There is a signup schedule for this event (UT EID required).

Type of Talk

:  UTCS Colloquium

Speaker/Affiliation:  Hao Jiang/Boston
College

Date/Time:  Wednesday, April 8, 2009 11:00 a.m.

<

p>Location:  ACES 2.404B

Host:  Kristen Grauman

Tal

k Title: "Labeling Problems and Convex Solutions"

Talk Ab

stract:

Many problems in computer vision such as image matching and o

bject tracking can be abstracted into labeling problems in which we try to<

br />assign labels to model parts in some consistent fashion. Apart from sp

ecial cases which can be solved efficiently using polynomial algorithms,&n

bsp; general consistent labeling problems are NP-hard. We are interested i

n efficient approximation algorithms that can explore the search space &nbs

p;  globally and approach the global optimum. Convex approximations

are useful methods that meet this demand. By carefully constructing convex

approximations, we can achieve efficient solutions which in some cases are
even faster than greedy methods. I will show how this approach helps&nbsp

;   in solving the problems of scale and rotation invariant obj

ect matching, action recognition, human pose estimation and multiple obje

ct tracking.

Speaker Bio:
Hao Jiang received PhD from Simon
Fraser University in 2006. He was an postdoctoral research fellow in the U

niversity of British Columbia in
2006-2007 and an associate researcher
in Microsoft Research Asia in 1999-2000. He is currently an assistant prof

essor in the computer science department at Boston College. His research in

terests include computer vision, artificial intelligence, multimedia and

graphics.