Event Location: NSH 1507
Bio: Junsong Yuan is a Nanyang Assistant Professor at Nanyang Technological University (NTU), Singapore, leading the video analytics program at School of EEE. He obtained his PhD from Northwestern University in Aug. 2009. His research interests include computer vision, video analytics, large-scale visual search and mining, human computer interaction, biomedical image analysis, etc. He has published over 100 technical papers and received over S$4.3M research grants as a PI or join-PI. He received Outstanding EECS Ph.D. Thesis award from Northwestern University and Doctoral Spotlight Award from IEEE Conf. Computer Vision and Pattern Recognition Conference (CVPR’09). He is Organizing Chair of Asian Conf. on Computer Vision (ACCV’14), and co-chairs workshops at CVPR’12’13 and ICCV’13. He also serves as Area Chair for WACV’14, ACCV’14, ICME’14, and gives tutorials at IEEE ICIP’13, FG’13, ICME’12, SIGGRAPH VRCAI’12, and PCM’12. He is an associate editor of Visual Computer Journal and Journal of Multimedia. He is currently visiting CMU with Tan Chin Tuan exchange fellowship.

Abstract: Human behaviour understanding plays a critical role in many applications, such as video surveillance and human computer interaction. In the past few years, there has been a lot of progress in action and gesture recognition with conventional 2D video cameras. Effective techniques have been developed to address challenging issues in real world environments such as dynamic and cluttered background as well as occlusions. More recently, the availability of commodity depth cameras has brought a new level of excitement to this field. Rapid progress has been made that addresses new technical issues in behaviour understanding with 3D depth cameras. In this talk, I will introduce my recent work of human behaviour understanding using both regular and depth cameras. The contents cover the action and gesture analysis using regular and depth cameras, as well as action analysis in movies and Youtube videos.