<< Back

Cen Rao

The representation plays an important role in recognition and understanding of human action from video sequences. A view-invariant representation of action consisting of dynamic instants and intervals, which is computed using spatiotemporal curvature of a trajectory, is presented. In order to validate our representation, we report experiments on several different actions performed by different people, and captured in different viewpoints

Associated publications:

Action Rectionition based onView Invariant Spatio-temporal Analysis (Draft) ,
ACM Multimedia 2003, Nov 2-8, Berkeley, CA USA

View-invariant Alignment and matching of Video Sequences (Draft)
The Ninth IEEE International Conference on Computer Vision, ICCV 2003, Nice, France

View-Invariant Representation And Recognition of Actions
International Journal of Computer Vision, Vol. 50, Issue 2, 2002

View Invariance in Action Recognition
Computer Vision and Pattern Recognition, CVPR 2001, Kauai, Hawaii, Dec 11-13, 2001

View-Invariant Representation and Learning of Human Action
IEEE Workshop on Detection and Recognition of Events in Video, Vancouver, Canada, July 8, 2001

A View-Invariant Representation of Human Action
International Conference on Control, Automation, Robotics and Vision, Singapore, Dec 5th-8th, 2000

For Power Point presentation click here

For more information click here

Some Result Videos

Video synchronization