Wanli OUYANG

Time: 10AM, 17 January 2014

Venue: SEIEE 5-406 (Institute of Image Communication)

Abstract: Deep learning is a new area of machine learning that attempts to learn in multiple levels of representation, corresponding to different levels of abstraction. Pedestrian detection is a key technology in automotive safety, robotics, and intelligent video surveillance. It has attracted a great deal of research interest. In order to utilize the deep learning model for our problem, the experiences and insights obtained from researchers for this problem are valuable. This talk introduces our works on using the existing experience in pedestrian detection and developing new deep learning models for learning feature, translational deformation, occlusion handling, contextual information, and classification. This talk will also introduce a new training strategy that jointly optimizes cascaded classifiers, in the mean time, avoids overfitting.

Bio: Wanli Ouyang received the M.S. degree in computer science from the College of Computer Science and Technology, Beijing University of Technology, Beijing, China. He received the PhD degree in the Department of Electronic Engineering, The Chinese University of Hong Kong, where he is now a research assistant professor. His research interests include image processing, computer vision and pattern recognition. He has been the reviewer of many top journals and conferences such as IEEE TIP, TSP, TITS, TNN, CVPR, ICCV, ECCV. He is a member of the IEEE.