UTCS Colloquia/AI - Silvio Savarese/University of Michigan, Ann Arbor, "Understanding the 3D World from Images," PAI 3.14

Contact Name: 
Jenna Whitney
PAI 3.14
Sep 7, 2012 11:30am - 12:30pm

There is a sign-up schedule for this event that can be found at http://apps.cs.utexas.edu/talkschedules/cgi/list_events.cgi

Type of Talk: UTCS Colloquia/AI

Speaker/Affiliation: Silvio Savarese/Univers ity of Michigan, Ann Arbor

Talk Audience: UTCS Faculty, Graduate Stu dents, Undergraduate Students, and Outside Interested Parties

Date/Time: Friday, September 7, 2012, 11:00 am

Location: PAI 3.14

Host: Kristen Grauman

Talk Title: Understanding the 3D World from Images

Talk Abstract:
In this talk I will introduce a novel paradigm for jointly addressing two fundamental problems in computer vision: 3D reconstr uction and object recognition. Most of the state-of-the-art methods deal wi th these two tasks separately. Methods for object recognition typically des cribe the scene as a list of object class labels, but are unable to accoun t for their 3D spatial organization. Most of the approaches for 3D scene mo deling produce accurate metric reconstructions but are unable to infer the semantic content of their components. A major line of work from my lab in r ecent years is to explore methodologies that seek to fill this gap and to c oherently describe objects and object components while simultaneously integ rating their 3D spatial arrangement in the scene''s physical space. This re search is relevant to many application areas such as autonomous navigation , robotics, automatic 3D modeling of urban environments and surveillance.

Silvio Savarese is an Assistant Professor of Electrical and Com puter Engineering at the University of Michigan, Ann Arbor. After earning his Ph.D. in Electrical Engineering from the California Institute of Techno logy in 2005, he joined the University of Illinois at Urbana-Champaign fro m 2005 - 2008 as a Beckman Institute Fellow. He is recipient of a TWR Autom otive Endowed Research Award in 2012, an NSF Career Award in 2011 and Goog le Research Award in 2010. In 2002 he was awarded the Walker von Brimer Awa rd for outstanding research initiative. He served as workshops chair and ar ea chair in CVPR 2010, and as area chair in ICCV 2011. He will be an area chair in CVPR 2013. His research interests include computer vision, object recognition and scene understanding, activity recognition, shape represe ntation and reconstruction, human visual perception and visual psychophysics.