Abstract: Computer Vision & Graphics and Multimedia research and practices have, and will continue, to play a center role in Cultural Heritage preservation efforts. The Second Workshop on eHeritage and Digital Art Preservation aims to bring together these researches as well as interdisciplinary researches that are related to these areas, in particular image and audio research, image and haptic (touch) research, as well as presentation of visual content over wide web and education. This workshop will follow the very successful First eHeritage Workshop which was held in conjunction with ICCV in Kyoto last year
WS07 – MiFor2010: Multimedia in Forensics, Security and Intelligence
Abstract: with the proliferation of multimedia data on the web, surveillance cameras in cities, and mobile phones in everyday life we see an enormous growth in multimedia data that needs to be secured to prevent illegal use, to be analyzed by forensic investigators to detect and reconstruct illegal activities, or be used as source of intelligence. The sheer volume of such datasets makes manual inspection of all data impossible. Tools are needed to support the investigator in their quest for relevant clues and evidence and in their strive towards preventing crime. Such tools should support the protection, management, processing, interpretation, and visualization of multimedia data in the different steps of the investigation process. The target audience of MiFor 2010 is composed of researchers working on innovative multimedia technology and representatives from companies developing tools used in forensics, security and intelligence. This workshop aims to bring the synergy needed to develop new and effective solutions to improve crime prevention and investigation in all of its steps.
WS08 – MTDL 2010: 2nd ACM Workshop on Multimedia Technologies for Distance Learning
Abstract: multimedia technologies and networking infrastructure have changed human social behavior. One typical example is education. The impact of distance learning to traditional universities in particular allows educational professionals to rethink about how to efficiently and effectively using multimedia technologies to improve instruction, as well as to encourage students to learn. Although multimedia technologies have already been used widely in e-learning, various considerations should be carefully addressed from both pedagogical and technological perspectives, to ensure the successful incorporation of these technologies in e-learning. This ACM workshop aims to discuss problems, current studies, and solutions in how to use multimedia and communication technologies to improve e-learning. Especially, presentations should address the difference between using and without using multimedia technologies in education. Practical solutions are encouraged, although pedagogical theories may be used to support the solutions.
WS09 – 3DVP 2010: ACM Workshop on 3D Video Processing
Abstract: Research on 3D video processing has gained a tremendous amount of momentum due to advances in video communications, broadcasting and entertainment technology, e.g., blockbusters like Avatar and Up. This is pushing the introduction of 3D services and the development of high- quality 3D displays in the near future. Beside the commercially interesting areas in entertainment and broadcasting, 3D video is becoming important in many other fields related to the analysis of single or multiple video streams. Examples are security and surveillance, biomechanics, human motion analysis and modelling, 3D reconstruction, indexing and retrieval as well as medical imaging. In all these fields, 3D video processing plays a key role and a large variety of challenges can be recognized. The aim of this workshop is to bring together leading experts in the field of 3D video processing from academia and industry, creating a stimulating and informative forum on recent advances in this exciting field. The topics of this workshop shall cover all aspects related to 3D video processing ranging from stereo to multi-view, image-based rendering, 3D production, real-time systems and applications.
Abstract: the use of three-dimensional (3D) image and model databases throughout the Internet is growing both in number and size. The development of modeling tools, 3D scanners, 3D graphic accelerated hardware, Web3D, and so on, is enabling access to 3D materials of high quality. The emergence of 3D media is also directly related to the emergence of the 3D acquisition technologies. Indeed, recent advances in 3D scanner acquisition and 3D graphics rendering technologies boost the creation of 3D model archives for several application domains. These include archeology, cultural heritage, computer-assisted design (CAD), medicine, 3D face recognition, videogames or bioinformatics. Thereupon, the development of efficient search mechanisms is required for the effective retrieval of 3D objects from large repositories. The purpose of this workshop is to bring together researchers interested in 3D retrieval from different fields (computer vision, computer graphics, machine learning and human-computer interaction). Its goal is to provide a state-of-the-art overview of challenges in the research on 3D retrieval. This workshop seeks original high innovative research in the area of 3D retrieval
WS03 – MML10: 3rd ACM Workshop on Machine Learning and Music
Abstract: With the current explosion and quick expansion of multimedia digital formats in general, and music digital formats in particular, research on machine learning and music is gaining increasing popularity. As complexity of the problems investigated by researchers on this area increases, there is a need to develop new algorithms and methods to solve these problems. Machine learning has proved to provide efficient solutions to many music-related problems both of academic and commercial interest. The goal of the workshop is to bring together researchers who are using machine learning in musical applications, providing the opportunity to promote, present and discuss ongoing work in the area. Research papers, case studies, lessons learned, status reports, and discussions of practical problems in machine-learning-based music processing applications are all welcome submissions.
Abstract: The SSCS 2010 workshop is a forum for presentation of recent research results concerning advances and innovation in the area of spoken content retrieval and in the area of multimedia search that makes use of automatic speech recognition technology. Spontaneous, conversational speech occurs in a wide variety of domains and the workshop is relevant for lectures, meetings, interviews, debates, conversational broadcast (e.g., talkshows), podcasts, call center recordings, cultural heritage archives, social video on the Web and spoken natural language queries. The objective of the workshop is to bring together researchers in theareas of speech recognition, audio processing, multimedia analysis and information retrieval for exchange and interaction.
WS11 – ARTEMIS2010: ACM Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams
Abstract: cognitive video supervision and event analysis in video sequences is a critical task in many multimedia applications. Methods, tools and algorithms that aim to detect and recognize high level concepts and their respective spatio-temporal and causal relations in order to identify semantic video activities, actions and procedures have been in the focus of the research community over the last years. This research area has strong impact on many real-life multimedia applications based on a semantic characterization and annotation of video streams in various domains (e.g., sports, news, documentaries, movies and surveillance), either broadcast or user-generated videos. Although a first critical issue is the estimation of quantitative parameters describing where events are detected, recent trends are facing the analysis of multimedia footage by applying image and video understanding techniques to that detected/tracked motion. That is, the challenge is becoming the generation of qualitative descriptions about the meaning of (human) motion, therefore describing not only where, but also why an event is being observed.
WS12 – AIEMPro10: 3d ACM Workshop on Automated Information Extraction in Media Production
Abstract: the third Workshop on Automated Information Extraction in Media Production (AIEMPro10) aims at fostering exchange of ideas and of practises between leading experts in research and leading actors in the media community, in order to catalyse the migration towards new ways of producing media content, aided by large scale introduction of tools for automated multimedia analysis and understanding. On the other hand, the workshop should help researchers in better understanding what are some real-life key requirements which would enable their scientific developments come into wider adoption. The workshop aims at attracting the attention of researchers and practitioners in the field of automatic information extraction based on audiovisual content analysis on the problems related with media production processes. In particular, the objective is to analyse the impact and performances of these tools in real-life applications, and on real-life material. Authors are encouraged to submit papers on which they enlighten the features of existing or novel tools in the key aspects of future media production based on automated information extraction, including acquisition, editing, publishing, archiving and repurposing of audiovisual material. The best accepted papers of AIEMPro will be considered for inclusion in a special issue of Springer’s Multimedia Tools and Applications journal.
WS04 – MoViD: ACM Workshop on Mobile Video Delivery
Abstract: the focus of this workshop is to present and discuss recent advances in wireless technologies for delivering video content to mobile users. The goal of this workshop is to deepen the understanding of research and deployment challenges in building the Next Generation Mobile Video Internet. The workshop also creates an interesting forum for discussion given the various choices we have in terms of wireless technologies and various approaches in terms of delivering video content. Specifically, the workshop intends to address the following topics: (a) Research challenges in developing new techniques for delivering rich video experience to users over existing wireless technologies; (b) New visions and concepts that will drive evolution of wireless access technologies to support high quality video content with diverse QoS requirements; (c) Deployment challenges in new video delivery models (broadcast/multicast) to mobile users, and (d) Novel mobile video applications.
WS13 – VLS-MCMR’10: ACM Workshop on Very-Large-Scale Multimedia Corpus, Mining and Retrieval
Abstract: pivotal to many tasks in relation to multimedia research and development is the availability of sufficiently large datasets and their corresponding ground truth as well as the tools for efficiently handling and managing such large datasets. Currently available datasets for multimedia research are either too small such as the Corel or Pascal datasets, too specific like the TRECVID dataset, or without ground truth, such as the several recent efforts by MIT and MSRA that gathered millions of Web images for testing. While it is relatively easy to crawl and store a huge amount of data, the creation of ground-truth necessary to systematically train, test, evaluate and compare the performance of various algorithms and systems is a major problem. For this reason, more and more research groups are individually putting efforts into the creation of such corpus in order to carry out research on large-scale dataset. There is a need to unify these individual efforts into the creation of a unified web-scale repository which would benefit the entire multimedia research community. The purpose of this workshop is to bring together researchers interested in the construction and analysis of Web Scale multimedia corpus and methodologies to mine and retrieve from them.
WS14 – MPVA 2010: ACM Workshop on Multimodal Pervasive Video Analysis
Abstract: Thanks to the confluence of urban monitoring applications and portable cameras carried by humans everywhere, video acquisition, processing, and storage systems have become an integral part of the fabric of today’s life.
Besides the classical applications such as security and surveillance, cameras have been considered for creating novel applications based on the notions of smart homes, ambient intelligence, human-computer interaction, social networks, ambient assisted living, smart seminar rooms, building emergency management, assistive technologies, and many more.
Cameras are mounted at fixed location in the urban infrastructure, or are moved around by humans or vehicles. Fusion of data between the cameras is explored as a means to enhance the interpretation task or to add confidence to the monitoring results. Such fusion can occur across different spatio-temporal levels and between subsets of fixed and mobile cameras as per the needs of the application and the availability of valuable information from each camera.
Addressing new challenges related to processing of distributed observations with a network of cameras and applications based on joint video analysis between fixed and mobile cameras will be the subjects of interest. Techniques and applications based on fixed or mobile camera systems will also be considered.
WS15 – ACM Workshop on Mobile Cloud Media Computing
Abstract: smart mobile devices such as camera phones typically will be carried by people all the time. These devices are true “multimedia” devices that acquire, process, transmit and present text, image, video and audio data using both media input (camera and other sensors) and output (screen and speaker) channels. However, due to the limitations in computation, storage, display, and camera, multimedia applications and systems have not been adequately supported on mobile devices. Recently, the rapid development along the following aspects largely mitigated these limitations: (1) Cloud computing, which solves both the bottle neck of computation and storage; (2) large and high-resolution display (more and more mobile devices are equipped with high-resolution LED); (3) 3G and WiFi, which solves the bandwidth issue; (4) high-quality cameras; (5) more informative sensors like GPS, gravity sensor, compass, etc; (6) More powerful CPU. With these developments, it is now the prime time for us to realize intelligent mobile device centered multimedia applications with the support of a cloud computing platform. In particular, the support of cloud computing platform has become an essential factor especially for scalable and connected mobile multimedia technologies, applications and systems, due to its powerful support on computation, storage and networking. The focus of this workshop is on exploring challenges and opportunities of intelligent multimedia technologies, applications and systems on mobile devices, especially when a media cloud computing platform can be appropriately leveraged.
WS16 – ACM Workshop on Advanced video streaming techniques for peer-to-peer networks and social networking
Abstract: peer-to-peer (P2P) is a promising technology for video streaming, and offers advantages in terms of robustness, reconfigurability and scalability. From the point of view of the broadcaster, the P2P approach permits to serve a larger audience without the need of proportionally increased resources. From the users’ point of view, the P2P should allow to experience high quality video in a cost effective fashion. Moreover, users themselves can act as prosumers by distributing their own contents within social networks enabling heterogeneous users to real time, TV-quality video streaming on P2P overlays. The workshop is about algorithms, issues and experiences related to P2P video streaming and social networks taking into account recent advances on multimedia coding such as scalability, resilience, cross layer optimization, network coding as well as its distribution and interaction.
The best paper award (€300) is sponsored by RADVISION.
WS17 – AFFINE 2010: 3rd ACM Workshop on Affective Interaction in Natural Environments
Abstract: a vital requirement for social robots, virtual agents, and human-centered multimedia interfaces is the ability to infer the affective and mental states of humans and provide appropriate, timely output during sustained social interactions. Examples include ensuring that the user is interested in maintaining the interaction or providing suitable empathic responses through the display of facial expressions, gestures, or generation of speech. This workshop will cover real-time computational techniques for the recognition and interpretation of human multimodal verbal and non-verbal behaviour, models of mentalising and empathising for interaction, and multimedia techniques for synthesis of believable social behaviour supporting human-agent and human-robot interaction.
WS18 – SAPMIA: ACM Workshop on Social, Adaptive and Personalized Multimedia Interaction and Access
Abstract: in an effort to address and overcome some of these open issues that hinder effective access and interaction of multimedia content, this workshop will bring together individuals from a number of research communities, including but not limited to Multimedia Distribution and Access, Social Network Analysis, Multimedia Content Analysis, and User Modelling Adaptation and Personalization. It is our belief that a synergetic approach involving these areas of work can exceed their individual potentials, leading to improved access, understanding, and retrieval of multimedia content. The main objective of this workshop is to provide a forum to disseminate work that explicitly exploit the synergy between multimedia content analysis, personalisation, and next generation networking and community aspects of social networks. We believe that this integration could result on robust, personalized multimedia services, providing users with an improved multimedia experience.
WS19 – CMM 2010: ACM Workshop on Connected Multimedia
Abstract: the theme of the workshop is connected multimedia — further exploiting social and cultural constraints for distributed multimedia computing. This workshop is intended to bring together researchers, engineers, and practitioners to exchange their ideas in this area and to advance and disseminate the most recent research results on this theme. By connected multimedia, we mean to address the distributed multimedia computing problem with two foci. The first is to incorporate the cultural constraints into the consideration. There are many successful examples in the literature in which the standard solutions to the multimedia computing problem fail, whereas the specialized solutions that incorporate the local cultural constraints into consideration succeed. One such example is the human flesh search in China. There are already many successful stories in China where when the “standard” search fails to work, people use the human flesh search to find what they expect to know from the Internet. These stories demonstrate the power of the collective human interactions to the computing facilities as the wisdom of crowds. In fact, due to these successful stories as well as the philosophy underneath these stories Google has already initiated a large project to incorporate those local cultural elements into their Chinese version search to hopefully empower their search performance. The second is to incorporate the social constraints into the consideration. In recent years it has become a hot research area where people attempt to use social contextual information to deliver more effective solutions in image or video understanding and/or to use multimedia technologies to further promote social or environmental interactions, such as folk computing, experiential computing, and social computing with many emerging, specially dedicated organizations or products such as facebook, flickr, and pipes.
Abstract: In recent years, we have witnessed a growing number of user-centric multimedia applications, especially with the popularity of the Web 2.0. Examples include Flickr, YouTube, Facebook, MySpace, etc. This initial movement has gained enormous momentum in recent years and spread largely to communicate online in digital social networks. These emerging applications on social web and social networks have produced some new type of multimedia content, which is termed as “social media”, that is created by people using highly accessible and scalable publishing technologies. Social multimedia is the media that is used as a means for communication in social networks.
This workshop will continue a successful first Workshop on Social Media 2009 and form a platform for the continued discussion of the key research issues in social multimedia. Unlike conventional multimedia data, social media contains much rich user-generated information, which is particularly critical to resolving the long-standing challenge toward multimedia understanding. This new media also introduces many challenging and new research issues and as well as many exciting real-world applications (e.g. large-scale social image and video analysis and retrieval). This workshop solicits contributions on various aspects of social media. In particular, workshop papers will elaborate related theory, methodology, algorithms and issues associated to social media content creation, manipulation, content analysis, storage, search, learning and mining.
WS20 – SSPW 2010: ACM Workshop on Social Signal Processing
Abstract: the ability to understand and manage social signals of a person we are communicating with is the core of social intelligence. Social Intelligence is a facet of human intelligence that has been argued to be indispensable and perhaps the most important for success in life. A widely accepted prediction is that next-generation computing needs to include the essence of social intelligence – the ability to recognize and generate social signals and social behaviours – in order to become more effective and more efficient. Due to this vision of the future, automated analysis and synthesis of social signals and social behaviours, including social interactions (like turn taking and backchanelling), social attitude (like alliance), and social relations/ roles, have attracted increasing attention. Machine analysis of human social interactions and social signals is progressing rapidly with new or pending applications in HCI, psychology, biomedicine, politics, and entertainment technology, among other fields. With these advances come new conceptual and methodological challenges. The workshop aims at presenting cutting-edge research and new challenges in automatic analysis and synthesis of human social interactions and signalling in an interdisciplinary forum of computer and behavioral scientists.
WS21 – ACM Workshop on Surreal Media and Virtual Cloning
Abstract: recent scientific advances in a variety of research fields are resulting in mature virtual reality technologies and systems to support real-time realistic interaction between humans in online virtual environments. Such systems aim at enabling collaboration between 3D objects and content captured and streamed in real-time to cooperative immersive 3D worlds. Low-latency interactivity requires accurate and time-critical information exchange between remote places to reduce cognitive workload, and enhance situation awareness. A virtual environment with live multimedia streams, 3D objects and real-time interactivity results in a unique ’surreal media’ allowing for varying configurations and information fusion from multiple sources and platforms. It further enables intuitive interfaces in which users can respond to dynamic situational context information in complex mix-reality environments. Surreal media encompasses realistic 3D virtual objects, virtual human clones, live media streams and 3D computer generated worlds. It brings a new range of 3D virtual experiences to many different everyday aspects of life. It also brings together, for a purpose, what can be disparate research groups working on several fields including: 3D video processing, real-time 3D media coding, computer graphics, human computer interaction and human factors.
WS06 – EiMM10: 2nd ACM Workshop on Events in Multimedia
Abstract: humans think in terms of events and entities. Events provide a natural abstraction of happenings in the real world. The concept of events has a long history in foundational sciences such as philosophy and linguistics. After first developing objects-based and entity-based approaches, computer science research is now addressing the concept of events and building many applications that consider events at least as important as objects. Consequently, we find many different solutions and approaches for modeling, detecting, and processing events. In addition, we find different applications that are based on events and make use of events. Conferences and workshops on events in computer science typically deal with the capturing, processing, and management of low-level events such as publish/subscribe-approaches, middleware-based architectures, complex event processing, and event stream processing. Although this work is very essential for an efficient execution of the applications build on top of such approaches, the understanding of the concept of events is disconnected from the domain-level of events that the actual users of such applications have to deal with. However, considering multimedia data, its semantics is naturally closely tied to the event(s) it documents. The workshop focuses on how to detect, model, and process domain-level events and applications that make use of domain-level events in the context of multimedia data.
Workshops
Workshops on Monday, October 25, 2010
Multimedia Content
Multimedia Technologies and Systems
Multimedia Trends
Workshops on Friday, October 29, 2010
Multimedia Content
Multimedia Technologies and Systems
Multimedia Trends
WS01 – eHeritage 2010: 2nd ACM Workshop on eHeritage and Digital Art Preservation
Olga Bellon, Matteo Dellepiane, Ilan Shimshoni
Website: http://www.imago.ufpr.br/ehw10/
Paper submission: http://edas.info/N9021
Abstract: Computer Vision & Graphics and Multimedia research and practices have, and will continue, to play a center role in Cultural Heritage preservation efforts. The Second Workshop on eHeritage and Digital Art Preservation aims to bring together these researches as well as interdisciplinary researches that are related to these areas, in particular image and audio research, image and haptic (touch) research, as well as presentation of visual content over wide web and education. This workshop will follow the very successful First eHeritage Workshop which was held in conjunction with ICCV in Kyoto last year
WS07 – MiFor2010: Multimedia in Forensics, Security and Intelligence
Sebastiano Battiato, Sabu Emmanuel, Adrian Ulges, Marcel Worring
Website: http://madm.dfki.de/mifor2010/MiFor2010.html
Paper submission: http://edas.info/N9023
Abstract: with the proliferation of multimedia data on the web, surveillance cameras in cities, and mobile phones in everyday life we see an enormous growth in multimedia data that needs to be secured to prevent illegal use, to be analyzed by forensic investigators to detect and reconstruct illegal activities, or be used as source of intelligence. The sheer volume of such datasets makes manual inspection of all data impossible. Tools are needed to support the investigator in their quest for relevant clues and evidence and in their strive towards preventing crime. Such tools should support the protection, management, processing, interpretation, and visualization of multimedia data in the different steps of the investigation process. The target audience of MiFor 2010 is composed of researchers working on innovative multimedia technology and representatives from companies developing tools used in forensics, security and intelligence. This workshop aims to bring the synergy needed to develop new and effective solutions to improve crime prevention and investigation in all of its steps.
WS08 – MTDL 2010: 2nd ACM Workshop on Multimedia Technologies for Distance Learning
Timothy K. Shih, Rynson Lau, Nadia Magnenat-Thalmann
Website: http://mtdl2010.mine.tku.edu.tw/
Paper submission: http://edas.info/N9061
Abstract: multimedia technologies and networking infrastructure have changed human social behavior. One typical example is education. The impact of distance learning to traditional universities in particular allows educational professionals to rethink about how to efficiently and effectively using multimedia technologies to improve instruction, as well as to encourage students to learn. Although multimedia technologies have already been used widely in e-learning, various considerations should be carefully addressed from both pedagogical and technological perspectives, to ensure the successful incorporation of these technologies in e-learning. This ACM workshop aims to discuss problems, current studies, and solutions in how to use multimedia and communication technologies to improve e-learning. Especially, presentations should address the difference between using and without using multimedia technologies in education. Practical solutions are encouraged, although pedagogical theories may be used to support the solutions.
WS09 – 3DVP 2010: ACM Workshop on 3D Video Processing
Oliver Schreer, Emanuele Trucco, Adrian Hilton
Website: http://ip.hhi.de/ACMMM10_Workshop3DVP/
Paper submission: http://edas.info/N9035
Abstract: Research on 3D video processing has gained a tremendous amount of momentum due to advances in video communications, broadcasting and entertainment technology, e.g., blockbusters like Avatar and Up. This is pushing the introduction of 3D services and the development of high- quality 3D displays in the near future. Beside the commercially interesting areas in entertainment and broadcasting, 3D video is becoming important in many other fields related to the analysis of single or multiple video streams. Examples are security and surveillance, biomechanics, human motion analysis and modelling, 3D reconstruction, indexing and retrieval as well as medical imaging. In all these fields, 3D video processing plays a key role and a large variety of challenges can be recognized. The aim of this workshop is to bring together leading experts in the field of 3D video processing from academia and industry, creating a stimulating and informative forum on recent advances in this exciting field. The topics of this workshop shall cover all aspects related to 3D video processing ranging from stereo to multi-view, image-based rendering, 3D production, real-time systems and applications.
WS02 – ACM Workshop on 3D Object Retrieval
Mohamed Daoudi, Michela Spagnuolo, Remco Veltkamp
Website: http://www-rech.telecom-lille1.eu/acm3dor/
Paper submission: http://edas.info/N9047
Abstract: the use of three-dimensional (3D) image and model databases throughout the Internet is growing both in number and size. The development of modeling tools, 3D scanners, 3D graphic accelerated hardware, Web3D, and so on, is enabling access to 3D materials of high quality. The emergence of 3D media is also directly related to the emergence of the 3D acquisition technologies. Indeed, recent advances in 3D scanner acquisition and 3D graphics rendering technologies boost the creation of 3D model archives for several application domains. These include archeology, cultural heritage, computer-assisted design (CAD), medicine, 3D face recognition, videogames or bioinformatics. Thereupon, the development of efficient search mechanisms is required for the effective retrieval of 3D objects from large repositories. The purpose of this workshop is to bring together researchers interested in 3D retrieval from different fields (computer vision, computer graphics, machine learning and human-computer interaction). Its goal is to provide a state-of-the-art overview of challenges in the research on 3D retrieval. This workshop seeks original high innovative research in the area of 3D retrieval
WS03 – MML10: 3rd ACM Workshop on Machine Learning and Music
Rafael Ramirez, Darrell Conklin, Christina Anagnostopoulou, Jose Manuel Iñesta
Website: http://www.dtic.upf.edu/~rramirez/MML10/
Paper submission: http://edas.info/N9039
Abstract: With the current explosion and quick expansion of multimedia digital formats in general, and music digital formats in particular, research on machine learning and music is gaining increasing popularity. As complexity of the problems investigated by researchers on this area increases, there is a need to develop new algorithms and methods to solve these problems. Machine learning has proved to provide efficient solutions to many music-related problems both of academic and commercial interest. The goal of the workshop is to bring together researchers who are using machine learning in musical applications, providing the opportunity to promote, present and discuss ongoing work in the area. Research papers, case studies, lessons learned, status reports, and discussions of practical problems in machine-learning-based music processing applications are all welcome submissions.
WS10 – SSCS 2010: ACM Workshop on Searching Spontaneous Conversational Speech
Martha Larson, Roeland Ordelman, Florian Metze, Franciska de Jong, Wessel Kraaij
Website: http://www.searchingspeech.org/
Paper submission: http://edas.info/N9029
Abstract: The SSCS 2010 workshop is a forum for presentation of recent research results concerning advances and innovation in the area of spoken content retrieval and in the area of multimedia search that makes use of automatic speech recognition technology. Spontaneous, conversational speech occurs in a wide variety of domains and the workshop is relevant for lectures, meetings, interviews, debates, conversational broadcast (e.g., talkshows), podcasts, call center recordings, cultural heritage archives, social video on the Web and spoken natural language queries. The objective of the workshop is to bring together researchers in theareas of speech recognition, audio processing, multimedia analysis and information retrieval for exchange and interaction.
WS11 – ARTEMIS2010: ACM Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams
Anastasios (Tasos) Doulamis, Jordi Gonzalez, Marco Bertini
Website: http://iselab.cvc.uab.es/artemis2010
Paper submission: http://edas.info/N9057
Abstract: cognitive video supervision and event analysis in video sequences is a critical task in many multimedia applications. Methods, tools and algorithms that aim to detect and recognize high level concepts and their respective spatio-temporal and causal relations in order to identify semantic video activities, actions and procedures have been in the focus of the research community over the last years. This research area has strong impact on many real-life multimedia applications based on a semantic characterization and annotation of video streams in various domains (e.g., sports, news, documentaries, movies and surveillance), either broadcast or user-generated videos. Although a first critical issue is the estimation of quantitative parameters describing where events are detected, recent trends are facing the analysis of multimedia footage by applying image and video understanding techniques to that detected/tracked motion. That is, the challenge is becoming the generation of qualitative descriptions about the meaning of (human) motion, therefore describing not only where, but also why an event is being observed.
WS12 – AIEMPro10: 3d ACM Workshop on Automated Information Extraction in Media Production
Alberto Messina, Jean-Pierre Evain, Robbie De Sutter, Masanori Sano, Gerald Friedland
Website: http://www.crit.rai.it/EN/attivita/archivi/AIEMPro10/index.html
Paper submission: http://edas.info/N9041
Abstract: the third Workshop on Automated Information Extraction in Media Production (AIEMPro10) aims at fostering exchange of ideas and of practises between leading experts in research and leading actors in the media community, in order to catalyse the migration towards new ways of producing media content, aided by large scale introduction of tools for automated multimedia analysis and understanding. On the other hand, the workshop should help researchers in better understanding what are some real-life key requirements which would enable their scientific developments come into wider adoption. The workshop aims at attracting the attention of researchers and practitioners in the field of automatic information extraction based on audiovisual content analysis on the problems related with media production processes. In particular, the objective is to analyse the impact and performances of these tools in real-life applications, and on real-life material. Authors are encouraged to submit papers on which they enlighten the features of existing or novel tools in the key aspects of future media production based on automated information extraction, including acquisition, editing, publishing, archiving and repurposing of audiovisual material. The best accepted papers of AIEMPro will be considered for inclusion in a special issue of Springer’s Multimedia Tools and Applications journal.
WS04 – MoViD: ACM Workshop on Mobile Video Delivery
Mainak Chatterjee, Samrat Ganguly, Igor Curcio, Nalini Venkatasubramanian
Website: http://eecs.ucf.edu/movid/
Paper submission: http://edas.info/N9025
Abstract: the focus of this workshop is to present and discuss recent advances in wireless technologies for delivering video content to mobile users. The goal of this workshop is to deepen the understanding of research and deployment challenges in building the Next Generation Mobile Video Internet. The workshop also creates an interesting forum for discussion given the various choices we have in terms of wireless technologies and various approaches in terms of delivering video content. Specifically, the workshop intends to address the following topics: (a) Research challenges in developing new techniques for delivering rich video experience to users over existing wireless technologies; (b) New visions and concepts that will drive evolution of wireless access technologies to support high quality video content with diverse QoS requirements; (c) Deployment challenges in new video delivery models (broadcast/multicast) to mobile users, and (d) Novel mobile video applications.
WS13 – VLS-MCMR’10: ACM Workshop on Very-Large-Scale Multimedia Corpus, Mining and Retrieval
Benoit Huet, Alex Hauptmann, Tat-Seng Chua
Website: http://vls-mcmr10.eurecom.fr/
Paper submission: http://edas.info/N9027
Abstract: pivotal to many tasks in relation to multimedia research and development is the availability of sufficiently large datasets and their corresponding ground truth as well as the tools for efficiently handling and managing such large datasets. Currently available datasets for multimedia research are either too small such as the Corel or Pascal datasets, too specific like the TRECVID dataset, or without ground truth, such as the several recent efforts by MIT and MSRA that gathered millions of Web images for testing. While it is relatively easy to crawl and store a huge amount of data, the creation of ground-truth necessary to systematically train, test, evaluate and compare the performance of various algorithms and systems is a major problem. For this reason, more and more research groups are individually putting efforts into the creation of such corpus in order to carry out research on large-scale dataset. There is a need to unify these individual efforts into the creation of a unified web-scale repository which would benefit the entire multimedia research community. The purpose of this workshop is to bring together researchers interested in the construction and analysis of Web Scale multimedia corpus and methodologies to mine and retrieve from them.
WS14 – MPVA 2010: ACM Workshop on Multimodal Pervasive Video Analysis
Vittorio Murino, Hamid Aghajan, Marco Cristani, Nicu Sebe
Website: http://profs.sci.univr.it/~cristanm/MPVA2010/
Paper submission: http://edas.info/N9031
Abstract: Thanks to the confluence of urban monitoring applications and portable cameras carried by humans everywhere, video acquisition, processing, and storage systems have become an integral part of the fabric of today’s life.
Besides the classical applications such as security and surveillance, cameras have been considered for creating novel applications based on the notions of smart homes, ambient intelligence, human-computer interaction, social networks, ambient assisted living, smart seminar rooms, building emergency management, assistive technologies, and many more.
Cameras are mounted at fixed location in the urban infrastructure, or are moved around by humans or vehicles. Fusion of data between the cameras is explored as a means to enhance the interpretation task or to add confidence to the monitoring results. Such fusion can occur across different spatio-temporal levels and between subsets of fixed and mobile cameras as per the needs of the application and the availability of valuable information from each camera.
Addressing new challenges related to processing of distributed observations with a network of cameras and applications based on joint video analysis between fixed and mobile cameras will be the subjects of interest. Techniques and applications based on fixed or mobile camera systems will also be considered.
WS15 – ACM Workshop on Mobile Cloud Media Computing
Xian-Sheng Hua, Chang Wen Chen, Gang Hua
Website: http://www.mcmc2010.info
Paper submission: http://edas.info/N9033
Abstract: smart mobile devices such as camera phones typically will be carried by people all the time. These devices are true “multimedia” devices that acquire, process, transmit and present text, image, video and audio data using both media input (camera and other sensors) and output (screen and speaker) channels. However, due to the limitations in computation, storage, display, and camera, multimedia applications and systems have not been adequately supported on mobile devices. Recently, the rapid development along the following aspects largely mitigated these limitations: (1) Cloud computing, which solves both the bottle neck of computation and storage; (2) large and high-resolution display (more and more mobile devices are equipped with high-resolution LED); (3) 3G and WiFi, which solves the bandwidth issue; (4) high-quality cameras; (5) more informative sensors like GPS, gravity sensor, compass, etc; (6) More powerful CPU. With these developments, it is now the prime time for us to realize intelligent mobile device centered multimedia applications with the support of a cloud computing platform. In particular, the support of cloud computing platform has become an essential factor especially for scalable and connected mobile multimedia technologies, applications and systems, due to its powerful support on computation, storage and networking. The focus of this workshop is on exploring challenges and opportunities of intelligent multimedia technologies, applications and systems on mobile devices, especially when a media cloud computing platform can be appropriately leveraged.
WS16 – ACM Workshop on Advanced video streaming techniques for peer-to-peer networks and social networking
Gabriella Olmo, Christian Timmerer, Keith Mitchell
Website: http://www.p2pstreaming.eu/
Paper submission: http://edas.info/N9045
Abstract: peer-to-peer (P2P) is a promising technology for video streaming, and offers advantages in terms of robustness, reconfigurability and scalability. From the point of view of the broadcaster, the P2P approach permits to serve a larger audience without the need of proportionally increased resources. From the users’ point of view, the P2P should allow to experience high quality video in a cost effective fashion. Moreover, users themselves can act as prosumers by distributing their own contents within social networks enabling heterogeneous users to real time, TV-quality video streaming on P2P overlays. The workshop is about algorithms, issues and experiences related to P2P video streaming and social networks taking into account recent advances on multimedia coding such as scalability, resilience, cross layer optimization, network coding as well as its distribution and interaction.
The best paper award (€300) is sponsored by RADVISION.
WS17 – AFFINE 2010: 3rd ACM Workshop on Affective Interaction in Natural Environments
Ginevra Castellano, Kostas Karpouzis, Jean-Claude Martin, Louis-Philippe Morency, Laurel Riek, Christopher Peters
Website: http://www.cl.cam.ac.uk/conference/affine2010
Paper submission: http://edas.info/N9037
Abstract: a vital requirement for social robots, virtual agents, and human-centered multimedia interfaces is the ability to infer the affective and mental states of humans and provide appropriate, timely output during sustained social interactions. Examples include ensuring that the user is interested in maintaining the interaction or providing suitable empathic responses through the display of facial expressions, gestures, or generation of speech. This workshop will cover real-time computational techniques for the recognition and interpretation of human multimodal verbal and non-verbal behaviour, models of mentalising and empathising for interaction, and multimedia techniques for synthesis of believable social behaviour supporting human-agent and human-robot interaction.
WS18 – SAPMIA: ACM Workshop on Social, Adaptive and Personalized Multimedia Interaction and Access
David Vallet, Naeem Ramzan, Martin Halvey, Charalampos Z. Patrikakis
Website: http://ir.ii.uam.es/sapmia2010/
Paper submission: http://edas.info/N9043
Abstract: in an effort to address and overcome some of these open issues that hinder effective access and interaction of multimedia content, this workshop will bring together individuals from a number of research communities, including but not limited to Multimedia Distribution and Access, Social Network Analysis, Multimedia Content Analysis, and User Modelling Adaptation and Personalization. It is our belief that a synergetic approach involving these areas of work can exceed their individual potentials, leading to improved access, understanding, and retrieval of multimedia content. The main objective of this workshop is to provide a forum to disseminate work that explicitly exploit the synergy between multimedia content analysis, personalisation, and next generation networking and community aspects of social networks. We believe that this integration could result on robust, personalized multimedia services, providing users with an improved multimedia experience.
WS19 – CMM 2010: ACM Workshop on Connected Multimedia
Zhongfei (Mark) Zhang, Zhengyou Zhang, Ramesh Jain
Website: http://www.fortune.binghamton.edu/CMM2010/
Paper submission: http://edas.info/N9049
Abstract: the theme of the workshop is connected multimedia — further exploiting social and cultural constraints for distributed multimedia computing. This workshop is intended to bring together researchers, engineers, and practitioners to exchange their ideas in this area and to advance and disseminate the most recent research results on this theme. By connected multimedia, we mean to address the distributed multimedia computing problem with two foci. The first is to incorporate the cultural constraints into the consideration. There are many successful examples in the literature in which the standard solutions to the multimedia computing problem fail, whereas the specialized solutions that incorporate the local cultural constraints into consideration succeed. One such example is the human flesh search in China. There are already many successful stories in China where when the “standard” search fails to work, people use the human flesh search to find what they expect to know from the Internet. These stories demonstrate the power of the collective human interactions to the computing facilities as the wisdom of crowds. In fact, due to these successful stories as well as the philosophy underneath these stories Google has already initiated a large project to incorporate those local cultural elements into their Chinese version search to hopefully empower their search performance. The second is to incorporate the social constraints into the consideration. In recent years it has become a hot research area where people attempt to use social contextual information to deliver more effective solutions in image or video understanding and/or to use multimedia technologies to further promote social or environmental interactions, such as folk computing, experiential computing, and social computing with many emerging, specially dedicated organizations or products such as facebook, flickr, and pipes.
WS05 – WSM2010: 2nd ACM Workshop on Social Media
Steven C.H. Hoi, Jiebo Luo, Roelof van Zwol, Susanne Boll-Westermann, Ioannis (Yiannis) Kompatsiaris
Website: http://www.cais.ntu.edu.sg/~wsm2010/
Paper submission: http://edas.info/N9051
Abstract: In recent years, we have witnessed a growing number of user-centric multimedia applications, especially with the popularity of the Web 2.0. Examples include Flickr, YouTube, Facebook, MySpace, etc. This initial movement has gained enormous momentum in recent years and spread largely to communicate online in digital social networks. These emerging applications on social web and social networks have produced some new type of multimedia content, which is termed as “social media”, that is created by people using highly accessible and scalable publishing technologies. Social multimedia is the media that is used as a means for communication in social networks.
This workshop will continue a successful first Workshop on Social Media 2009 and form a platform for the continued discussion of the key research issues in social multimedia. Unlike conventional multimedia data, social media contains much rich user-generated information, which is particularly critical to resolving the long-standing challenge toward multimedia understanding. This new media also introduces many challenging and new research issues and as well as many exciting real-world applications (e.g. large-scale social image and video analysis and retrieval). This workshop solicits contributions on various aspects of social media. In particular, workshop papers will elaborate related theory, methodology, algorithms and issues associated to social media content creation, manipulation, content analysis, storage, search, learning and mining.
WS20 – SSPW 2010: ACM Workshop on Social Signal Processing
Alessandro Vinciarelli, Maja Pantic, Alex Pentland
Website: http://sspnet.eu/2010/04/sspw/
Paper submission: http://edas.info/N9053
Abstract: the ability to understand and manage social signals of a person we are communicating with is the core of social intelligence. Social Intelligence is a facet of human intelligence that has been argued to be indispensable and perhaps the most important for success in life. A widely accepted prediction is that next-generation computing needs to include the essence of social intelligence – the ability to recognize and generate social signals and social behaviours – in order to become more effective and more efficient. Due to this vision of the future, automated analysis and synthesis of social signals and social behaviours, including social interactions (like turn taking and backchanelling), social attitude (like alliance), and social relations/ roles, have attracted increasing attention. Machine analysis of human social interactions and social signals is progressing rapidly with new or pending applications in HCI, psychology, biomedicine, politics, and entertainment technology, among other fields. With these advances come new conceptual and methodological challenges. The workshop aims at presenting cutting-edge research and new challenges in automatic analysis and synthesis of human social interactions and signalling in an interdisciplinary forum of computer and behavioral scientists.
WS21 – ACM Workshop on Surreal Media and Virtual Cloning
Ebroul Izquierdo, Yang Cai
Website: http://acmmm10-smvc.eecs.qmul.ac.uk/
Paper submission: http://edas.info/N9055
Abstract: recent scientific advances in a variety of research fields are resulting in mature virtual reality technologies and systems to support real-time realistic interaction between humans in online virtual environments. Such systems aim at enabling collaboration between 3D objects and content captured and streamed in real-time to cooperative immersive 3D worlds. Low-latency interactivity requires accurate and time-critical information exchange between remote places to reduce cognitive workload, and enhance situation awareness. A virtual environment with live multimedia streams, 3D objects and real-time interactivity results in a unique ’surreal media’ allowing for varying configurations and information fusion from multiple sources and platforms. It further enables intuitive interfaces in which users can respond to dynamic situational context information in complex mix-reality environments. Surreal media encompasses realistic 3D virtual objects, virtual human clones, live media streams and 3D computer generated worlds. It brings a new range of 3D virtual experiences to many different everyday aspects of life. It also brings together, for a purpose, what can be disparate research groups working on several fields including: 3D video processing, real-time 3D media coding, computer graphics, human computer interaction and human factors.
WS06 – EiMM10: 2nd ACM Workshop on Events in Multimedia
Ansgar Scherp, Ramesh Jain, Mohan S. Kankanhalli, Vasileios Mezaris
Website: http://www.uni-koblenz.de/confsec/eimm10/
Paper submission: http://edas.info/N9112
Abstract: humans think in terms of events and entities. Events provide a natural abstraction of happenings in the real world. The concept of events has a long history in foundational sciences such as philosophy and linguistics. After first developing objects-based and entity-based approaches, computer science research is now addressing the concept of events and building many applications that consider events at least as important as objects. Consequently, we find many different solutions and approaches for modeling, detecting, and processing events. In addition, we find different applications that are based on events and make use of events. Conferences and workshops on events in computer science typically deal with the capturing, processing, and management of low-level events such as publish/subscribe-approaches, middleware-based architectures, complex event processing, and event stream processing. Although this work is very essential for an efficient execution of the applications build on top of such approaches, the understanding of the concept of events is disconnected from the domain-level of events that the actual users of such applications have to deal with. However, considering multimedia data, its semantics is naturally closely tied to the event(s) it documents. The workshop focuses on how to detect, model, and process domain-level events and applications that make use of domain-level events in the context of multimedia data.