BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Graph algorithms for more efficient inference in 1st-order and hig
 her-order MRF's - Professor Ramin Zabih\, Cornell University
DTSTART:20150811T130000Z
DTEND:20150811T140000Z
UID:TALK60361@talks.cam.ac.uk
CONTACT:12852
DESCRIPTION:Efficient inference is a major challenge for the MRF's that ar
 ise in computer vision.\nMost such MRF's are 1st-order\, and are typically
  solved with methods like message \npassing or graph cuts. I will present 
 a new preprocessing technique for 1st-order\nMRF's that makes widely used 
 graph cut methods an order of magnitude more\nefficient. Higher-order MRF'
 s are very powerful\, but present a much more difficult \nchallenge\; I wi
 ll describe techniques based on a variant of submodular flow that\ncan per
 form efficient inference over some important higher-order priors.\n
LOCATION:Engineering Department - Lecture Room - LR4
END:VEVENT
END:VCALENDAR