[Colloquium] TTI-C Show and Tell Series, Ramanan (1.17.06 @ 12:00 pm)

[Katherine Cumming]

TTI-C SHOW AND TELL SERIES

Presented by:  Toyota Technological Institute at Chicago
 

Speaker: Deva Ramanan, TTI-C
Speaker's home page:  http://www.tti-c.org/ramanan.html


Time: Tuesday, January 17, 2006
Location: TTI-C Conference Room
Lunch Provided @ 12:00pm 
Seminar @ 12:15pm

 

Title: Training Deformable Models for Localization in Images
 

Abstract:  We present a new method for training deformable models.  Assume
that we have training images of objects (say, a horse) where parts have been
labeled.  Typically, one fits a model by maximizing the likelihood of the
part labels.  Alternatively, one could fit a model such that, when the 
model is run on the training images, it finds the parts. We show this
criteria leads to very different models because the objective is
discriminative (rather than generative) and model parameters are jointly
learned (rather than independantly).

We formulate model-learning as parameter estimation in a conditional random
field (CRF); this means we can learn globally optimal parameters by simple
gradient ascent. We present results on three established vision datasets of
motorcyles, people, and horses that achieve or surpass the state-of-the-art.

This is joint work with Cristian Sminchesescu.

----------------------------------------------------------------------------
------

If you have questions, or would like to meet the speaker, please contact
Katherine at 773-834-1994 or kcumming at tti-c.org.   For information on future
TTI-C talks and events, please go to the TTI-C Events page:
http://www.tti-c.org/events.html.  TTI-C (1427 East 60th Street, Chicago, IL
60637)