BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Strategies for General Recognition - Derek Hoiem\, University of I
 llinois at Urbana-Champaign
DTSTART:20130820T123000Z
DTEND:20130820T133000Z
UID:TALK46662@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:One of the major challenges in computer vision is general reco
 gnition\, the ability to infer useful properties of objects within sight. 
 It's a slippery problem whose solution depends on the details of a particu
 lar situation -- what do I want to know\, what kind of object\, how simila
 r to those I have seen before. I'll present the work from my group over th
 e past few years on how to organize and infer knowledge of objects\, with 
 a focus on generalizing to new types of objects\, providing details\, and 
 learning models of parts. I will highlight some lessons learned and also p
 oint to problems uncovered.
LOCATION:Microsoft Research Ltd\, 21 Station Road\, Cambridge\, CB1 2FB
END:VEVENT
END:VCALENDAR