% Year: 2018 % Encoding: utf-8 @InProceedings{Zhou2018, author = {Zhou, Liting and Piras, Luca and Riegler, Michael and Lux, Mathias and Dang-Nguyen, Duc-Tien and Gurrin, Cathal}, title = {{An Interactive Lifelog Retrieval System for Activities of Daily Living Understanding}}, booktitle = {CLEF 2018 Working Notes}, year = {2018}, month = {September}, publisher = {CEUR-Workshop Proceedings}, abstract = {This paper describes the participation of the Organizer Teamin the ImageCLEFlifelog 2018 Daily Living Understanding and Lifelog MomentRetrieval. In this paper, we propose how to exploit LIFER, aninteractive lifelog search engine to solve the two tasks: Lifelog MomentRetrieval and Activities of Daily Living Understanding. We propose approachesfor both baseline, which aim to provide a reference system forother approaches, and human-in-the-loop, which advance the baselineresults.}, url = {http://ceur-ws.org/Vol-2125/} } @InProceedings{Zabrovskiy2018a, title = {{A Practical Evaluation of Video Codecs for Large-Scale HTTP Adaptive Streaming Services}}, author = {Zabrovskiy, Anatoliy and Feldmann, Christian and Timmerer, Christian}, booktitle = {2018 25th IEEE International Conference on Image Processing (ICIP)}, year = {2018}, address = {Piscataway (NJ)}, month = {Oktober}, pages = {998--1002}, publisher = {IEEE}, abstract = {The number of bandwidth-hungry applications and services is constantly growing. HTTP adaptive streaming of audiovisual content accounts for the majority of today's internet traffic. Although the internet bandwidth increases also constantly, audio-visual compression technology is inevitable and we are currently facing the challenge to be confronted with multiple video codecs. This paper provides a practical evaluation of state of the art video codecs (i. e., AV1, AVC/libx264, HEVC/libx265, VP9/Iibvpx-vp9) for large-scale HTTP adaptive streaming services. In anticipation of the results, AV I shows promising performance compared to established video codecs. Additionally, AV I is intended to be royalty free making it worthwhile to be considered for large scale HTTP adaptive streaming services.}, doi = {10.1109/ICIP.2018.8451017}, url = {https://ieeexplore.ieee.org/document/8451017} } @InProceedings{Zabrovskiy2018, title = {Multi-codec DASH dataset}, author = {Zabrovskiy, Anatoliy and Feldmann, Christian and Timmerer, Christian}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {438--443}, publisher = {ACM Press}, abstract = {The number of bandwidth-hungry applications and services is constantly growing. HTTP adaptive streaming of audio-visual content accounts for the majority of today's internet traffic. Although the internet bandwidth increases also constantly, audio-visual compression technology is inevitable and we are currently facing the challenge to be confronted with multiple video codecs.This paper proposes a multi-codec DASH dataset comprising AVC, HEVC, VP9, and AV1 in order to enable interoperability testing and streaming experiments for the efficient usage of these codecs under various conditions. We adopt state of the art encoding and packaging options and also provide basic quality metrics along with the DASH segments. Additionally, we briefly introduce a multi-codec DASH scheme and possible usage scenarios. Finally, we provide a preliminary evaluation of the encoding efficiency in the context of HTTP adaptive streaming services and applications.}, doi = {10.1145/3204949.3208140}, url = {https://dl.acm.org/citation.cfm?id=3208140} } @InProceedings{Trattnig2018, title = {Investigation of YouTube regarding Content Provisioning for HTTP Adaptive Streaming}, author = {Trattnig, Armin and Timmerer, Christian and Müller, Christopher}, booktitle = {PV '18 Proceedings of the 23rd Packet Video Workshop}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {60--65}, publisher = {ACM Press}, abstract = {About 300 hours of video are uploaded to YouTube every minute. The main technology to delivery YouTube content to various clients is HTTP adaptive streaming and the majority of today's internet traffic comprises streaming audio and video. In this paper, we investigate content provisioning for HTTP adaptive streaming under predefined aspects representing content features and upload characteristics as well and apply it to YouTube. Additionally, we compare the YouTube's content upload and processing functions with a commercially available video encoding service. The results reveal insights into YouTube's content upload and processing functions and the methodology can be applied to similar services. All experiments conducted within the paper allow for reproducibility thanks to the usage of open source tools, publicly available datasets, and scripts used to conduct the experiments on virtual machines.}, doi = {10.1145/3210424.3210431}, url = {https://dl.acm.org/citation.cfm?id=3210424.3210431} } @InProceedings{TimmererHVEI2018, title = {{A Framework for Adaptive Delivery of Omnidirectional Video}}, author = {Timmerer, Christian and Begen, Ali Cengiz}, booktitle = {IS\&T International Symposium on Electronic Imaging 2018, Human Vision and Electronic Imaging 2018 Conference}, year = {2018}, month = jan, issn = {2470-1173}, journal = {Electronic Imaging}, url = {https://doi.org/10.2352/ISSN.2470-1173.2018.14.HVEI-524} } @InProceedings{Timmerer2018c, author = {Timmerer, Christian and Zabrovskiy, Anatoliy and Begen, Ali C.}, title = {{Automated Objective and Subjective Evaluation of HTTP Adaptive Streaming Systems}}, booktitle = {2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)}, year = {2018}, address = {Piscataway (NJ)}, month = {April}, publisher = {IEEE}, abstract = {Streaming audio and video content currently accounts for the majority of the internet traffic and is typically deployed over the top of the existing infrastructure. We are facing the challenge of a plethora of media players and adaptation algorithms showing different behavior but lack a common framework for both objective and subjective evaluation of such systems. This paper aims to close this gap by (i) proposing such a framework, (ii) describing its architecture, (iii) providing an example evaluation, (iv) and discussing open issues.}, doi = {10.1109/MIPR.2018.00080}, url = {https://ieeexplore.ieee.org/document/8397036/} } @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} } @InProceedings{Timmerer2018_NAB, title = {Efficient Multi-Codec Support for OTT Services: HEVC/H.265 and/or AV1?}, author = {Timmerer, Christian and Smole, Martin and Mueller, Christopher}, booktitle = {2018 NAB BEIT Proceedings}, year = {2018}, address = {Washington DC, USA}, editor = {available, not}, month = apr, pages = {5}, publisher = {National Association of Broadcasters (NAB)} } @InProceedings{Timmerer2018_MIPR, title = {Automated Objective and Subjective Evaluation of HTTP Adaptive Streaming Systems}, author = {Timmerer, Christian and Zabrovskiy, Anatoliy and Begen, Ali Cengiz}, booktitle = {Proceedings of the 1st IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR)}, year = {2018}, editor = {available, not}, month = apr, pages = {6}, abstract = {Streaming audio and video content currently accounts for the majority of the internet traffic and is typically deployed over the top of the existing infrastructure. We are facing the challenge of a plethora of media players and adaptation algorithms showing different behavior but lack a common framework for both objective and subjective evaluation of such systems. This paper aims to close this gap by (i) proposing such a framework, (ii) describing its architecture, (iii) providing an example evaluation, (iv) and discussing open issues.}, doi = {10.1109/MIPR.2018.00080}, url = {https://ieeexplore.ieee.org/document/8397036/} } @InProceedings{Timmerer2018, author = {Timmerer, Christian}, title = {{MPEG column: 123rd MPEG meeting in Ljubljana, Slovenia}}, booktitle = {ACM SIGMultimedia Records}, year = {2018}, volume = {10}, address = {New York (NY)}, month = {September}, publisher = {ACM Press}, abstract = {The original blog post can be found at the Bitmovin Techblog and has been modified/updated here to focus on and highlight research aspects.}, doi = {10.1145/3300001.3300012}, url = {https://dl.acm.org/citation.cfm?id=3300012} } @InProceedings{Taschwer2018a, author = {Taschwer, Mario and Primus, Manfred J{\"u}rgen and Schoeffmann, Klaus and Marques, Oge}, booktitle = {Working Notes Proceedings of the MediaEval 2018 Workshop}, title = {Early and Late Fusion of Classifiers for the {MediaEval Medico} Task}, year = {2018}, editor = {M. Larson and P. Arora and C.H. Demarty and M. Riegler and B. Bischke and E. Dellandrea and M. Lux and A. Porter and G.J.F. Jones}, series = {CEUR Workshop Proceedings}, volume = {2283}, url = {http://ceur-ws.org/Vol-2283/MediaEval_18_paper_23.pdf} } @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} } @Book{Schoeffmann2018e, title = {{MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 1)}}, publisher = {Springer}, year = {2018}, author = {Schöffmann, Klaus and Chalidabhongse, Thanarat H. and Ngo, Chong-Wah and O´Connor, Noel E. and Aramvith, Supavadee and Ho, Yo-Sung and Gabbouj, Moncef and Elgammal, Ahmed}, volume = {10704}, month = {Januar}, doi = {10.1007/978-3-319-73603-7}, url = {https://www.springer.com/de/book/9783319736020} } @InProceedings{Schoeffmann2018d, author = {Schöffmann, Klaus and Münzer, Bernd and Primus, Manfred Jürgen and Kletz, Sabrina and Leibetseder, Andreas}, title = {{How Experts Search Different Than Novices – An Evaluation of the diveXplore Video Retrieval System at Video Browser Showdown 2018}}, booktitle = {2018 IEEE International Conference on Multimedia \& Expo Workshops (ICMEW)}, year = {2018}, address = {Piscataway (NJ)}, month = {Juli}, publisher = {IEEE}, abstract = {We present a modern interactive video retrieval tool, called diveXplore, that has been used for several iterations of the Video Browser Showdown (VBS) competition with great success – 2nd place for the last two years in a row. The tool provides novel video content search and interaction features (e.g., a semantic map-search & browsing feature with similarity arrangement and a highly efficient sketch-search, optimized for mobile touch-interaction) that make it perfectly suited for flexible video retrieval in large video collections. With the help of a user study we show that the diveXplore system can be used very efficiently by both type of users: novices and experts. Our evaluation results do also show that the interaction statistics of novices and experts differ in terms of used features. The details of our insights can be used to further optimize interfaces of video retrieval tools for non-experts.}, doi = {10.1109/ICMEW.2018.8551552}, url = {https://ieeexplore.ieee.org/document/8551552} } @InProceedings{Schoeffmann2018c, author = {Schöffmann, Klaus and Bailer, Werner and Gurrin, Cathal and Awad, George M. and Lokoč, Jakub}, title = {{Interactive Video Search: Where is the User in the Age of Deep Learning?}}, booktitle = {MM '18 Proceedings of the 26th ACM international conference on Multimedia}, year = {2018}, pages = {2101--2103}, address = {New York (NY)}, month = {Oktober}, publisher = {ACM Press}, abstract = {In this tutorial we discuss interactive video search tools and methods, review their need in the age of deep learning, and explore video and multimedia search challenges and their role as evaluation benchmarks in the field of multimedia information retrieval. We cover three different campaigns (TRECVID, Video Browser Showdown, and the Lifelog Search Challenge), discuss their goals and rules, and present their achieved findings over the last half-decade. Moreover, we talk about datasets, tasks, evaluation procedures, and examples of interactive video search tools, as well as how they evolved over the years. Participants of this tutorial will be able to gain collective insights from all three challenges and use them for focusing their research efforts on outstanding problems that still remain unsolved in this area.}, doi = {10.1145/3240508.3241473}, url = {https://dl.acm.org/citation.cfm?id=3241473} } @Book{Schoeffmann2018b, title = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 2)}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Supavadee Aramvith and Noel E. O´Connor and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, publisher = {Springer}, year = {2018}, month = {Januar}, volume = {10705}, doi = {10.1007/978-3-319-73600-6}, url = {https://www.springer.com/de/book/9783319735993} } @Book{Schoeffmann2018a, title = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 1)}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Noel E. O´Connor and Supavadee Aramvith and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, publisher = {Springer}, year = {2018}, month = {Januar}, volume = {10704}, doi = {10.1007/978-3-319-73603-7}, url = {https://www.springer.com/de/book/9783319736020} } @InProceedings{Schoeffmann2018, title = {Cataract-101: video dataset of 101 cataract surgeries}, author = {Klaus Schöffmann and Mario Taschwer and Stephanie Sarny and Bernd Münzer and Manfred Jürgen Primus and Doris Putzgruber-Adamitsch}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Mai}, pages = {421--425}, publisher = {ACM Press}, abstract = {Cataract surgery is one of the most frequently performed microscopic surgeries in the field of ophthalmology. The goal behind this kind of surgery is to replace the human eye lense with an artificial one, an intervention that is often required due to aging. The entire surgery is performed under microscopy, but co-mounted cameras allow to record and archive the procedure. Currently, the recorded videos are used in a postoperative manner for documentation and training. An additional benefit of recording cataract videos is that they enable video analytics (i.e., manual and/or automatic video content analysis) to investigate medically relevant research questions (e.g., the cause of complications). This, however, necessitates a medical multimedia information system trained and evaluated on existing data, which is currently not publicly available. In this work we provide a public video dataset of 101 cataract surgeries that were performed by four different surgeons over a period of 9 months. These surgeons are grouped into moderately experienced and highly experienced surgeons (assistant vs. senior physicians), providing the basis for experience-based video analytics. All videos have been annotated with quasi-standardized operation phases by a senior ophthalmic surgeon.}, doi = {http://dx.doi.org/10.1145/3204949.3208137}, url = {https://dl.acm.org/citation.cfm?id=3208137} } @InProceedings{Riegler2018, author = {Riegler, Michael and Halvorsen, Pal and Münzer, Bernd and Schöffmann, Klaus}, title = {{The Importance of Medical Multimedia}}, booktitle = {MM '18 Proceedings of the 26th ACM international conference on Multimedia}, year = {2018}, pages = {2016--2108}, address = {New York (NY)}, month = {Oktober}, publisher = {ACM Press}, abstract = {Multimedia research is becoming more and more important for the medical domain, where an increasing number of videos and images are integrated in the daily routine of surgical and diagnostic work. While the collection of medical multimedia data is not an issue, appropriate tools for efficient use of this data are missing. This includes management and inspection of the data, visual analytics, as well as learning relevant semantics and using recognition results for optimizing surgical and diagnostic processes. The characteristics and requirements in this interesting but challenging field are different than the ones in classic multimedia domains. Therefore, this tutorial gives a general introduction to the field, provides a broad overview of specific requirements and challenges, discusses existing work and open challenges, and elaborates in detail how machine learning approaches can help in multimedia-related fields to improve the performance of surgeons/clinicians.}, doi = {10.1145/3240508.3241475}, url = {https://dl.acm.org/citation.cfm?id=3241475} } @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} } @InProceedings{Rainer2018, author = {Rainer, Benjamin and Petscharnig, Stefan and Timmerer, Christian}, title = {{Merge and Forward: A Self-Organized Inter-Destination Media Synchronization Scheme for Adaptive Media Streaming over HTTP}}, booktitle = {MediaSync}, year = {2018}, pages = {593--627}, address = {Berlin}, month = {März}, publisher = {Springer}, abstract = {In this chapter, we present Merge and Forward, an IDMS scheme for adaptive HTTP streaming as a distributed control scheme and adopting the MPEG-DASH standard as representation format. We introduce so-called IDMS sessions and describe how an unstructured peer-to-peer overlay can be created using the session information using MPEG-DASH. We objectively assess the performance of Merge and Forward with respect to convergence time (time needed until all clients hold the same reference time stamp) and scalability. After the negotiation on a reference time stamp, the clients have to synchronize their multimedia playback to the agreed reference time stamp. In order to achieve this, we propose a new adaptive media playout approach minimizing the impact of playback synchronization on the QoE. The proposed adaptive media playout is assessed subjectively using crowd sourcing. We further propose a crowd sourcing methodology for conducting subjective quality assessments in the field of IDMS by utilizing GWAP. We validate the applicability of our methodology by investigating the lower asynchronism threshold for IDMS in scenarios like online quiz games.}, doi = {10.1007/978-3-319-65840-7_21}, url = {https://link.springer.com/chapter/10.1007/978-3-319-65840-7_21} } @InProceedings{Primus2018a, title = {The ITEC Collaborative Video Search System at the Video Browser Showdown 2018}, author = {Manfred Jürgen Primus and Bernd Münzer and Andreas Leibetseder and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 2)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Supavadee Aramvith and Noel E. O´Connor and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {438--443}, publisher = {Springer}, series = {LNCS}, volume = {10705}, abstract = {We present our video search system for the Video Browser Showdown (VBS) 2018 competition. It is based on the collaborative system used in 2017, which already performed well but also revealed high potential for improvement. Hence, based on our experience we introduce several major improvements, particularly (1) a strong optimization of similarity search, (2) various improvements for concept-based search, (3) a new flexible video inspector view, and (4) extended collaboration features, as well as numerous minor adjustments and enhancements, mainly concerning the user interface and means of user interaction. Moreover, we present a spectator view that visualizes the current activity of the team members to the audience to make the competition more attractive.}, doi = {10.1007/978-3-319-73600-6_47}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73600-6_47} } @InProceedings{Primus2018, title = {Frame-Based Classification of Operation Phases in Cataract Surgery Videos}, author = {Manfred Jürgen Primus and Doris Putzgruber-Adamitsch and Mario Taschwer and Bernd Münzer and Yosuf El-Shabrawi and Laszlo Böszörmenyi and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 1)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Noel E. O´Connor and Supavadee Aramvith and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {241--253}, publisher = {Springer}, series = {LNCS}, volume = {10704}, abstract = {Cataract surgeries are frequently performed to correct a lens opacification of the human eye, which usually appears in the course of aging. These surgeries are conducted with the help of a microscope and are typically recorded on video for later inspection and educational purposes. However, post-hoc visual analysis of video recordings is cumbersome and time-consuming for surgeons if there is no navigation support, such as bookmarks to specific operation phases. To prepare the way for an automatic detection of operation phases in cataract surgery videos, we investigate the effectiveness of a deep convolutional neural network (CNN) to automatically assign video frames to operation phases, which can be regarded as a single-label multi-class classification problem. In absence of public datasets of cataract surgery videos, we provide a dataset of 21 videos of standardized cataract surgeries and use it to train and evaluate our CNN classifier. Experimental results display a mean F1-score of about 68% for frame-based operation phase classification, which can be further improved to 75% when considering temporal information of video frames in the CNN architecture.}, doi = {10.1007/978-3-319-73603-7_20}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73603-7_20} } @InProceedings{Postoaca2018, title = {{h-Fair: Asymptotic Scheduling of Heavy Workloads in Heterogeneous Data Centers}}, author = {Postoaca, Andrei and Pop, Florin and Prodan, Radu}, booktitle = {2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)}, year = {2018}, address = {Piscataway (NJ)}, month = {Mai}, publisher = {IEEE}, abstract = {Large scale computing solutions are increasingly used in the context of Big Data platforms, where efficient scheduling algorithms play an important role in providing optimized cluster resource utilization, throughput and fairness. This paper deals with the problem of scheduling a set of jobs across a cluster of machines handling the specific use case of fair scheduling for jobs and machines with heterogeneous characteristics. Although job and cluster diversity is unprecedented, most schedulers do not provide implementations that handle multiple resource type fairness in a heterogeneous system. We propose in this paper a new scheduler called h-Fair that selects jobs for scheduling based on a global dominant resource fairness heterogeneous policy, and dispatches them on machines with similar characteristics to the resource demands using the cosine similarity. We implemented h-Fair in Apache Hadoop YARN and we compare it with the existing Fair Scheduler that uses the dominant resource fairness policy based on the Google workload trace. We show that our implementation provides better cluster resource utilization and allocates more containers when jobs and machines have heterogeneous characteristics.}, doi = {10.1109/CCGRID.2018.00058}, url = {https://ieeexplore.ieee.org/document/8411047/authors#authors} } @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} } @InProceedings{Pogorelov2018a, author = {Pogorelov, Konstantin and Riegler, Michael and Halvorsen, Pal and Hicks, Steven Alexander and Ranheim Randel, Kristin and Dang-Nguyen, Duc-Tien and Lux, Mathias and Ostroukhova, Olga and de Lange, Thomas}, title = {{Medico Multimedia Task at MediaEval 2018}}, booktitle = {Working Notes Proceedings of the MediaEval 2018 Workshop}, year = {2018}, address = {Aachen}, month = {Oktober}, publisher = {CEUR Workshop Proceedings (CEUR-WS.org)}, abstract = {The Medico: Multimedia for Medicine Task, running for the secondtime as part of MediaEval 2018, focuses on detecting abnormalities,diseases, anatomical landmarks and other findings in imagescaptured by medical devices in the gastrointestinal tract. The taskis described, including the use case and its challenges, the datasetwith ground truth, the required participant runs and the evaluationmetrics.}, url = {http://ceur-ws.org/Vol-2283/} } @InProceedings{Pogorelov2018, title = {Opensea: open search based classification tool}, author = {Konstantin Pogorelov and Zeno Albisser and Olga Ostroukhova and Mathias Lux and Dag Johansen and Pal Halvorsen and Michael Riegler}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {363--368}, publisher = {ACM Press}, abstract = {This paper presents an open-source classification tool for image and video frame classification. The classification takes a search-based approach and relies on global and local image features. It has been shown to work with images as well as videos, and is able to perform the classification of video frames in real-time so that the output can be used while the video is recorded, playing, or streamed. OpenSea has been proven to perform comparable to state-of-the-art methods such as deep learning, at the same time performing much faster in terms of processing speed, and can be therefore seen as an easy to get and hard to beat baseline. We present a detailed description of the software, its installation and use. As a use case, we demonstrate the classification of polyps in colonoscopy videos based on a publicly available dataset. We conduct leave-one-out-cross-validation to show the potential of the software in terms of classification time and accuracy.}, doi = {10.1145/3204949.3208128}, url = {https://dl.acm.org/citation.cfm?id=3208128} } @InProceedings{PetscharnigMMM18Demo, author = {Petscharnig, Stefan and Schöffmann, Klaus}, booktitle = {International Conference on Multimedia Modeling}, title = {ActionVis: An Explorative Tool to Visualize Surgical Actions in Gynecologic Laparoscopy}, year = {2018}, address = {Cham, Switzerland}, editor = {not available, yet}, month = {feb}, pages = {1-5}, publisher = {Springer}, abstract = {Appropriate visualization of endoscopic surgery recordings has a huge potential to benefit surgical work life. For example, it enables surgeons to quickly browse medical interventions for purposes of documentation, medical research, discussion with colleagues, and training of young surgeons. Current literature on automatic action recognition for endoscopic surgery covers domains where surgeries follow a standardized pattern, such as cholecystectomy. However, there is a lack of support in domains where such standardization is not possible, such as gynecologic laparoscopy. We provide ActionVis, an interactive tool enabling surgeons to quickly browse endoscopic recordings. Our tool analyses the results of a post-processing of the recorded surgery. Information on individual frames are aggregated temporally into a set of scenes representing frequent surgical actions in gynecologic laparoscopy, which help surgeons to navigate within endoscopic recordings in this domain.}, doi = {10.1007/978-3-319-73600-6_30}, language = {EN}, location = {Bangkok, Thailand}, talkdate = {2018.02.05}, talktype = {poster}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73600-6_30} } @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} } @InProceedings{Muenzer2018a, author = {Münzer, Bernd and Leibetseder, Andreas and Kletz, Sabrina and Primus, Manfred Jürgen and Schöffmann, Klaus}, title = {{lifeXplore at the Lifelog Search Challenge 2018}}, booktitle = {LSC '18 Proceedings of the 2018 ACM Workshop on The Lifelog Search Challenge}, year = {2018}, address = {New York, NY}, month = {Juni}, publisher = {ACM Digital Library}, abstract = {With the growing hype for wearable devices recording biometric data comes the readiness to capture and combine even more personal information as a form of digital diary - lifelogging today is practiced ever more and can be categorized anywhere between an informative hobby and a life-changing experience. From an information processing point of view, analyzing the entirety of such multi-source data is immensely challenging, which is why the first Lifelog Search Challenge 2018 competition is brought into being, as to encourage the development of efficient interactive data retrieval systems. Answering this call, we present a retrieval system based on our video search system diveXplore, which has successfully been used in the Video Browser Showdown 2017 and 2018. Due to the different task definition and available data corpus, the base system was adapted and extended to this new challenge. The resulting lifeXplore system is a flexible retrieval and exploration tool that offers various easy-to-use, yet still powerful search and browsing features that have been optimized for lifelog data and for usage by novice users. Besides efficient presentation and summarization of lifelog data, it includes searchable feature maps, concept and metadata filters, similarity search and sketch search.}, doi = {10.1145/3210539.3210541}, url = {https://dl.acm.org/citation.cfm?id=3210541} } @InProceedings{Muenzer2018, title = {Video Browsing on a Circular Timeline}, author = {Bernd Münzer and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 2)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Supavadee Aramvith and Noel E. O´Connor and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {395--399}, publisher = {Springer}, series = {LNCS}, volume = {10705}, abstract = {The emerging ubiquity of videos in all aspects of society demands for innovative and efficient browsing and navigation mechanisms. We propose a novel visualization and interaction paradigm that replaces the traditional linear timeline with a circular timeline. The main advantages of this new concept are (1) significantly increased and dynamic navigation granularity, (2) minimized spacial distances between arbitrary points on the timeline, as well as (3) the possibility to efficiently utilize the screen space for bookmarks or other supplemental information associated with points of interest. The demonstrated prototype implementation proves the expedience of this new concept and includes additional navigation and visualization mechanisms, which altogether create a powerful video browser.}, doi = {10.1007/978-3-319-73600-6_40}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73600-6_40} } @InProceedings{Moll2018d, author = {Moll, Philipp and Lux, Mathias and Theuermann, Sebastian and Hellwagner, Hermann}, title = {{A Network Traffic and Player Movement Model to Improve Networking for Competitive Online Games}}, booktitle = {Proceedings of the 16th Annual Workshop on Network and Systems Support for Games (NetGames 2018)}, year = {2018}, pages = {1--6}, month = {Juni}, abstract = {}, doi = {}, url = {https://dl.acm.org/citation.cfm?id=3307315}, pdf = {https://www.itec.aau.at/bib/files/a1-moll.pdf} } @InProceedings{Moll2018c, author = {Moll, Philipp and Lux, Mathias and Theuermann, Sebastian and Hellwagner, Hermann}, title = {{A Network Traffic and Player Movement Model to Improve Networking for Competitive Online Games}}, booktitle = {Proceedings of the OAGM Workshop 2018}, year = {2018}, pages = {89--89}, month = {Mai}, abstract = {The popularity of computer games and e-sports is enormously high and still growing every year. Despite the popularity computer games often rely on old technologies, especially in the field of networking. Research in networking for games is challenging due to the low availability of up-todate datasets and network traces. In order to achieve a high user satisfaction while keeping the network activity as low as possible, modern networking solutions of computer games take players’ activities as well as closeness of players in the game world into account. In this paper, we analyze the Battle Royale game mode of the online multiplayer game Fortnite, where 100 players challenge each other in a king-of-the-hill like game within a constantly contracting game world, as an example for a popular online game with demanding technical requirements. We extrapolate player movement patterns by finding player positions automatically from videos, uploaded by Fortnite players on popular streaming platforms and show, how they influence network traffic from the client to the server and vice versa. This extended abstract features the highlights of [1], which has been accepted at the NetGames 2018 event.}, doi = {10.3217/978-3-85125-603-1-17}, url = {http://diglib.tugraz.at/proceedings-of-the-oagm-workshop-2018-2018} } @InProceedings{Moll2018b, author = {Moll, Philipp and Theuermann, Sebastian and Hellwagner, Hermann}, title = {{Wireless Network Emulation for Research on Information-Centric Networking}}, booktitle = {WiNTECH '18 Proceedings of the 12th International Workshop on Wireless Network Testbeds, Experimental Evaluation \& Characterization}, year = {2018}, pages = {46--55}, address = {New York (NY)}, month = {Oktober}, publisher = {ACM Press}, abstract = {When developing new approaches in networking research, one of the most important requirements is to evaluate the degree of improvement of a new approach both realistically and cost-effectively. Wireless networks and their adequate emulation play an important role in evaluation, but emulation of wireless links and networks is still difficult to handle. In this paper, we present a low-cost, fixed-network testbed able to emulate the dynamically changing conditions of wireless links caused by client mobility and physical phenomena. We extend the existing fixed-network testbed for the purpose of wireless network emulation using the Linux tools tc, iptables, and NetEm in sophisticated ways. Convenient function blocks are provided to configure wireless network topologies as well as dynamic link and mobility conditions to be emulated with modest efforts. We utilize the testbed's capabilities to investigate the influence of different mobility models on streaming SVC-encoded videos in Named Data Networking (NDN), a novel Information-Centric Networking architecture. Furthermore, we evaluate the benefits of using early loss detection mechanisms for streaming in NDN, by implementing Wireless Loss Detection and Recovery (WLDR). Our results show that the extended fixed-network testbed can precisely emulate wireless network conditions and usage. For instance, the emulation revealed that both the choice of the mobility model and the use of WLDR have a substantial influence on the resulting SVC video streaming performance.}, doi = {10.1145/3267204.3267211}, url = {https://dl.acm.org/citation.cfm?id=3267211}, pdf = {https://www.itec.aau.at/bib/files/p46-moll.pdf} } @InProceedings{Moll2018a, title = {{Persistent Interests in Named Data Networking}}, author = {Moll, Philipp and Theuermann, Sebastian and Hellwagner, Hermann}, booktitle = {2018 IEEE 87th Vehicular Technology Conference (VTC Spring)}, year = {2018}, address = {Piscataway (NJ)}, month = {Juni}, publisher = {IEEE}, abstract = {Recent research in the field of Information-Centric Networking (ICN) shows the need for push-based data transfer, which is not supported in current pull-based ICN architectures, such as Named Data Networking (NDN). IoT deployments as well as emergency notifications and real-time multimedia communication are well suited to be realized using the ICN principles, but experience challenges in pull-based environments. Persistent Interests (PIs) are a promising approach to introduce pushlike traffic in Interest-based ICN architectures such as NDN. In this paper, we explore the characteristics of PIs and discuss advantages and disadvantages of using them. We provide an efficient solution for preventing so-called Data loops, which are introduced by giving up NDN’s one-request-per-packet principle. Furthermore, we investigate the performance of PIs compared to classical Interests in terms of the computational complexity of forwarding and discuss possible applications of PIs.}, doi = {10.1109/VTCSpring.2018.8417861}, url = {https://ieeexplore.ieee.org/document/8417861/}, pdf = {https://www.itec.aau.at/bib/files/08417861.pdf} } @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} } @InProceedings{Lux2018b, author = {Lux, Mathias and Brown, John N. A.}, title = {{Playing Captain Kirk: Designing a Video Game Based on Star Trek}}, booktitle = {Set Phasers to Teach!}, year = {2018}, pages = {125--135}, address = {Berlin}, month = {Juli}, publisher = {Springer}, doi = {10.1007/978-3-319-73776-8}, url = {https://www.springer.com/gp/book/9783319737751} } @Inproceedingsn{Lux2018a, author = {Lux, Mathias and Riegler, Michael and Dang-Nguyen, Duc-Tien and Larson, Marcus and Potthast, Martin and Halvorsen, Pal}, title = {{GameStory Task at MediaEval 2018}}, month = {Oktober}, year = {2018}, abstract = {That video games have reached the masses is well known. Moreover,game streaming and watching other people play video games is aphenomenon that has outgrown its small beginnings. Game videostreams, be it live or recorded, are viewed by millions. E-sports is theresult of organized leagues and tournaments in which players cancompete in controlled environments and viewers can experiencethe matches, discuss and criticize, just like in physical sports. In theGameStory task, taking place the first time in 2018, we approachthe game streaming and e-sports phenomena from a multimediaresearch side. We focus on the task of summarizing matches usinga specific relevant game, Counter-Strike: Global Offensive, as a casestudy. With the help of ZNIPE.tv, we provide a data set of highquality data and meta data from competitive tournaments and aimto foster research in the area of e-sports and game streaming.}, address = {Aachen}, booktitle = {Working Notes Proceedings of the MediaEval 2018 Workshop}, publisher = {CEUR Workshop Proceedings (CEUR-WS.org)}, url = {http://ceur-ws.org/Vol-2283/} } @InCollection{Lux2018, title = {{Playing Captain Kirk: Designing a Video Game Based on Star Trek}}, author = {Lux, Mathias and Brown, John N. A.}, booktitle = {Set Phasers to Teach!}, publisher = {Springer}, year = {2018}, address = {Berlin}, month = {Juli}, pages = {125--135}, doi = {10.1007/978-3-319-73776-8}, url = {https://www.springer.com/gp/book/9783319737751} } @InProceedings{Lokoc2018a, author = {Lokoč, Jakub and Bailer, Werner and Schöffmann, Klaus}, title = {{What is the Role of Similarity for Known-Item Search at Video Browser Showdown? }}, booktitle = {SISAP 2018: Similarity Search and Applications}, year = {2018}, pages = {96--104}, address = {Berlin}, month = {Oktober}, publisher = {Springer}, abstract = {Across many domains, machine learning approaches start to compete with human experts in tasks originally considered as very difficult for automation. However, effective retrieval of general video shots still represents an issue due to their variability, complexity and insufficiency of training sets. In addition, users can face problems trying to formulate their search intents in a given query interface. Hence, many systems still rely also on interactive human-machine cooperation to boost effectiveness of the retrieval process. In this paper, we present our experience with known-item search tasks in the Video Browser Showdown competition, where participating interactive video retrieval systems mostly rely on various similarity models. We discuss the observed difficulty of known-item search tasks, categorize employed interaction components (relying on similarity models) and inspect successful interactive known-item searches from the recent iteration of the competition. Finally, open similarity search challenges for known-item search in video are presented.}, doi = {10.1007/978-3-030-02224-2_8}, url = {https://link.springer.com/chapter/10.1007%2F978-3-030-02224-2_8} } @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)} } @InProceedings{Leibetseder2018c, author = {Leibetseder, Andreas and Schöffmann, Klaus}, title = {{Extracting and Using Medical Expert Knowledge to Advance in Video Processing for Gynecologic Endoscopy}}, booktitle = {ICMR '18 Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval}, year = {2018}, address = {New York, NY}, month = {Juni}, publisher = {ACM Digital Library}, abstract = {Modern day endoscopic technology enables medical staff to conveniently document surgeries via recording raw treatment footage, which can be utilized for planning further proceedings, future case revisitations or even educational purposes. However, the prospect of manually perusing recorded media files constitutes a tedious additional workload on physicians' already packed timetables and therefore ultimately represents a burden rather than a benefit. The aim of this PhD project is to improve upon this situation by closely collaborating with medical experts in order to devise datasets and systems to facilitate semi-automatic post-surgical media processing.}, doi = {10.1145/3206025.3206082}, url = {https://dl.acm.org/citation.cfm?doid=3206025.3206082} } @InProceedings{Leibetseder2018b, title = {Lapgyn4: a dataset for 4 automatic content analysis problems in the domain of laparoscopic gynecology}, author = {Andreas Leibetseder and Stefan Petscharnig and Manfred Jürgen Primus and Sabrina Kletz and Bernd Münzer and Klaus Schöffmann and Jörg Keckstein}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {357--362}, publisher = {ACM Press}, abstract = {Modern imaging technology enables medical practitioners to perform minimally invasive surgery (MIS), i.e. a variety of medical interventions inflicting minimal trauma upon patients, hence, greatly improving their recoveries. Not only patients but also surgeons can benefit from this technology, as recorded media can be utilized for speeding-up tedious and time-consuming tasks such as treatment planning or case documentation. In order to improve the predominantly manually conducted process of analyzing said media, with this work we publish four datasets extracted from gynecologic, laparoscopic interventions with the intend on encouraging research in the field of post-surgical automatic media analysis. These datasets are designed with the following use cases in mind: medical image retrieval based on a query image, detection of instrument counts, surgical actions and anatomical structures, as well as distinguishing on which anatomical structure a certain action is performed. Furthermore, we provide suggestions for evaluation metrics and first baseline experiments.}, doi = {10.1145/3204949.3208127}, url = {https://dl.acm.org/citation.cfm?id=3208127} } @InProceedings{Leibetseder2018a, title = {Sketch-Based Similarity Search for Collaborative Feature Maps}, author = {Andreas Leibetseder and Sabrina Kletz and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 2)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Supavadee Aramvith and Noel E. O´Connor and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {425--430}, publisher = {Springer}, series = {LNCS}, volume = {10705}, abstract = {Past editions of the annual Video Browser Showdown (VBS) event have brought forward many tools targeting a diverse amount of techniques for interactive video search, among which sketch-based search showed promising results. Aiming at exploring this direction further, we present a custom approach for tackling the problem of finding similarities in the TRECVID IACC.3 dataset via hand-drawn pictures using color compositions together with contour matching. The proposed methodology is integrated into the established Collaborative Feature Maps (CFM) system, which has first been utilized in the VBS 2017 challenge.}, doi = {10.1007/978-3-319-73600-6_45}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73600-6_45} } @InProceedings{Leibetseder2018, title = {Automatic Smoke Classification in Endoscopic Video}, author = {Andreas Leibetseder and Manfred Jürgen Primus and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 2)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Supavadee Aramvith and Noel E. O´Connor and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {362--366}, publisher = {Springer}, series = {LNCS}, volume = {10705}, abstract = {Medical smoke evacuation systems enable proper, filtered removal of toxic fumes during surgery, while stabilizing internal pressure during endoscopic interventions. Typically activated manually, they, however, are prone to inefficient utilization: tardy activation enables smoke to interfere with ongoing surgeries and late deactivation wastes precious resources. In order to address such issues, in this work we demonstrate a vision-based tool indicating endoscopic smoke – a first step towards automatic activation of said systems and avoiding human misconduct. In the back-end we employ a pre-trained convolutional neural network (CNN) model for distinguishing images containing smoke from others.}, doi = {10.1007/978-3-319-73600-6_33}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73600-6_33} } @InProceedings{Kletz2018, title = {Evaluation of Visual Content Descriptors for Supporting Ad-Hoc Video Search Tasks at the Video Browser Showdown}, author = {Sabrina Kletz and Andreas Leibetseder and Klaus Schöffmann}, booktitle = {MultiMedia Modeling - 24th International Conference, MMM 2018 (Part 1)}, year = {2018}, address = {Berlin}, editor = {Klaus Schöffmann and Thanarat H. Chalidabhongse and Chong-Wah Ngo and Noel E. O´Connor and Supavadee Aramvith and Yo-Sung Ho and Moncef Gabbouj and Ahmed Elgammal}, month = {Januar}, pages = {203--215}, publisher = {Springer}, series = {LNCS}, volume = {10704}, abstract = {Since 2017 the Video Browser Showdown (VBS) collaborates with TRECVID and interactively evaluates Ad-Hoc Video Search (AVS) tasks, in addition to Known-Item Search (KIS) tasks. In this video search competition the participants have to find relevant target scenes to a given textual query within a specific time limit, in a large dataset consisting of 600 h of video content. Since usually the number of relevant scenes for such an AVS query is rather high, the teams at the VBS 2017 could find only a small portion of them. One way to support them at the interactive search would be to automatically retrieve other similar instances of an already found target scene. However, it is unclear which content descriptors should be used for such an automatic video content search, using a query-by-example approach. Therefore, in this paper we investigate several different visual content descriptors (CNN Features, CEDD, COMO, HOG, Feature Signatures and HOF) for the purpose of similarity search in the TRECVID IACC.3 dataset, used for the VBS. Our evaluation shows that there is no single descriptor that works best for every AVS query, however, when considering the total performance over all 30 AVS tasks of TRECVID 2016, CNN features provide the best performance.}, doi = {10.1007/978-3-319-73603-7_17}, url = {https://link.springer.com/chapter/10.1007/978-3-319-73603-7_17} } @InProceedings{Kimovski2018, author = {Kimovski, Dragi and Ijaz, Humaira and Saurabh, Nishant and Prodan, Radu}, title = {An Adaptive Nature-inspired Fog Architecture}, booktitle = {2018 IEEE 2nd International Conference on Fog and Edge Computing (ICFEC 2018)}, year = {2018}, address = {Piscataway (NJ)}, month = {Mai}, publisher = {IEEE}, abstract = {During the last decade, Cloud computing has efficiently exploited the economyof scale by providing low cost computational and storage resources over theInternet, eventually leading to consolidation of computing resources into largedata centers. However, the nascent of the highly decentralized Internet ofThings (IoT) technologies that cannot effectively utilize the centralized Cloudinfrastructures pushes computing towards resource dispersion. Fog computingextends the Cloud paradigm by enabling dispersion of the computational andstorage resources at the edge of the network in a close proximity to where thedata is generated. In its essence, Fog computing facilitates the operation ofthe limited compute, storage and networking resources physically located closeto the edge devices. However, the shared complexity of the Fog and theinfluence of the recent IoT trends moving towards deploying and interconnectingextremely large sets of pervasive devices and sensors, requires exploration ofadaptive Fog architectural approaches capable of adapting and scaling inresponse to the unpredictable load patterns of the distributed IoTapplications. In this paper we introduce a promising new nature-inspired Fogarchitecture, named SmartFog, capable of providing low decision making latencyand adaptive resource management. By utilizing novel algorithms and techniquesfrom the fields of multi-criteria decision making, graph theory and machinelearning we model the Fog as a distributed intelligent processing system,therefore emulating the function of the human brain.}, doi = {10.1109/CFEC.2018.8358723}, url = {https://ieeexplore.ieee.org/document/8358723/} } @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} } @InProceedings{Ionescu2018, author = {Ionescu, Bogdan and Müller, Henning and Villegas, Mauricio and de Herrera, Aöna Garcoa Secp and Eickhoff, Carsten and Andrearczyk, Vincent and Dicente Cid, Yashin and Liauchuk, Vitali and Kovalev, Vassili and Hasan, Sadid H. and Ling, Yuan and Farri, Oladimeji and Liu, Joey and Lungren, Matthew and Dang-Nguyen, Duc-Tien and Piras, Luca and Riegler, Michael and Zhou, Liting and Lux, Mathias and Gurrin, Cathal}, title = {{Overview of ImageCLEF 2018: Challenges, Datasets and Evaluation}}, booktitle = {Experimental IR Meets Multilinguality, Multimodality, and Interaction}, year = {2018}, volume = {11018}, series = {LNCS}, address = {Berlin}, month = {August}, publisher = {Springer}, abstract = {This paper presents an overview of the ImageCLEF 2018 evaluation campaign, an event that was organized as part of the CLEF (Conference and Labs of the Evaluation Forum) Labs 2018. ImageCLEF is an ongoing initiative (it started in 2003) that promotes the evaluation of technologies for annotation, indexing and retrieval with the aim of providing information access to collections of images in various usage scenarios and domains. In 2018, the 16th edition of ImageCLEF ran three main tasks and a pilot task: (1) a caption prediction task that aims at predicting the caption of a figure from the biomedical literature based only on the figure image; (2) a tuberculosis task that aims at detecting the tuberculosis type, severity and drug resistance from CT (Computed Tomography) volumes of the lung; (3) a LifeLog task (videos, images and other sources) about daily activities understanding and moment retrieval, and (4) a pilot task on visual question answering where systems are tasked with answering medical questions. The strong participation, with over 100 research groups registering and 31 submitting results for the tasks, shows an increasing interest in this benchmarking campaign.}, doi = {10.1007/978-3-319-98932-7_28}, url = {https://link.springer.com/chapter/10.1007/978-3-319-98932-7_28} } @InProceedings{Hossfeld2018, author = {Hossfeld, Tobias and Timmerer, Christian}, title = {{Quality of experience column: an introduction}}, booktitle = {ACM SIGMultimedia Records}, year = {2018}, volume = {10}, address = {New York (NY)}, month = {September}, publisher = {ACM Press}, abstract = {Research on Quality of Experience (QoE) has advanced significantly in recent years and attracts attention from various stakeholders. Different facets have been addressed by the research community like subjective user studies to identify QoE influence factors for particular applications like video streaming, QoE models to capture the effects of those influence factors on concrete applications, QoE monitoring approaches at the end user site but also within the network to assess QoE during service consumption and to provide means for QoE management for improved QoE. However, in order to progress in the area of QoE, new research directions have to be taken. The application of QoE in practice needs to consider the entire QoE eco-system and the stakeholders along the service delivery chain to the end user.}, doi = {10.1145/3300001.3300011}, url = {https://dl.acm.org/citation.cfm?id=3300011} } @InProceedings{Hosseini2018, title = {Dynamic Adaptive Point Cloud Streaming}, author = {Hosseini, Mohammad and Timmerer, Christian}, booktitle = {PV '18 Proceedings of the 23rd Packet Video Workshop}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {25--30}, publisher = {ACM Press}, abstract = {High-quality point clouds have recently gained interest as an emerging form of representing immersive 3D graphics. Unfortunately, these 3D media are bulky and severely bandwidth intensive, which makes it difficult for streaming to resource-limited and mobile devices. This has called researchers to propose efficient and adaptive approaches for streaming of high-quality point clouds.In this paper, we run a pilot study towards dynamic adaptive point cloud streaming, and extend the concept of dynamic adaptive streaming over HTTP (DASH) towards DASH-PC, a dynamic adaptive bandwidth-efficient and view-aware point cloud streaming system. DASH-PC can tackle the huge bandwidth demands of dense point cloud streaming while at the same time can semantically link to human visual acuity to maintain high visual quality when needed. In order to describe the various quality representations, we propose multiple thinning approaches to spatially sub-sample point clouds in the 3D space, and design a DASH Media Presentation Description manifest speci.c for point cloud streaming. Our initial evaluations show that we can achieve signi.cant bandwidth and performance improvement on dense point cloud streaming with minor negative quality impacts compared to the baseline scenario when no adaptations is applied.}, doi = {10.1145/3210424.3210429}, url = {https://dl.acm.org/citation.cfm?id=3210429} } @InProceedings{Hicks2018a, title = {Comprehensible reasoning and automated reporting of medical examinations based on deep learning analysis}, author = {Steven Alexander Hicks and Konstantin Pogorelov and Thomas de Lange and Mathias Lux and Mattis Jeppsson and Kristin Ranheim Randel and Sigrun L. Eskeland and Pal Halvorsen and Michael Riegler}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {490--493}, publisher = {ACM Press}, abstract = {In the future, medical doctors will to an increasing degree be assisted by deep learning neural networks for disease detection during examinations of patients. In order to make qualified decisions, the black box of deep learning must be opened to increase the understanding of the reasoning behind the decision of the machine learning system. Furthermore, preparing reports after the examinations is a significant part of a doctors work-day, but if we already have a system dissecting the neural network for understanding, the same tool can be used for automatic report generation. In this demo, we describe a system that analyses medical videos from the gastrointestinal tract. Our system dissects the Tensorflow-based neural network to provide insights into the analysis and uses the resulting classification and rationale behind the classification to automatically generate an examination report for the patient's medical journal.}, doi = {10.1145/3204949.3208113}, url = {https://dl.acm.org/citation.cfm?id=3208113} } @InProceedings{Hicks2018, title = {Mimir: an automatic reporting and reasoning system for deep learning based analysis in the medical domain}, author = {Steven Alexander Hicks and Sigrun L. Eskeland and Mathias Lux and Thomas de Lange and Kristin Ranheim Randel and Mattis Jeppsson and Konstantin Pogorelov and Pal Halvorsen and Michael Riegler}, booktitle = {MMSys '18 Proceedings of the 9th ACM Multimedia Systems Conference}, year = {2018}, address = {New York (NY)}, month = {Juni}, pages = {369--374}, publisher = {ACM Press}, abstract = {Automatic detection of diseases is a growing field of interest, and machine learning in form of deep learning neural networks are frequently explored as a potential tool for the medical video analysis. To both improve the "black box"-understanding and assist in the administrative duties of writing an examination report, we release an automated multimedia reporting software dissecting the neural network to learn the intermediate analysis steps, i.e., we are adding a new level of understanding and explainability by looking into the deep learning algorithms decision processes. The presented open-source software can be used for easy retrieval and reuse of data for automatic report generation, comparisons, teaching and research. As an example, we use live colonoscopy as a use case which is the gold standard examination of the large bowel, commonly performed for clinical and screening purposes. The added information has potentially a large value, and reuse of the data for the automatic reporting may potentially save the doctors large amounts of time.}, doi = {10.1145/3204949.3208129}, url = {https://dl.acm.org/citation.cfm?id=3208129} } @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} } @InProceedings{Dang-Nguyen2018a, author = {Dang-Nguyen, Duc-Tien and Schöffmann, Klaus and Hürst, Wolfgang}, title = {{LSE2018 Panel - Challenges of Lifelog Search and Access}}, booktitle = {LSC '18 Proceedings of the 2018 ACM Workshop on The Lifelog Search Challenge}, year = {2018}, address = {New York, NY}, month = {Juni}, publisher = {ACM Digital Library}, abstract = {Lifelogging is becoming an increasingly important topic of research and this paper highlights the thoughts of the three panelists at the LSC - Lifelog Search Challenge at ICMR 2018 in Yokohama, Japan on June 11, 2018. The thoughts cover important topics such as the need for challenges in multimedia access, the need for a better user interface and the challenges in building datasets and organising benchmarking activities such as the LSC.}, doi = {10.1145/3210539.3210540}, url = {https://dl.acm.org/citation.cfm?id=3210540} } @InProceedings{Dang-Nguyen2018, author = {Dang-Nguyen, Duc-Tien and Piras, Luca and Riegler, Michael and Zhou, Liting and Lux, Mathias and Gurrin, Cathal}, title = {{Overview of ImageCLEFlifelog 2018: Daily Living Understanding andL ifelog Moment Retrieval}}, booktitle = {CLEF 2018 Working Notes}, year = {2018}, volume = {2125}, month = {September}, publisher = {CEUR-Workshop Proceedings}, abstract = {Benchmarking in Multimedia and Retrieval related researchelds has a long tradition and important position within the community.Benchmarks such as the MediaEval Multimedia Benchmark or CLEFare well established and also served by the community. One major goalof these competitions beside of comparing dierent methods and approachesis also to create or promote new interesting research directionswithin multimedia. For example the Medico task at MediaEval with thegoal of medical related multimedia analysis. Although lifelogging createsa lot of attention in the community which is shown by several workshopsand special session hosted about the topic. Despite of that there exist alsosome lifelogging related benchmarks. For example the previous editionof the lifelogging task at ImageCLEF. The last years ImageCLEFlifelogtask was well received but had some barriers that made it dicult forsome researchers to participate (data size, multi modal features, etc.) TheImageCLEFlifelog 2018 tries to overcome these problems and make thetask accessible for an even broader audience (e.g., pre-extracted featuresare provided). Furthermore, the task is divided into two subtasks (challenges).The two challenges are lifelog moment retrieval (LMRT) and theActivities of Daily Living understanding (ADLT). All in all seven teamsparticipated with a total number of 41 runs which was an signicantincrease compared to the previous year.}, url = {http://ceur-ws.org/Vol-2125/} } @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} }