[452] | Daniela Pohl, Abdelhamid Bouchachia, Hermann Hellwagner, Automatic Identification of Crisis-Related Sub-Events using Clustering, In 11th International Conference on Machine Learning and Applications (Jiawei Han, Taghi M Khoshgoftaar, Xingquan Zhu, eds.), IEEE, Los Alamitos, CA, USA, pp. 333-338, 2012.
[bib][url] [pdf] [abstract]
Abstract: Social media are becoming an important instrument for supporting crisis management, due to their broad acceptance and the intensive usage of mobile devices for accessing them. Social platforms facilitate collaboration among the public during a crisis and also support after-the-fact analysis. Thus, social media are useful for the processes of understanding, learning, and decision making. In particular, having information from social networks in a suitable, ideally summarized, form can speed up such processes. The present study relies on Flickr and YouTube as social media and aims at automatically identifying individual sub-events within a crisis situation. The study applies a two-phase clustering approach to detect those sub-events. The first phase uses geo-referenced data to locate a sub-event, while the second phase uses the natural language descriptions of pictures and videos to further identify the ”what-about” of those sub-events. The results show high potential of this social media-based clustering approach for detecting crisis-related sub-events.
|
[451] | Daniela Pohl, Abdelhamid Bouchachia, Hermann Hellwagner, Supporting Crisis Management via Sub-Event Detection in Social Networks, In IEEE 21st International Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE) (Michel Diaz, Patrick Senac, eds.), IEEE, Toulouse, Fance, pp. 373 -378, 2012.
[bib] [doi] [abstract]
Abstract: Social networks give the opportunity to gather and share knowledge about a situation of relevance. This so called user-generated content is getting increasingly important during crisis management. It facilitates the collaboration with citizens or parties involved from the very beginning of the crisis. The information captured in form of images, text or videos is a valuable source of identifying sub-events of a crisis. In this study, we use metadata of images and videos collected from Flickr and YouTube to extract sub-events in crisis situations. We investigate the suitability of clustering techniques to detect sub-events. In particular two algorithms are evaluated on several data sets related to crisis situations. The results show the high potential of the approach proposed.
|
[450] | Daniela Pohl, Abdelhamid Bouchachia, Hermann Hellwagner, Automatic Sub-Event Detection in Emergency Management using Social Media, In Proceedings of the 21st International Conference Companion on World Wide Web (Alain Mille, Fabien Gandon, Jacques Misselis, eds.), ACM, New York, NY, USA, pp. 683-686, 2012.
[bib] [pdf] [abstract]
Abstract: Emergency management is about assessing critical situations, followed by decision making as a key step. Clearly, information is crucial in this two-step process. The technology of social (multi)media turns out to be an interesting source for collecting information about an emergency situation. In particular, situational information can be captured in form of pictures, videos, or text messages. The present paper investigates the application of multimedia metadata to identify the set of sub-events related to an emergency situation. The used metadata is compiled from Flickr and YouTube during an emergency situation, where the identification of the events relies on clustering. Initial results presented in this paper show how social media data can be used to detect different sub-events in a critical situation.
|
[449] | Alexander Müller, Mathias Lux, Laszlo Böszörmenyi, The video summary GWAP: summarization of videos based on a social game, In Proceedings of the 12th International Conference on Knowledge Management and Knowledge Technologies (Stefanie Lindstaedt, Michael Granitzer, eds.), ACM, New York, NY, USA, pp. 15:1-15:7, 2012.
[bib][url] [doi] |
[448] | Bernd Münzer, Klaus Schoeffmann, Laszlo Böszörmenyi, Detection of Circular Content Area in Endoscopic Videos for Efficient Encoding and Improved Content Analysis, Technical report, Institute of Information Technology (ITEC), Klagenfurt University, no. TR/ITEC/12/2.03, Klagenfurt, Austria, pp. 20, 2012.
[bib] [pdf] [abstract]
Abstract: The actual content of endoscopic videos is typically limited to a circular area in the center of the image due to the inherent characteristics of the camera. This area is surrounded by a dark border that fills up the remainder of the rectangular image and is subject to noise. The position and size of the circle is not standardized and usually varies over time. In this paper a robust algorithm is presented that (1) classifies which parts of an endoscopic video feature a circular content area and (2) determines its exact position and size, if present. This information is useful for improving video encoding efficiency, limiting further analysis steps to the relevant area and saving ink when printing still images on findings. Our evaluation shows that the proposed method is very fast, reliable and robust. Moreover, it indicates that by exploiting this information for video encoding a considerable bitrate reduction is possible with the same visual quality.
|
[447] | Christopher Mueller, Martin Smole, Klaus Schoeffmann, A Demonstration of A Hierarchical Multi-Layout 3D Video Browser, In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME 2012) (Jian Zhang, Dan Schonfeld, David Dagan Feng, Jianfei Cai Nanyang, Alan Hanjalic, Enrico Magli, Mark Pickering, Gerald Friedland, Xian-Sheng Hua, eds.), IEEE Computer Society, Los Alamitos, CA, USA, pp. 665, 2012.
[bib] [pdf] [abstract]
Abstract: This paper demonstrates a novel 3D Video Browser (3VB) that enables interactive search within a single video as well as video collections by utilizing 3D projection and an intuitive interaction. The browsing approach is based on hierarchical search, which means that the user can split a video into several segments. The 3VB disposes a convenient interface that allows flexible arrangement of video segments in the 3D space. It allows for concurrent playback of video segments and flexible inspection of these segments at any desired level of detail through convenient user interaction.
|
[446] | Christopher Mueller, Daniele Renzi, Stefan Lederer, Stefano Battista, Christian Timmerer, Using Scalable Video Coding for Dynamic Adaptive Streaming over HTTP in Mobile Environments, In Proceedings of the 20th European Signal Processing Conference (EUSIPCO12) (Corneliu Burileanu, Béatrice Pesquet-Popescu, eds.), European Signal Processing (EURASIP) Society, Bucharest, Romania, pp. 2208-2212, 2012.
[bib] [pdf] [abstract]
Abstract: Dynamic Adaptive Streaming over HTTP (DASH) is a convenient approach to transfer videos in an adaptive and dynamic way to the user. As a consequence, this system provides high bandwidth flexibility and is especially suitable for mobile use cases where the bandwidth variations are tremendous. In this paper we have integrated the Scalable Video Coding (SVC) extensions of the Advanced Video Coding (AVC) standard into the recently ratified MPEG-DASH standard. Furthermore, we have evaluated our solution under restricted conditions using bandwidth traces from mobile environments and compared it with an improved version of our MPEG-DASH implementation using AVC as well as major industry solutions.
|
[445] | Christopher Mueller, Stefan Lederer, Christian Timmerer, An Evaluation of Dynamic Adaptive Streaming over HTTP in Vehicular Environments, In Proceedings of the Fourth Annual ACM SIGMM Workshop on Mobile Video (MoVid12) (Mohamed Hefeeda, Cheng-Hsin Hsu, Mainak Chatterjee, Nalini Venkatasubramanian, Samrat Ganguly, eds.), ACM, New York, NY, USA, pp. 37-42, 2012.
[bib] [pdf] [abstract]
Abstract: MPEGs' Dynamic Adaptive Streaming over HTTP (MPEG-DASH) is an emerging standard designed for media delivery over the top of existing infrastructures and able to handle varying bandwidth conditions during a streaming session. This requirement is very important, specifically within mobile environments and, thus, DASH could potentially become a major driver for mobile multimedia streaming. Hence, this paper provides a detailed evaluation of our implementation of MPEG DASH compared to the most popular propriety systems, i.e., Microsoft Smooth Steaming, Adobe HTTP Dynamic Streaming, and Apple HTTP Live Streaming. In particular, these systems will be evaluated under restricted conditions which are due to vehicular mobility. In anticipation of the results, our prototype implementation of MPEG-DASH can very well compete with state-of-the-art solutions and, thus, can be regarded as a mature standard ready for industry adaption.
|
[444] | Christopher Mueller, Stefan Lederer, Christian Timmerer, A Proxy Effect Analysis and Fair Adaptation Algorithm for Multiple Competing Dynamic Adaptive Streaming over HTTP Clients, In Proceedings of the IEEE Conference on Visual Communications and Image Processing Conference (VCIP 2012) (Kiyoharu Aizawa, Jay Kuo, Zicheng Liu, eds.), IEEE, San Diego, CA, USA, pp. 6, 2012.
[bib][url] [pdf] [abstract]
Abstract: Multimedia streaming technologies based on the Hypertext Transfer Protocol (HTTP) are very popular and used by many content providers such as Netflix, Hulu, and Vudu. Recently, ISO/IEC MPEG has ratified Dynamic Adaptive Streaming over HTTP (DASH) which extends the traditional HTTP streaming with an adaptive component addressing the issue of varying bandwidth conditions that users are facing in networks based on the Internet Protocol (IP). Additionally, industry has already deployed several solutions based on such an approach which simplifies large scale deployment because the whole streaming logic is located at the client. However, these features may introduce drawbacks when multiple clients compete for a network bottleneck due to the fact that the clients are not aware of the network infrastructure such as proxies or other clients. This paper identifies these negative effects and the evaluation thereof using MPEG-DASH and Microsoft Smooth Streaming. Furthermore, we propose a novel adaptation algorithm introducing the concept of fairness regarding a cluster of clients. In anticipation of the results we can conclude that we achieve more efficient bottleneck bandwidth utilization and less quality switches.
|
[443] | Stefan Lederer, Christopher Mueller, Christian Timmerer, Dynamic Adaptive Streaming over HTTP Dataset, In Proceedings of the Third Annual ACM SIGMM Conference on Multimedia Systems (MMSys12) (Mark Claypool, Carsten Griwodz, Ketan Mayer-Patel, eds.), ACM, New York, NY, USA, pp. 89-94, 2012.
[bib] [pdf] [abstract]
Abstract: Adaptive HTTP streaming got lot of attention in recent years and with dynamic adaptive streaming over HTTP (DASH) a standard is available. Many papers cover this topic and present their research results, but unfortunately all of them use their own private dataset which – in most cases – is not publicly available. Hence, it is difficult to compare, e.g., adaptation algorithms in an objective way due to the lack of a common dataset which shall be used as basis for such experiments. In this paper, we present our DASH dataset featuring our DASHEncoder, an open source DASH content generation tool. We also provide basic evaluations of the different segment lengths, the influence of HTTP server settings, and, in this context, we show some of the advantages as well as problems of shorter segment lengths.
|
[442] | Dejan Milojicic, Martin Arlitt, Doree Duncan Seligmann, George Thiruvathukal, Christian Timmerer, Innovation Mashups: Academic Rigor Meets Social Networking Buzz, In Computer, IEEE Computer Society, vol. 45, no. 9, Los Alamitos, CA, USA, pp. 101-105, 2012.
[bib] [doi] [pdf] [abstract]
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.
|
[441] | Oge Marques, Mathias Lux, Visual information retrieval using Java and LIRE, In Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval (William Hersh, Jamie Callan, Yoelle Maarek, Mark Sanderson, eds.), ACM, New York, NY, USA, pp. 1193-1193, 2012.
[bib][url] [doi] |
[440] | Mathias Lux, Mario Taschwer, Oge Marques, Classification of photos based on good feelings: ACM MM 2012 multimedia grand challenge submission, In Proceedings of the 20th ACM international conference on Multimedia (Kiyoharu Aizawa, Noboru Babaguchi, John Smith, eds.), ACM, New York, NY, USA, pp. 1367-1368, 2012.
[bib][url] [doi] |
[439] | Mathias Lux, Mario Taschwer, Oge Marques, A closer look at photographers' intentions: a test dataset, In Proceedings of the ACM multimedia 2012 workshop on Crowdsourcing for multimedia (Kiyoharu Aizawa, Noboru Babaguchi, John Smith, eds.), ACM, New York, NY, USA, pp. 17-18, 2012.
[bib][url] [doi] |
[438] | Mathias Lux, Mario Guggenberger, Alexander Müller, Finding Image Regions with Human Computation and Games with a Purpose, In Proceedings of the Eighth Artificial Intelligence and Interactive Digital Entertainment International Conference (AIIDE 2012) (Mark Riedl, Gita Sukthankar, eds.), Association for the Advancement of Artificial Intelligence (AAAI Press), Palo Alto, California, USA, pp. 220, 2012.
[bib][url] [abstract]
Abstract: Manual image annotation is a tedious and time-consuming task, while automated methods are error prone and limited in their results. Human computation, and especially games with a purpose, have shown potential to create high quality annotations by "hiding the complexity" of the actual annotation task and employing the "wisdom of the crowds". In this demo paper we present two games with a single purpose: finding regions in images that correspond to given terms. We discuss approach, implementation, and preliminary results of our work and give an outlook to immediate future work.
|
[437] | Yaning Liu, Joost Geurts, Benjamin Rainer, Stefan Lederer, Christopher Mueller, Christian Timmerer, DASH over CCN: A CCN use-case for a Social Media based collaborative project, In CCNx Community Meeting (CCNxConn 2012) (Giovanna Carofiglio, ed.), Parc, Sophia Antipolis, pp. 1-1, 2012.
[bib][url] [pdf] |
[436] | Stefan Lederer, Christopher Mueller, Benjamin Rainer, Markus Waltl, Christian Timmerer, An open source MPEG DASH evaluation suite, In Proceedings of the IEEE Conference on Visual Communications and Image Processing Conference (VCIP 2012) (Ebroul Izquierdo, Xin Wang, eds.), IEEE, San Diego, CA, USA, pp. 1-1, 2012.
[bib][url] [pdf] [abstract]
Abstract: In this paper we demonstrate our MPEG-DASH evaluation suite, which comprises several components on the client side as well as on the server side. The major client components are the VLC DASH plugin, libDASH, and DASH-JS, a JavaScript-based DASH client. These tools enable performance tests on various platforms, e.g., Windows and Linux as well as mobile platforms such as Android. Moreover, due to their flexible structure it is possible to integrate adaptation logics and evaluate them under consistent conditions. On the server side we provide the content generation tool DASHEncoder, our MPEG-DASH datasets well as the MPEG-DASH conformance validator.
|
[435] | Stefan Lederer, Christopher Mueller, Christian Timmerer, Towards Peer-Assisted Dynamic Adaptive Streaming over HTTP, In Proceedings of the 19th International Packet Video Workshop (PV 2012) (Christine Guillemot, Jacob Chakareski, Eckehard Steinbach, eds.), IEEE, Munich, Germany, pp. 1-6, 2012.
[bib] [pdf] [abstract]
Abstract: This paper presents our peer-assisted Dynamic Adaptive Streaming over HTTP (pDASH) proposal as well as an evaluation based on our DASH simulation environment in comparison to conventional approaches, i.e., non-peer-assisted DASH. Our approach maintains the standard conformance to MPEG-DASH enabling an easy and straightforward way of enhancing a streaming system with peer assistance to reduce the bandwidth and infrastructure requirements of the content/service provider. In anticipation of the results our system achieves a bandwidth reduction of Content Distribution Networks (CDN) and as a consequence the corresponding infrastructure costs of the content/service providers by up to 25% by leveraging the upstream capacity of neighboring peers. Furthermore, the cost savings have been evaluated using a cost model that is based on the current Amazon CloudFront pricing scheme. Furthermore, we have also evaluated the performance impact that various combinations of quality levels of the content could have in a peer-assisted streaming system as well as the client behavior in such an environment.
|
[434] | Robert Kuschnig, Evsen Yanmaz, Ingo Kofler, Bernhard Rinner, Hermann Hellwagner, Profiling IEEE 802.11 Performance on Linux-based UAVs, In Proceedings of the Austrian Robotics Workshop (ARW-12) (Suzana Uran Gerald Steinbauer, ed.), Graz University of Technology, Graz, Austria, pp. 6, 2012.
[bib] [pdf] |
[433] | Robert Kuschnig, Congestion-Aware Quality-Adaptive Streaming of Scalable Video, PhD thesis, Klagenfurt University, pp. 186, 2012.
[bib] [pdf] [abstract]
Abstract: Internet video streaming is a hot topic in multimedia systems. A large variety of devices (computers, mobile phones, TVs, etc.) are connected to the Internet via wired or wireless networks and are capable of receiving and decoding HD video content. To enable new services like HD video streaming (e.g., online video rental), the Internet’s infrastructure was enhanced. But the Internet is still a best-effort network, which does not implement quality-of-service or admission control, resulting in time-varying bandwidth and packet delay, packet loss and network congestion. Because video streaming accounts for a considerable amount of the Internet’s traffic, video streaming needs additionally to be congestion-aware, to avoid a congestion collapse of the Internet. The Transmission Control Protocol (TCP) can adapt to changing network conditions and is currently the de facto standard protocol for congestion-aware and reliable data transmission in the Internet. This fact gave TCP-based video streaming a huge momentum. Consequently, this thesis investigates TCP-based adaptive video streaming for the Internet. The main goal is to provide a solution for congestion-aware video streaming, while still being able to achieve a reasonable performance in error-prone networks. To complement existing work on congestion-aware adaptive streaming, this thesis makes six contributions. (1) The baseline performance of TCP-based adaptive streaming is identified by means of an evaluation of different adaptive streaming approaches. The results represent a reference for further investigations. (2) An investigation on the influence of TCP’s behavior in presence of packet loss on the video streaming performance. (3) To overcome the shortcomings of TCP-based video streaming (single TCP connections fail to deliver a good performance in case of packet loss), a new approach to video streaming based on multiple request-response streams was introduced. The novelty of this system is that it is able to make use of multiple HTTP-based request-response streams while still providing TCP-friendliness. (4) A performance model of the HTTP-based request-response streams was developed, to estimate the influence of the system parameters and the network characteristics on the throughput performance. (5) A comprehensive evaluation of the HTTP-based request-response streams under diverse network conditions was conducted, to validate the model’s estimations. Additionally, the TCP-friendliness was evaluated, showing that request-response streaming systems can be configured to achieve TCP-friendliness. (6) A cellular network with high bandwidth fluctuations and RTTs was used to investigate the performance of the request-response streaming system in a mobile video streaming scenario. The results indicate that the streaming system can make good use of the available bandwidth, while the number of quality switches is kept low. While aggregating multiple TCP connections to improve the TCP streaming performance is quite common, usually the improvement comes at the cost of high deployment effort. By placing the streaming logic at the client, request-response streams can avoid this complexity. Additionally, this client-driven approach responds faster to changing network conditions and enables easy recovery from connection stalls or aborts, because the control loop is at the client. To improve the network efficiency and the scalability in terms of number of clients served, HTTP-based request-response streams can utilize HTTP proxies and caches.
|
[432] | Marian Kogler, Mathias Lux, Robust image retrieval using bag of visual words with fuzzy codebooks and fuzzy assignment, In i-KNOW '12 Proceedings of the 12th International Conference on Knowledge Management and Knowledge Technologies (Stefanie Lindstaedt, ed.), ACM, New York, NY, USA, pp. 34.1 - 34.4, 2012.
[bib][url] [doi] [abstract]
Abstract: Content-based retrieval systems leverage low level features such as color, texture or local information of images to find similar images to a respective query image. In recent years the Bag of Visual Words (BoVW) approach, which relies on quantized visual information around local image patches, has gained importance in image retrieval. In this paper we focus on fuzzy algorithms, in order to improve the descriptiveness of image descriptors. We extend the BoVW approach by applying fuzzy clustering and fuzzy assignment to take a step towards more effective visual descriptors, which are matched against each other in content-based similarity searches.
|
[431] | Ingo Kofler, Robert Kuschnig, Hermann Hellwagner, Implications of the ISO Base Media File Format on Adaptive HTTP Streaming of H.264/SVC, In Proceedings of the 9th IEEE Consumer Communications and Networking Conference (CCNC) (Behrooz Shirazi, ed.), IEEE, Los Alamitos, CA, USA, pp. 5, 2012.
[bib][url] [pdf] [abstract]
Abstract: HTTP streaming has gained significant attraction in the last few years. Currently many commercial as well as standardized streaming systems are already offering adaptive streaming. In most cases, the adaptation is achieved by switching between separately encoded video streams in different qualities. In contrast to that, this paper focuses on the applicability of scalable video coding based on the H.264/SVC standard for adaptive HTTP streaming. Recent work has already highlighted the conceptual advantages like better cache utilization, fine-grained bit rate scalability, and lower storage requirements. This paper discusses the actual realization and design options for implementing priority streaming using the ISO Base Media File Format (BMFF). We propose three different strategies for organizing the scalable video bit stream that consider both the possibilities as well as limitations of the ISO BMFF. The proposed strategies are discussed and evaluated both conceptually and quantitatively. For that purpose, we provide a detailed analysis based on modeling both the overhead of the file format and the HTTP encapsulation. The results for all three priority streaming strategies show that the limitations of the ISO BMFF result in a high relative overhead in the case of low bit rate content. However, when applied to high quality content, priority streaming of H.264/SVC can be implemented at a very low cost. Depending on the number of layers and the offered scalability dimensions, different strategies should be chosen to minimize the overhead. Based on the analytical model and the discussion, this paper provides guidance for selecting the most efficient strategy.
|
[430] | Tobias Hoßfeld, Raimund Schatz, Martin Varela, Christian Timmerer, Challenges of QoE Management for Cloud Applications, In Communications Magazine, IEEE, IEEE Communications Society, vol. 50, no. 4, New York, NY, USA, pp. 28-36, 2012.
[bib] [doi] [pdf] [abstract]
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.
|
[429] | Hermann Hellwagner, Scalable Coherent Interface (SCI), Chapter in Encyclopedia of Parallel Computing (David Padua, ed.), Springer, Berlin, Heidelberg, New York, pp. 9, 2012.
[bib] [abstract]
Abstract: Scalable Coherent Interface (SCI) is the specification (standardized by ISO/IEC and the IEEE) of a high-speed, flexible, scalable, point-to-point-based interconnect technology that was implemented in various ways to couple multiple processing nodes. SCI supports both the message-passing and shared-memory communication models, the latter in either the cache-coherent or non-coherent variants. SCI can be deployed as a system area network for compute clusters, as a memory interconnect for large-scale, cache-coherent, distributed-shared-memory multiprocessors, or as an I/O subsystem interconnect.
|
[428] | Michael Grafl, Christian Timmerer, Markus Waltl, George Xilouris, Nikolaos Zotos, Daniele Renzi, Stefano Battista, Alex Chernilov, Distributed Adaptation Decision-Taking Framework and Scalable Video Coding Tunneling for Edge and In-Network Media Adaptation, In Proceedings of the 2012 IEEE International Conference on Telecommunications and Multimedia (TEMU 2012) (Evangelos Pallis, Vassilios Zacharopoulos, Anastasios Kourtis, eds.), IEEE, Los Alamitos, CA, USA, pp. 6, 2012.
[bib] [doi] [pdf] [abstract]
Abstract: Existing and future media ecosystems need to cope with the ever-increasing heterogeneity of networks, devices, and user characteristics collectively referred to as (usage) context. The key to address this problem is media adaptation to various and dynamically changing contexts in order to provide a service quality that is regarded as satisfactory by the end user. The adaptation can be performed in many ways and at different locations, e.g., at the edge and within the network resulting in a substantial number of issues to be integrated within a media ecosystem. This paper describes research challenges, key innovations, target research outcomes, and achievements so far for edge and in-network media adaptation by introducing the concept of Scalable Video Coding (SVC) tunneling.
|