UTCS Colloquia - Deva Ramanan, Associate Professor, University of California at Irvine, "Training a Computer to See People," ACES 2.302

Contact Name: 
Kristen Grauman
Location: 
ACES 2.302
Date: 
Nov 6, 2012 11:00am - 12:00pm

Sign-up Schedule: http://apps.cs.utexas.edu/talkschedules/cgi/list_events.cgi 

Type of Talk: Colloquium

Speaker/Affiliation: Deva Ramanan, Associate Professor, University of California at Irvine

Talk Audience: UTCS faculty, grads, undergrads

Date/Time: November 6, 2012. 11:00 AM to 12:00 PM (Pre-talk coffee at 10:30 a.m. outside of Avaya.)

Location: ACES 2.302

Host: Kristen Grauman

Talk Title: Training a Computer to See People

Video Recording (available after event): http://mediasite.aces.utexas.edu/UTMediasite/Catalog/Full/8253d475397742258c1a81a0af2a72c021#8253d475397742258c1a81a0af2a72c021/?state=kKAKHhqq9v8JFTGB6IH2&_suid=768

Talk Abstract: 

One of the great, open challenges in machine vision is to train a computer to "see people." A reliable solution opens up tremendous possibilities, from automated persistent surveillance and next-generation image search, to more intuitive computer interfaces. It is difficult to analyze people, and objects in general, because their appearance can vary due to a variety of "nuisance" factors (including viewpoint, body pose, and clothing) and because real-world images contain clutter. I will describe machine learning algorithms that accomplish such tasks by encoding image statistics of the visual world learned from large-scale training data. I will focus on predictive models that produce
rich, structured descriptions of images and videos (How many people are present? What are they doing?) and models that compensate for nuisance factors through the use of latent variables. I will illustrate such approaches for the tasks of object detection, people tracking, and activity recognition, producing state-of-the-art systems as evidenced by recent benchmark competitions.

Speaker Bio:

Deva Ramanan is an associate professor of Computer Science at the University of California at Irvine. Prior to joining UCI, he was a Research Assistant Professor at the Toyota Technological Institute at Chicago. He received his B.S. in computer engineering from the University of Delaware in 2000, graduating summa cum laude. He received his Ph.D. in Electrical Engineering and Computer Science from UC Berkeley in 2005 under the supervision of David Forsyth.

His research interests span computer vision, machine learning, and computer graphics, with a focus on visual recognition. He was awarded the David Marr Prize in 2009, the PASCAL VOC Lifetime Achievement Prize in 2010, an NSF Career Award in 2010, the Outstanding Young Researcher in Image and Vision Computing Award in 2012, and was selected as one of Popular Science's Brilliant 10 researchers in 2012. His work is supported by NSF, ONR, DARPA, as well as industrial collaborations with the Intel Science and Technology Center for Visual Computing, Google Research, and Microsoft Research. He has held visiting researcher positions at the Robotics Institute at CMU, the Visual Geometry Group at Oxford, and has been a consultant for Microsoft and Google.

He serves on the editorial board of the International Journal of Computer Vision (IJCV), serves as associate editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), regularly serves as a senior program committee member for the IEEEConference of Computer Vision and Pattern Recognition (CVPR) and European Conference on Computer Vision (ECCV), and regularly serves on NSF panels for computer vision and machine learning.

Tags: