal = {Multimedia Tools and Applications}, title = {Semantic based Prefetching in News-on-Demand Video Server}, year = {2002}, month = nov, pages = {159-179}, volume = {Vol 18}, abstract = {The Multimedia Description Standard MPEG-7 is an International Standard since February 2002. It defines a huge set of description classes for multimedia content, for its creation and its communication. This article investigates what MPEG-7 means to Multimedia Database Systems (MMDBSs) and vice versa. We argue that MPEG-7 has to be considered complementary to, rather than competing with, data models employed in MMDBSs. Finally we show by an example scenario how these technologies can reasonably complement one another..}, address = {Heidelberg, Germany}, language = {EN}, publisher = {Springer}, url = {http://www.springerlink.com/content/gr9uwpdmlk2varl6/} } @Article{Kosch2002a, author = {Kosch, Harald and Atnafu, Solomon}, journal = {Information Processing Letter}, title = {A Multimedia Join by the Method of Nearest Neighbour Search}, year = {2002}, issn = {0020-0190}, month = jun, number = {Issue 5}, pages = {269-276}, volume = {Vol. 82}, abstract = {Multimedia databases; Processing of a multimedia join; Nearest neighbor search.}, address = {Oxford, UK}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/2002-0002-HKAS.pdf}, publisher = {Elsev}, url = {http://www.sciencedirect.com/science?} } @Article{Kosch2002, author = {Kosch, Harald}, journal = {Sigmod Records, ACM Press}, title = {MPEG-7 and Multimedia Database Systems}, year = {2002}, month = jun, number = {No. 2}, pages = {34-39}, volume = {Vol. 31}, address = {New York, NY, USA}, doi = {http://doi.acm.org/10.1145/565117.565123}, language = {EN}, publisher = {ACM}, url = {http://www.acm.org/sigmod/record/issues/0206/index.html} } @Article{Hellwagner2002a, author = {Hellwagner, Hermann and Ohlenroth, Matthias}, journal = {Future Generation Computer Systems}, title = {VI Architecture Communication Features and Performance on the Giganet Cluster LAN}, year = {2002}, issn = {0167-739X}, month = jan, number = {Issue 3}, pages = {421-433}, volume = {Vol. 18}, 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. VI architecture aims to close the performance gap between the bandwidths and latencies provided by the communication hardware and visible to the application, respectively, by minimizing the software overhead on the critical path of the communication. 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.}, address = {Amsterdam, Netherlands}, doi = {http://dx.doi.org/10.1016/S0167-739X(01)00060-7}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/VI Architecture Communication Features and Performance on the Giganet Cluster LAN.pdf}, publisher = {Elsevier B.V.}, url = {http://www.sciencedirect.com/science/article/pii/S0167739X01000607} } @Article{Weiß2000, author = {Weiß, Christian and Hellwagner, Hermann and Stals, Linda and Rüde, Ulrich}, journal = {Concepts of Numerical Software}, title = {Data Locality Optimizations to Improve The Efficiency of Multigrid Methods}, year = {2000}, month = {jan}, pages = {1-10}, abstract = {Current superscalar microprocessors are able to operate at a peak performance of up to 1 GFlop/sec. However, current main memory technology does not provide the data needed fast enough to keep the CPU busy. To minimize idle times of the CPU, caches are used to speed up accesses to frequently used data. To exploit caches, the software must be aware of them and reuse data in the cache before it is being replaced. Unfortunately, all conventional multigrid codes are not cache-aware and hence exploit less than 10 percent of the peak performance of cache based machines. Our studies with linear PDEs with constant coefficients show that it is possible to speed up the execution of our multigrid method by a large factor and hence solve a Poisson’s equation with one million unknowns in less than 3 seconds. The optimized reuse of data in the cache allows us to exploit 30 percent of the peak performance of the CPU, in contrast to mgd9v for instance, which achieves less than 5 percent on the same machine. To achieve this, we used several techniques like loop unrolling and loop fusion to better exploit the memory hierarchy and the superscalar CPU. We study the effects of these techniques on the runtime performance in detail. We also study several tools which guide the optimizations and help to restructure the code.}, address = {NA}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/10.1.1.42.3070.pdf}, publisher = {NA} } @Article{Kosch2000, author = {Kosch, Harald}, journal = {Future Generation Computer Systems}, title = {Managing the operator ordering problem in parallel data-Bases}, year = {2000}, month = may, number = {No 3}, pages = {665-676}, volume = {Vol 16}, abstract = {This paper focuses on parallel query optimization. We consider the operator problem and introduce a new class of execution strategies called Linear-oriented Bushy Trees (LBT). Compared to the related approach of the General Bushy Trees (GBT) a significant complexity reduction of the operator ordering problem can be derived theoretically and demonstrated experimentally (e.g. compared with GBTs, LBTs authorize optimization time improvement that can reach up to 49%) without losing quality. Finally we demonstrate that existing commercial parallel query optimizers need little extension mod ifications in order to handle LBTs.}, address = {Langford Lane, Kidlington, Oxford OX5 1GB, United Kingdom}, keywords = {Parallel databases, Parallel query optimization, Linear-oriented Bushy Trees, Extending existing optimizers}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1998-0039-Kosc.pdf}, publisher = {Elsevier} } @Article{Hoelzl2000, author = {Hölzl, Günter and Böszörmenyi, Laszlo}, journal = {Future Generation Computer Systems}, title = {Distributed Federative QoS Resource Managment-Extended version}, year = {2000}, month = apr, number = {Issue 6, No 16}, pages = {717-725}, volume = {Vol. 16}, address = {Oxford, United Kingdom}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/2000-0019-GHAL.pdf}, publisher = {Elsevier} } @Article{Boeszoermenyi2000, author = {Böszörmenyi, Laszlo}, journal = {APL-Journal}, title = {Computer im Kindergarten?}, year = {2000}, issn = {1438-4531}, month = {jan}, number = {Nr. 1}, pages = {29-33}, volume = {Jg. 19}, abstract = {Es läuft eine spannende Diskussion darüber, wie früh man Kinder an den Computer heranführen sollte. Jenseits solcher Intellektuellen-Diskussionen machen manche Firmen schon seit Jahren enorme Geschäfte mit Software und Hardware für Kinder im Kindergartenalter. Auch der erste Computer für Babys hat schon seinen Siegeszug auf dem amerikanischen Markt angetreten. Mit den Geschäftemachern zu diskutieren, ist wahrscheinlich nicht viel klüger als gegen Windmühlen zu kämpfen. Diese Firmen könnten ihre Geschäfte nicht machen, wenn es nicht viele Eltern, Großeltern, Pädagogen und Psychologen gäbe, die den Computer kleinen Kindern mit guter Absicht in die Hand geben. Die folgende Diskussion spricht die wohlwollenden Erwachsenen an, die sich für Kinder verantwortlich fühlen und sich nicht entscheiden können, wann und wie Kinder mit dem Phänomen Computer konfrontiert werden sollten.}, address = {Mannheim, Berlin, Nürnberg, Germany}, language = {DE}, pdf = {https://www.itec.aau.at/bib/files/p008EZ-01-1997.pdf}, publisher = {APL-Journal}, url = {http://www.rhombos.de/shop/c/file/000189/APL12000.pdf} } @Article{Hellwagner1999b, author = {Hellwagner, Hermann and Zoraja, Ivan and Sunderam, Vaidy}, journal = {Concurrency: Practice and Experience}, title = {SCIPVM: Parallel Distributed Computing on SCI Workstation Clusters}, year = {1999}, issn = {1096-9128}, month = feb, number = {No 3}, pages = {121-138}, volume = {Vol 11}, abstract = {Workstation and PC clusters interconnected by SCI (Scalable Coherent Interface) are very promising technologies for high performance cluster computing. Using commercial SBus to SCI interface cards and early system software and drivers, a two-workstation cluster has been constructed for initial testing and evaluation. The PVM system has been adapted to operate on this cluster using raw device access to the SCI interconnect, and preliminary communications performance tests have been carried out. Our preliminary results indicate that communications throughput in the range of 3.5 MBytes/s, and latencies Research supported by the Applied Mathematical Sciences program, Office of Basic Energy Sciences, U. S. Department of Energy, under Grant No. DE-FG05-91ER25105, the National Science Foundation, under Award Nos. ASC-9527186 and ASC-9214149, and the German Science Foundation SFB342. of 620 ¯s can be achieved on SCI clusters. These figures are significantly better (by a factor of 3 to 4) ...}, address = {N, A}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/10.1.1.41.2639.pdf}, publisher = {N, A} } @Article{Boeszoermenyi1999h, author = {Böszörmenyi, Laszlo}, journal = {Tani-Tani}, title = {Computer az óvodában?}, year = {1999}, month = dec, pages = {4-14}, address = {Budapest, Hungary}, language = {HU}, publisher = {Tani-Tani} } @Article{Boeszoermenyi1999g, author = {Böszörmenyi, Laszlo}, journal = {APL-Journal}, title = {Parallel Programming}, year = {1999}, month = nov, number = {Nr. 2}, pages = {85-89}, volume = {Jg. 18}, address = {Mannheim, Berlin, Nürnberg, Germany}, language = {EN}, publisher = {APL-Journal} } @Article{Boeszoermenyi1999a, author = {Böszörmenyi, Laszlo and Stopper, Andreas}, journal = {Simulation Practice and Theory}, title = {Semi-automatic parallelization of object-oriented simulations}, year = {1999}, issn = {0928-4869}, month = {jan}, number = {Issue 4}, pages = {295-307}, volume = {Vol. 7}, abstract = {An approach is introduced for semi-automatic parallelization of object-oriented simulations. The basic idea is to prepare parallelization at the earliest possible stage in the life-cycle of the creation of new simulations (i.e. at modeling), thus minimizing causality conflicts at run-time. The object-oriented model of a simulation is enriched by hints, describing the estimated load and communication costs between major classes and objects. This helps to grasp the inherent parallelism of the model. Based on this additional information, a partitioning with minimal communication between partitions can be generated automatically. Remaining dependency-conflicts must be resolved at run-time. The GoSim [A. Stopper, GoSim, ein Ansatz zur Beschleunigung diskreter, objektorientierter, verteilter Simulationen, Ph.D. Thesis, Institute of Informatics, University Klagenfurt, 1997] simulation system is presented, which implements the described proposal and provides semi-automatic parallelization of large-scale and/or high-performance simulations. It provides a description language, a partitioning tool, a program-skeleton generator and a simulation engine. Some measurements prove the usability of the approach.}, address = {Oxford, United Kingdom}, language = {EN}, publisher = {Elsevier} } @Article{Boeszoermenyi1998, author = {Böszörmenyi, Laszlo}, journal = {Software - Concepts \& Tools}, title = {Why Java is not my favorite first-course language}, year = {1998}, issn = {0945-8115}, month = {jan}, number = {Volume 19, Number 3}, pages = {141-145}, abstract = {The choice of the first-course programming language for a university-level computer science curriculum has pedagogical ramifications in terms of comprehensibility and mastery of fundamental concepts. This paper compares the merits of Java and Modula-3 as a first-course language.}, address = {Berlin, Heidelberg, New York}, doi = {10.1007/s003780050017}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1998_LB_Java.pdf}, publisher = {Springer} } @Article{Mayerle1997a, author = {Mayerle, Wolfgang and Hellwagner, Hermann}, journal = {Praxis der Informationsverarbeitung und Kommunikation}, title = {Konzepte und funktionaler Vergleich von Thread-Systemen (2)}, year = {1997}, issn = {0930-5157}, month = oct, number = {4}, pages = {225-229}, volume = {20}, address = {Mannheim, Germany}, language = {DE}, publisher = {Spani} } @Article{Mayerle1997, author = {Mayerle, Wolfgang and Hellwagner, Hermann}, journal = {Praxis der Informationsverarbeitung und Kommunikation}, title = {Konzepte und funktionaler Vergleich von Thread-Systemen (1)}, year = {1997}, issn = {0930-5157}, month = {jan}, pages = {164-174}, volume = {20}, abstract = {Dieses Papier gibt eine allgemeine Einführung in Threads und vergleicht einige derzeit für Arbeitsplatzrechner erhältliche Thread-Systeme. Aufbauend auf einer Motivation und grundlegenden Erläuterung des Thread-Konzepts werden wichtige Aspekte und Probleme von Thread-Bibliotheken vorgestellt. Nach einigen Hinweisen zur Programmierung mit Threads werden mehrere Implementierungen einander gegenübergestellt.}, address = {Mannheim, Germany}, language = {DE}, pdf = {https://www.itec.aau.at/bib/files/1997-0048-MaHe.pdf}, publisher = {Spaniol, Otto} } @Article{Hellwagner1997e, author = {Hellwagner, Hermann and Karl, Wolfgang and Leberecht, Markus}, journal = {Speedup Journal, Proceedings, 21st Workshop, March 13-14, 1997, Cadro-Lugano}, title = {Enabling a PC Cluster for High-Performance Computing}, year = {1997}, month = jun, number = {1}, pages = {18-23}, volume = {Vol. 11}, abstract = {Due to their excellent cost/performance ratio, clusters of PCs can be attractive high-performance computing (HPC) platforms. Yet, their limited communication performance over standard LANs is still prohibitive for parallel applications. The project "Shared Memory in a LAN-like Environment" (SMiLE) at LRR-TUM adopts Scalable Coherent Interface (SCI) interconnect technology to build, and provide software for, a PC cluster which, with hardware-based distributed shared memory (DSM) and high-performance communication characteristics, is regarded as well suited for HPC. The paper describes the key features of the enabling technology, SCI. It then discusses the developments and important results of the SMiLE project so far: the development and initial performance of a PCI/SCI interface card, and the design and initial performance results of low-latency communication layers, Active Messages and a sockets emulation library.}, address = {N, A}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1997-0049-HeKL.pdf}, publisher = {N, A} } @Article{Boeszoermenyi1997b, author = {Böszörmenyi, Laszlo}, journal = {Erziehungskunst - Monatsschrift zur Pädagogik Rudolf Steiners}, title = {Informatik in der Schule}, year = {1997}, month = feb, pages = {113-121}, address = {Stuttgart, Germany}, language = {DE}, pdf = {https://www.itec.aau.at/bib/files/EZ-02-1997.pdf}, publisher = {Erziehungskunst}, url = {http://www.erziehungskunst.de/archiv/jahrgang-1990-1999/jahrgang-1997/februar-1997/} } @Article{Boeszoermenyi1997a, author = {Böszörmenyi, Laszlo and Eder, Karl-Heinz and Weich, Carsten}, journal = {Simulations Practice and Theory}, title = {A Very Fast Parallel Object Store for Very Fast Applications}, year = {1997}, month = {jan}, pages = {605-622}, volume = {Volume 5, Numbers 7-8}, abstract = {An architecture for a memory-resident, Parallel and Persistent ObjectSTore (PPOST) is suggested. Different object-oriented databases might be built on top of PPOST. The term memory-resident (or main memory based) means that the primary storage device is main memory. Persistence is guaranteed automatically by managing secondary and stable storage devices (such as main memory with uninterrupted power supply, discs and tapes). The architecture is able to take advantage of available main memory in a parallel or distributed environment. Thus, transactions can be actually performed with memory-speed, without being limited by the size of the memory of a given computer. Such an architecture is especially advantageous for applications requiring very fast answers, such as CAD or high-performance simulation.}, address = {Oxford, United Kingdom}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/1997-0041-BoEW.pdf}, publisher = {Elsevier} } @Article{Boeszoermenyi1997, author = {Böszörmenyi, Laszlo and Eder, Karl-Heinz}, journal = {Parallel Computing}, title = {M3Set - A Language for Handling of Distributed and Persistent Sets of Objects}, year = {1997}, month = {jan}, number = {13}, pages = {1897-1912}, volume = {22}, abstract = {We claim that distributed object-oriented systems must provide a higher level of abstraction to their users, than usually provided. Especially, it is necessary to provide application-oriented, intelligent aggregates of objects with transparent distribution of their elements. Beside that, it seems to be not only reasonable, but also relatively easy to connect persistence with distribution. A system, offering distributed and persistent polymorphic sets of objects, on the level of a clean, type safe programming language is introduced. 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 or classes of objects.}, address = {Oxford, United Kingdom}, keywords = {Distributed object management, Parallel distributed languages, Parallel distributed databases, Object-oriented languages, Modula-3}, language = {EN}, publisher = {Elsevier}, url = {http://www.sciencedirect.com/science/article/pii/S0167819196000841} } @Article{Boeckle1996a, author = {Böckle, Günter and Hellwagner, Hermann and Lepold, Roland and Sandweg, Gerd and Schallenberger, Burghardt and Thudt, Raimar and and Wallstab, Stefan}, journal = {IEEE Computer Society}, title = {Structured Evaluation of Computer Systems}, year = {1996}, issn = {0018-9162}, month = jun, number = {No 6}, pages = {45-51}, volume = {Vol. 29}, abstract = {Evaluating computers and other systems is difficult for a couple of reasons. First, the goal of evaluation is typically ill-defined: customers, sometimes even designers, either don't know or can't specify exactly what result they expect. Often, they don't specify the architectural variants to consider, and often the metrics and workload they expect you to use are ill-defined. Second, they rarely clarify which kind of model and evaluation method best suit the evaluation problem. These problems have consequences. For one thing, the decision-maker may not trust the evaluation. For another, poor planning means the evaluation cannot be reproduced if any of the parameters are changed slightly. Finally, the evaluation documentation is usually inadequate, and so some time after the evaluation you might ask yourself, how did I come to that conclusion? An approach developed at Siemens makes decisions explicit and the process reproducible}, address = {N, A}, doi = {http://dx.doi.org/10.1109/2.507631}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/00507631.pdf}, publisher = {N, A} } @Article{Boeszoermenyi1994, author = {Böszörmenyi, Laszlo}, journal = {Erziehungskunst - Monatsschrift zur Pädagogik Rudolf Steiners}, title = {Phantasie und TV-Gewalt}, year = {1994}, month = mar, number = {3}, pages = {210-212}, volume = {58. Jahrgang}, address = {Stuttgart, Germany}, language = {DE}, publisher = {Erziehungskunst}, url = {http://www.erziehungskunst.de/archiv/jahrgang-1990-1999/jahrgang-1994/maerz-1994/} } @Article{Hellwagner1993, author = {Hellwagner, Hermann}, journal = {The Computer Journal - Parallel Processing}, title = {Design Considerations for Scalable Parallel File Systems}, year = {1993}, month = {jan}, number = {8}, pages = {741-755}, volume = {Vol. 36}, abstract = {This paper addresses the problem of providing high-performance disk I/O in massively parallel computers. Resolving the fundamental I/O bottleneck in parallel architectures involves both hardware and software issues. We review previous work on disk arrays and I/O architectures aimed at providing highly parallel disk I/O subsystems. We then focus on the requirements and design of parallel file systems (PFSs) which are responsible to make the parallelism offered by the hardware and a declustered file organization available to application programs. We present the design strategy and key concepts of a general-purpose file system for a parallel computer with scalable distributed shared memory. The principal objectives of the PFS are to fully exploit the parallelism inherent among and within file accesses, and to provide scalable I/O performance. The machine model underlying the design is described, with and emphasis on the innovative architectural features supporting scalability of the shared memory. Starting from a classification of various scenarios of concurrent I/O requests, the features of the PFS design essential for achieving the goals are described and justified. It is argued that the inter- and intra-request parallelism of the I/O load can indeed be effectively exploited and supported by the parallel system resources. Scalability of I/O performance and of the PFS software can be ensured by avoiding serial bottlenecks through the use of the powerful architectural features.}, address = {N, A}, language = {EN}, pdf = {https://www.itec.aau.at/bib/files/741.full.pdf}, publisher = {N, A} } @Article{Boeszoermenyi1993a, author = {Böszörmenyi, Laszlo}, journal = {Didaktische Zeitschrift des IST-Zentrums Linz}, title = {Informatik in der Grundschule}, year = {1993}, month = {jan}, pages = {15-17}, address = {Linz, Austria}, language = {DE}, publisher = {Interdisziplinäre Zentrum für Soziale Kompetenz} } @Article{Boeszoermenyi1993, author = {Böszörmenyi, Laszlo}, journal = {Structured Programming}, title = {A Comparison of Modula-3 and Oberon-2: extended version}, year = {1993}, month = {jan}, number = {1}, pages = {15-22}, volume = {Volume 14}, address = {Berlin, Heidelberg, New York}, language = {EN}, publisher = {Springer} } @Article{Boeszoermenyi1992a, author = {Böszörmenyi, Laszlo}, journal = {Informatik in der Schule - Informatik für die Schule}, title = {Informatik und Wissenschaftsgeschichte}, year = {1992}, issn = {3205055322}, month = sep, pages = {not available}, volume = {10}, abstract = {Informatik in der Schule - Informatik für die Schule.}, address = {Vienna, Austria}, language = {DE}, publisher = {Böhlau} }