Title:Alternatives for Future Telepresence Systems
Speaker: Henry Fuchs (University of North Carolina at Chapel Hill)
Abstract: Visions for future telepresence technologies vary from conventional cameras and displays to fanciful holographic contact lenses. These visions have long been inspired by the appearance of telepresence achieved through special effects in movies, on stage, and even in mainstream news programs. These illusions may fool most uninformed observers, but of course do not achieve telepresence for the actual participants. Even today's best "Telepresence" systems have difficulty supporting such simple capabilities as eye contact and gaze awareness among these multiple distant users. This talk will review some component technologies needed to achieve natural--some would say "transparent"--telepresence (3D acquisition, tracking, rendering, 3D display), will present some recent progress, and will outline several promising future directions. Specifically, recent progress in 3D depth cameras, and in multi-viewer autostereo displays may make possible dramatically improved telepresence systems within the next few years. Such progress will allow development of a new generation of capabilities, such as the distant participants mixing naturally and arbitrarily in the shared space, which today are beyond consideration of even the best "Telepresence" systems.
Bio: Henry Fuchs is the Federico Gil Distinguished Professor of Computer Science and Adjunct Professor of Biomedical Engineering at UNC Chapel Hill.
He has been active in computer graphics since the early 1970s, with rendering algorithms (BSP Trees), hardware (Pixel-Planes and PixelFlow), virtual environments, tele-immersion systems and medical applications. He received a Ph.D. in 1975 from the University of Utah . He was a member of the faculty of the University of Texas at Dallas from 1975 to 1978. He joined the faculty at the University of North Carolina at Chapel Hill in 1978.
He is a member of the National Academy of Engineering, a fellow of the American Academy of Arts and Sciences, the recipient of the 1992 ACM-SIGGRAPH Achievement Award, the 1992 Academic Award of the National Computer Graphics Association, and the 1997 Satava Award of the Medicine Meets Virtual Reality Conference.
Title: Managing large-scale social images as part of a live Social Media Observatory
Speaker: Tat-Seng Chua (National University of Singapore)
Abstract: The popularity and convenience of social networks have encouraged users to share all kinds of contents related to their daily activities; and users are increasingly sharing more media contents with little or no textual annotations. This has resulted in massive amount of media data being available in social network sites such as Twitter/Weibo and Facebook. For example, in the live social observatory setup in NUS as part of the NExT project, over 100 million new images are shared and found each month. This talk describes our research to manage this huge and growing image/video depository to meet users’ information needs as well as to support other information analysis tasks such as the live event detection and inference. More specifically, the talk describes our approach to index and retrieve these social images, as well as research to infer the often ambiguous users’ intention during media search. For this, it discusses the use of related samples and attributes during relevance feedback, which offer promising new alternatives to help users quickly find relevant images, especially for complex and rare queries. It then describes several applications that involve the use of both media and textual/metadata analysis, such as the fashion search, product search, and the inference of location analytics and Twitter/Weibo events. Finally, the talk outlines a large-scale 5-year collaborative effort between Tsinghua and NUS to mine and structure user-generated contents.
Bio: Tat-Seng Chua is the KITHCT Chair Professor at the School of Computing, National University of Singapore (NUS). He was the Acting and Founding Dean of the School of Computing in 1998-2000. He joined NUS in 1983, and spent three years as a research staff member at the Institute of Systems Science (now I2R) in the late 1980s. His main research interests are in multimedia information retrieval, multimedia question-answering, and the analysis and structuring of user-generated contents. He is the co-Director of NExT: a large-scale research center between NUS and Tsinghua focusing on research in extreme search.
Dr Chua has organized and served as program committee member of numerous international conferences in the areas of computer graphics, multimedia and text processing. He is the conference co-chair of ACM Multimedia 2005, CIVR (now ICMR) 2005, ACM SIGIR 2008, and the Technical PC Co-Chair of SIGIR 2010. He serves in the editorial boards of: ACM Transactions of Information Systems (ACM), Foundation and Trends in Information Retrieval (NOW), The Visual Computer (Springer Verlag), and Multimedia Tools and Applications (Kluwer). He sits in the steering committee of ICMR (International Conference on Multimedia Retrieval), Computer Graphics International, and Multimedia Modeling conference series; and serves as member of an International Review Panel of a large-scale research project in Europe.