Video-based Behavior Analysis and Action Recognition

Speaker:        Prof. Ying-Li Tian
                The City College
                City University of New York
                USA

Title:          "Video-based Behavior Analysis and Action Recognition"

Date:           Tuesday, 29 October 2013

Time:           11:00am - 12 noon

Venue:          Lecture Theater H (near lifts 27 & 28)), HKUST

Abstract:

Video-based behavior analysis and action recognition play an increasingly
important role in many applications such as video surveillance, social
media, health informatics, assistive technology, etc. With the release of
RGBD cameras and the associated SDK, it has become practical to capture
RGB sequences as well as depth maps in real time. Meanwhile, 3D positions
of skeleton joints can be provided in real time and with reasonable
accuracy. It has therefore motivated recent research work to investigate
action recognition using the 3D information. In this talk, I will focus on
our research of behavior analysis and action recognition from both 2D and
depth videos. In particular, this talk will report several new types of
features which are robust and efficient for video-based action recognition
including ActionHOG, Eigenjoints, Depth motion maps, Edge enhanced depth
motion maps, and Histogram of 3D Facets. The effectiveness and robustness
of these features are evaluated on several public databases for action
recognition and TRECVID Surveillance Event Detection 2012.

**************
Biography:

Dr. Ying-Li Tian is a professor in the Department of Electrical
Engineering at the City College of New York and the Department of Computer
Science at the Graduate Center of the City University of New York. She
received her PhD from the Department of Electronic Engineering at the
Chinese University of Hong Kong in 1996 and her BS and MS from TianJin
University, China in 1987 and 1990. After she held an associate professor
position in National Laboratory of Pattern Recognition at the Chinese
Academy of Sciences, Beijing, China, Dr. Tian joined the Robotics
Institute in Carnegie Mellon University as a postdoctoral fellow from 1998
to 2001. She focused on automatic facial expression analysis. From 2001 to
2008, Dr. Tian was a research staff member at IBM T. J. Watson Research
Center. Her research focused on moving object detection, tracking, and
event and activity analysis for video surveillance. She was one of the
inventors of the IBM Smart Surveillance Solutions (SSS) product and was
leading the video analytics team. She received several IBM Invention
Achievement Awards and the IBM Outstanding Innovation Achievement Award
due to her contributions to IBM SSS. She is an Associate Editor of
Computer Vision and Image Understanding. Dr. Tian has published more than
130 papers in journals and conferences and has filed more than 30 patents.
She is a Senior Member of the IEEE and a member of the ACM. Her current
research focuses on a wide range of computer vision problems from event
detection and analysis, assistive technology, to multimodal affection
recognition, scene understanding, and video surveillance.