Title: Visual Event Recognition in Videos by Learning from Web Data
Speaker: Prof. Dong Xu （Nanyang Technological University）
Time: 2010-12-24 9:00
Venue: the Conference Room of Optical Image Analysis and Learning Center (OPTIMAL), 3rd Floor, Building 3
Abstract:
In this talk, I will first describe a new visual event recognition framework for consumer domain videos by leveraging a large amount of loosely labeled web videos (e.g., from YouTube). Specifically, I will present a new aligned space-time pyramid matching method and a novel cross-domain learning method to better fuse the information from multiple pyramid levels and different types of local features and to cope with the mismatch in data distribution of consumer video domain and web video domain. This work wins the best student paper award at CVPR 2010. Moreover, I will also introduce the ongoing research projects and job opportunities in the Visual Computing Group at Nanyang Technological University.
Speaker Profile:
Dong Xu is currently an assistant professor at Nanyang Technological University in Singapore. He is currently leading the Visual Computing Group with more than ten research students and staff working on new theories, algorithms and systems for intelligent processing and understanding of visual data such as images and videos. He has published more than 40 papers in top venues including T-PAMI, T-IP, T-CSVT, CVPR, ACM MM, ICML, and IJCAI. He was co-author (with his PhD student Lixin Duan) of a paper that won the Best Student Paper Award in the prestigious IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2010). The PhD students Yi Huang and Lixin Duan in his research group were awarded the prestigious MSRA Fellowship Awards in 2008 and 2009, respectively. He is an associate editor of Neurocomputing (Elsevier) and Machine Vision and Applications Journal (Springer) and he is an editorial board member of Journal of Multimedia (Academy). He is currently serving as the guest editor of a forthcoming special issue on Social Media in ACM Transactions on Multimedia Computing, Communications and Applications (ACM TOMCCAP) and a forthcoming special issue on Visual Content Identification and Search in IEEE Multimedia. He has served as the guest editors of three special issues on video and event analysis in T-CSVT, CVIU and PRL as well as the workshop co-chairs of The ACM SIGMM Workshop on Social Media and The ICME Workshop on Visual Content Identification and Search. He will serve as the program co-chair of The 2012 Pacific-Rim Conference on Multimedia (PCM 2012) in Singapore. Moreover, he has regularly served on the program committees of the major computer vision and multimedia conferences including ICCV, CVPR, ECCV, and ACM MM.
Optical Image Analysis and Learning Center
Tel: 029 - 8888 9302
E-mail: OPTIMAL@opt.ac.cn
Download：