Winston Hsu, Rong Yan
There is a growing interest on effective multimedia content analysis and retrieval from both the academia and the industry, evidenced by the growing submission of multimedia-retrieval-related conference, increasing participation in video retrieval evaluation such as TRECVID (e.g., 70+ participants in 2007), and the huge success of online image/video sharing websites such as Flickr and YouTube. ICASSP is an ideal venue for this tutorial due to the following reasons: (1) ICASSP is one of the major conferences for signal processing. Most of the audience are keen to the recent advance of image/video retrieval approaches developed by other communities; (2) the emerging methods such as bags of visual words and semantic concepts provide an intermediate layer that allows multimedia researchers to access and manage multimedia data in a more effective manner. Our tutorial can be seen as an effort for bridging the gap between the fields of image/video retrieval, text retrieval, computer vision and multimedia content delivery. It will expedite the sharing of the ideas between these fields.
Dr. Winston Hsu is an Assistant Professor in the Graduate Institute of Networking and Multimedia, National Taiwan University and the founder of MiRA (Multimedia indexing, Retrieval, and Analysis) Research Group. He received his Ph.D. (2006) degree from Columbia University, New York. Before that, he was devoted to a multimedia software company, where experiencing Engineer, Project Leader, and R&D Manager.
Dr. Hsu’s current research interests are to enable "Next-Generation Multimedia Retrieval" and generally include content analysis, mining, retrieval, and machine learning over large-scale multimedia databases. Dr. Hsu’s research work in video analysis and retrieval had achieved one of the best systems in TRECVID benchmarks since 2003. He received the Best Paper Runner-Up award in ACM Multimedia 2006 and was named in the “Watson Emerging Leaders in Multimedia Workshop 2006” by IBM. Dr. Hsu is a frequent reviewer for major international journals. He is a member of IEEE and ACM.
Dr. Rong Yan is a Research Staff Member in the Intelligent Information Management Department at the IBM T. J. Watson Research Center since 2006. Dr. Yan received his M.Sc. (2004) and Ph.D. (2006) degrees from Carnegie Mellon University's School of Computer Science. His research interests include multimedia retrieval, video content analysis, data mining, machine learning and computer vision. Dr. Yan is the principle designer of the automatic/manual video retrieval system that achieves the best performance in the world-wide TRECVID evaluation in 2003 and 2005. He received the Best Paper Runner-Up award in ACM Multimedia 2004 and ACM CIVR 2007.
Dr. Yan has authored or co-authored more than 55 international conference and journal papers. He holds 1 U.S. patent and 3 pending patents. He has served in the NSF Career Proposal review panel. Dr. Yan has served or is serving on the Program Committees of ICME’06-08, CIKM’08, SIGIR’07-08, CIVR’07-08, ACM MM’04/07 and several other conferences. He has been a co-chair for the industrial program in ISM’08, the VideOlympics showcase in CIVR’07-08 and a special session in ICSC 2007. Dr. Yan is a reviewer for more than 10 international journals. He is a member of IEEE and ACM.