Video Analytics Lab

Nanyang Technological University; School of EEE

Junsong Yuan is a Nanyang Assistant Professor at Nanyang Technological University, leading the video analytics program at School of EEE. He obtained PhD from Northwestern University, M.Eng. from National University of Singapore, and B.Eng. from special class for the gifted young at Huazhong University of Science and Technology, China. He has co-authors over 100 technical papers and filed 3 US patents and 2 provisional US patents. 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 is an associate editor of Visual Computer Journal and Journal of Multimedia. He gives tutorials at IEEE ICIP'13, FG'13, ICME'12, SIGGRAPH VRCAI'12, and PCM'12. From Aug. 2009, he has been PI or joint-PI of over S$ 5.4M research grants, sponsored by sponsored by Singapore National Research Foundation (NRF), Media Development Authority (MDA), Infocomm Development Authority (IDA), Defence Science Organization (DSO) National Labs, Japan Society for the Promotion of Science (JSPS), Microsoft Research Redmond, USA, Adobe Research, USA, and Nanyang Technological University.

Over the last decade, the rapid advances in video content capture, storage and communication technologies have ushered an era of unprecedented growth of digital video content. We have surveillance cameras that dot every corner of big cities. We have a camera equipped mobile phones in our pockets. We have websites such as YouTube and Earthcam that make sharing videos such an addictive hobby. The huge repository of videos presents both great opportunities and challenges. On one hand, we can leverage the rich visual information in the videos to improve our daily lives, such as identifying traffic patterns from traffic videos to help reduce congestions and accidents, detecting suspicious activities from surveillance videos to prevent crimes, and providing better in-home healthcare by monitoring the behaviour of the elderly through CCTV. On the other hand, major challenges exist in analyzing large-scale videos: 1) the complexity and variations of video data; 2) the computational cost of processing large-scale video content. To this end, Dr. Yuan’s Group aims to develop intelligent video analytics tools and systems that help make sense of the big video data.

jsyuan@ntu.edu.sg