UTCS Distinguished Lecturer: Daphne Koller/Stanford University: "Probabilistic Models for Holistic Scene Understanding" ACES 2.302, Tuesday, April 14, 2009 11:00 a.m.

Contact Name: 
Jenna Whitney
Date: 
Apr 14, 2009 11:00am - 12:00pm

There is a sign up schedule for this event:

http://www

.cs.utexas.edu/department/webevent/utcs/events/cgi/eidshow.cgi?person=Daphn

eKoller

Type of Talk:  UTCS Distinguished Lecturer

Speak

er/Affiliation:  Daphne Koller/Stanford University

Date/Time:&n

bsp; Tuesday, April 14, 2009 11:00 a.m.

Location:  ACES 2.30

2

Host: J. Strother Moore

Talk Title:  "Probabilist

ic Models for Holistic Scene Understanding"

Talk Abstract:

Over recent years, computer vision has made great strides towards annot

ating parts of an image with symbolic labels, such as object categories (t

hings) or segment types (stuff). However, we are still far from the goal o

f providing a semantic description of an image, such as "a man, wal

king a dog on a sidewalk, carrying a backpack".  In this talk

, I will describe some projects we have done that attempt to use probabilis

tic models to move us closer towards the goal.

The first part of
the talk will present methods that use a more holistic  scene analys

is to improve our performance at core tasks such as object detection, segm

entation, or 3D reconstruction.   The second part of the talk

will focus on finer-grained modeling of object shape, so as to allow us to
annotate images with descriptive labels related to the object shape, pose

, or activity (e.g., is a cheetah running or standing).   The

se vision tasks rely on novel algorithms for core problems in machine learn

ing and probabilistic models, such as
efficient algorithms for probab

ilistic correspondence, transfer learning across related object classes fo

r learning from sparse data, and more.

Speaker Bio:
Daphne
Koller is a Professor of Computer Science at Stanford University.  H

er main research focus is in developing and using machine learning and prob

abilistic methods to model and analyze complex systems, and she is particu

larly interested in using these techniques to understand biological systems
and the world around us. Professor Koller is the author of over 100 refere

ed publications, which have appeared in venues that include Science, Natu

re Genetics, and the Journal of Games and Economic Behavior.  She is
a Fellow of
the American Association for Artificial Intelligence, an

d has received a number of awards, including the Sloan Foundation Faculty

Fellowship in 1996, the ONR Young Investigator Award in 1998, the Preside

ntial Early Career Award for Scientists and Engineers (PECASE) from Preside

nt Clinton in 1999, the IJCAI Computers and Thought Award in 2001, the Co

x Medal for excellence in fostering undergraduate research at Stanford in 2

003,  the MacArthur Foundation Fellowship in 2004 and the first-ever
ACM/Infosys award in 2008.