Prior, Context and Interactive Computer Vision

Speaker:	Harry Shum
		Microsoft Research Asia

Title: 		"Prior, Context and Interactive Computer Vision"

Date: 		Friday, 6 May 2005

Time:		2:00pm - 3:00pm

Venue:		Room 3008 (Phase I, via lift nos. 3 or 4)
		HKUST

Abstract:

For many years, computer vision researchers have worked hard chasing the
illusive goals such as "can the robot find a boy in the scene" or "can
your vision system automatically segment the cat from the background".
These tasks require a lot of prior knowledge and contextual information.
How to incorporate prior knowledge and contextual information into vision
systems, however, is very challenging. In this talk, we propose that many
difficult vision tasks can only be solved with interactive vision systems,
by combining powerful and real-time vision techniques with intuitive and
clever user interfaces.  I will show two interactive vision systems we
developed recently, Lazy Snapping (Siggraph 2004) and Poisson Matting
(Siggraph 2004), where Lazy Snapping cuts out an object with solid
boundary, while Poisson Matting recovers soft boundary (matte) as well. A
key element in designing such interactive systems is how we model the
user's intention using conditional probability (context) and likelihood
associated with user interactions. Given how ill-posed most image
understanding problems are, I am convinced that interactive computer
vision is the paradigm we should focus today's vision research on.


Time permitting, I will give a quick overview of the latest work on
interactive computer vision from Microsoft Research Asia.



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

Harry Shum received his Ph.D. in robotics from the School of Computer
Science, Carnegie Mellon University in 1996. He worked as a researcher for
three years in the vision technology group at Microsoft Research Redmond.
In 1999, he moved to Microsoft Research Asia where he is currently the
Managing Director. His research interests include computer vision,
computer graphics, human computer interaction, pattern recognition,
statistical learning and robotics. He is on the editorial boards for IEEE
Transactions on Pattern Analysis and Machine Intelligence (PAMI),
International Journal of Computer Vision (IJCV), and Graphical Models. He
is the General Co-Chair of Tenth International Conference on Computer
Vision (ICCV 2005 Beijing). He is also an adjunct professor of computer
science at Hong Kong University of Science and Technology.