Speaker:Prof. Ying Wu  Northwestern University
Time:10:00am, Apr. 10, 2009 (FRI)
Place:Report Hall,4th Floor,ICT

Abstract:
Persistent long-duration tracking of general targets is quite challenging for computer vision, because in reality targets' visual appearances are likely to undergo large uncertainties and the environments can be cluttered and distractive. This has been a bottleneck in many video analysis applications. However, being able to persistently follow targets seems to be very basic and natural in human visual perception. Why is there a huge gap and how can we bridge it?
This talk presents our recent efforts in persistent tracking on developing new computational models that reflect and accommodate some important aspects in the human perception of visual dynamics, e.g., selective attention and context-awareness. Human perception of visual dynamics is attentional and selective. Both early attentional selection that may be innate and late attentional selection that may be learned are essential. By reflecting spatial selective attention and visual context, we propose a new visual tracking approach, i.e., the synergetic selective attention (SSA) model. It has four components: early selection that extracts informative attentional regions (ARs), synergetic tracking of these ARs based on a dynamic random field model, robust integration that is able to resolve the inconsistency in the attentional fusion, and context-aware learning for late selection that learns contextual-ARs and discriminative-ARs.

Bio:
Prof.Ying Wu received the B.S. from Huazhong University of Science and Technology, Wuhan, China, in 1994, the M.S. from Tsinghua University, Beijing, China, in 1997, and the Ph.D. in electrical and computer engineering from the University of Illinois at Urbana-Champaign (UIUC), Urbana, Illinois, in 2001. He joined the Department of Electrical and Computer Engineering at Northwestern University, Evanston, Illinois, as an assistant professor in 2001, and he is currently an associate professor of Electrical Engineering and Computer Science at Northwestern University.
His current research interests include computer vision, image and video analysis, pattern recognition, machine learning, multimedia data mining, and human-computer interaction. He serves as associate editors for IEEE Transactions on Image Processing, SPIE Journal of Electronic Imaging, and IAPR Journal of Machine Vision and Applications. He served as a local chair in CVPR'07, an area chair for CVPR'08, ICCV'09, ICIP'08 and ICIP'09.
He received the Robert T. Chien Award at UIUC in 2001, and the NSF CAREER award in 2003. He is a senior member of the IEEE.