Web-scale Multimedia Data Management:
Challenges and Remedies
Abstract: Text-based search engines have been flourishing. However, despite increasing needs of tools for organizing and searching imagery and video content, we have not seen a successful deployment of a Web-scale multimedia search engine. This talk analyzes main technical challenges of such a deployment, and presents remedies in three areas: feature extraction, similarity characterization, and scalability.
Speaker's Bio: Professor Edward Chang received his M.S. in Computer Science and PhD in Electrical Engineering at Stanford University in 1994 and 1999, respectively. He joined the department of Electrical & Computer Engineering at University of California, Santa Barbara, in September 1999. He received his tenure in March 2003, and was promoted to full professor of Electrical Engineering in 2006. His recent research activities are in the areas of machine learning, data mining, high-dimensional data indexing, and their applications to image databases, video surveillance, and Web mining. Recent research contributions of his group include methods for learning image/video query concepts via active learning with kernel methods, formulating distance functions via dynamic associations and kernel alignment, managing and fusing distributed video-sensor data, categorizing and indexing high-dimensional image/video information, and speeding up Support Vector Machines via parallel matrix factorization and indexing. Professor Chang has served on several ACM, IEEE, and SIAM conference program committees. He co-founded the annual ACM Video Sensor Network Workshop and has co-chaired it since 2003. In 2006, he co-chairs three international conferences: Multimedia Modeling (Beijing), SPIE/IS&T Multimedia Information Retrieval (San Jose), and ACM Multimedia (Santa Barbara). He serves as an Associate Editor for IEEE Transactions on Knowledge and Data Engineering and ACM Multimedia Systems Journal. Professor Chang is a recipient of the IBM Faculty Partnership Award and the NSF Career Award. He is currently on leave from UC, heading R&D effort at Google/China.
(Delft University of Technology, The Netherlands)
Title: Content You Like, Anytime & Anyplace: Multimedia Research for New TV Concepts
Abstract: This talk is about much more
than just ¡°watching television¡±. It is about getting
the content we like, anytime and anyplace. It is
about getting entertained and informed seamlessly
and in a personalized fashion wherever we are, and
whenever we like it. It is about not feeling the
overload caused by enormous multimedia data
collections and the continuously increasing TV
content production, while at the same time drawing
the maximum benefit from the available information.
And, finally, it is about maximizing the quality of
experience. The science and technology required to
bring these scenarios closer to reality are still
not entirely mature. In particular, providing access
to the right content at the right time, and this
also in a way which is efficient enough, and also
sufficiently natural and intuitive for the user, is
still a challenging problem for the multimedia
In this talk we will analyze the current research trends in the fields of multimedia content analysis, indexing, recommendation and retrieval, in view of the requirements posed by the users at home and mobile users. Based on this analysis, paradigm shifts for multimedia research will be identified and discussed, which are likely to enable practical realization of the envisioned concept of getting the right content anywhere and anytime, and at the acceptable level of service dependability and quality of experience. These shifts require (a) more flexible, adaptive and generic content analysis and indexing approaches, (b) innovative ideas of involving the user naturally and intuitively into the content analysis and management processes, and (c) seamless integration of automatic content analysis solutions, user involvement, and distributed intelligence spread over quickly emerging social (P2P) and device networks.
Speaker's Bio: Alan Hanjalic is an Associate Professor of Multimedia Technology at the Department of Mediamatics, Delft University of Technology, The Netherlands. He was a visiting scientist and research fellow at Hewlett-Packard Labs, Palo Alto CA, British Telecom Labs, Ipswich, UK, Philips Research Labs, Briarcliff Manor NY, and Microsoft Research Asia, Beijing, China. Research interests and expertise of Dr. Hanjalic are in the broad area of multimedia information retrieval, with focus on multimedia content analysis and personalized content delivery. He authored and co-authored more than 70 publications, among which the books titled Image and Video Databases: Restoration, Watermarking and Retrieval (Elsevier, 2000) and Content-Based Analysis of Digital Video (Kluwer Academic Publishers, 2004), and holds a number of EU/US patents. Dr. Hanjalic is a member of Editorial Boards of the IEEE Transactions on Multimedia and Journal of Multimedia. He was a Guest Editor of the International Journal of Image and Graphics, Special Issue on Content-based Image and Video Retrieval, July 2001, and currently serves as a Guest Editor of the IEEE Trans. on Multimedia, Special Issue on Integration of Context and Content for Multimedia Management, and as a Chief Guest Editor of the Proceedings of the IEEE, Special Issue on Advances in Multimedia Information Retrieval. He has also served as a Co-Chair of the IS&T/SPIE Conference on Multimedia Content Analysis, Management and Retrieval 2006, Co-Chair of the IS&T/SPIE Conference on Multimedia Content Access: Algorithms and Systems 2007, Technical Program Co-Chair of the ACM Multimedia 2007 conference, Workshops Co-Chair of the ACM Multimedia 2006 conference, and as Area/Track Co-Chair of the MMM 2007, IEEE ICME 2007, PCM 2007 and WWW 2008 conferences. Dr. Hanjalic will serve as a Technical Program Co-Chair of the ACM CIVR 2008 conference, Niagara Falls, Canada, and as a General Co-Chair of the ACM Multimedia 2009 conference, Beijing, China.