Space-Time Analysis and Manipulation of Behaviors in Video
Dept. of Computer Science and Applied Math
The Weizmann Institute of Science
Refreshments 3:15 pm
Talk 3:30 pm
Video provides a visual window into the space-time world. It tells us how dynamic scenes continuously evolve over extended periods of time. This makes video much more than a plain collection of image-frames. Yet, it is still treated as such.
In this talk I will show how by moving away from image-frames and analyzing information contained in entire space-time volumes, we can perform tasks that are very difficult and often impossible to perform otherwise. In particular, I will show how this space-time approach can be used for solving three problems related to analysis of dynamic scenes:
(i) Fast search of complex behaviors in video (based on a single example clip).
(ii) Completion of missing information in video (including very complex dynamic information).
(iii) Detection of "irregularities" in visual data (including detection of suspicious/salient behaviors in video, saliency/attention in images, and other applications).
Michal Irani is on staff at the Weizmann Institute of
Science, working in the Department of Computer Science and Applied Mathematics.
She received a B.Sc. degree in Mathematics and Computer Science from the Hebrew
University of Jerusalem in 1985, and M.Sc. and Ph.D. degrees in Computer
Science from the same institution in 1989 and 1994, respectively. From 1993 to
1996, she was a member of the technical staff of the Vision Technologies
Laboratory at the
Michal's research interests center around computer vision and image processing. Currently, she focuses on automatic analysis of video information and its application to real-world problems. Michal's prizes and honors include the David Sarnoff Research Center Technical Achievement Award (1994), the Yigal Allon Three-Year Fellowship for Outstanding Young Scientists (1998), and the Morris L. Levinson Prize in Mathematics (2003). At the European Conference on Computer Vision, she received awards for Best Paper in 2000 and in 2002, and was awarded an Honorable Mention for the Marr Prize at the IEEE International Conference on Computer Vision in 2001 and in 2005.
For appointments, please contact Janice Brochetti (firstname.lastname@example.org)