CS Colloquium on Oct 30 at 2PM

Title: Computer Recognition of Human Actions

Speaker: James W. Davis
         Dept. of Computer and Information Science
         Ohio State University

Place: MCS 135, 111 Cummington Street

Abstract:

The ability of computers to detect people and reliably recognize their 
activities (and ultimately their intent) is of significant importance to 
automatic, intelligent video surveillance. In this talk, I will describe 
two of our current research projects related to action recognition. 
First I will present a probabilistic reliable-inference framework used 
to classify different actions at the shortest time exposure necessary 
for recognition. Next, I will present an expressive three-mode principal 
components model for representing and recognizing different action 
styles. I will also briefly describe our ongoing efforts toward 
integrating the research into an automatic video surveillance system. 
Support for this research is provided by the National Science 
Foundation, U.S. Army Night Vision Laboratory, U.S. Air Force, and Ohio 
Board of Regents.

Biography of the Speaker:

James W. Davis earned his Ph.D. from MIT in 2000, and is currently an 
Assistant Professor in the Department of Computer and Information 
Science at Ohio State University. He is also affiliated with the Center 
for Cognitive Science at OSU. His main research interests are in 
computer vision, visual perception, human-computer interaction, and 
artificial intelligence. Specifically, he is interested in designing 
intelligent video surveillance systems using computer vision to reliably 
detect and recognize human activities.  His research was recently 
recognized by the National Science Foundation with the prestigious NSF 
Faculty Early Career Development (CAREER) Program award.

Host: Stan Sclaroff (http://www.cs.bu.edu/~sclaroff)