BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Thomas Pock (Graz University of Technology)
DTSTART:20210621T133000Z
DTEND:20210621T143000Z
DTSTAMP:20260423T021003Z
UID:OWOS/53
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/OWOS/53/">Le
 arning with Markov Random Field Models for Computer Vision</a>\nby Thomas 
 Pock (Graz University of Technology) as part of One World Optimization sem
 inar\n\n\nAbstract\nIn this talk I will show how learning techniques can b
 e used to significantly improve the quality of discrete Markov Random Fiel
 d (MRF) models. I will start by discussing fast algorithms that combine dy
 namic programming with continuous optimization for solving MRF models. I t
 hen show how their potentials can be learned from data to achieve state-of
 -the-art performance for computer vision tasks such as stereo\, optical fl
 ow and image segmentation.\n\nThe address and password of the zoom room of
  the seminar are sent by e-mail on the mailinglist of the seminar one day 
 before each talk\n
LOCATION:https://researchseminars.org/talk/OWOS/53/
END:VEVENT
END:VCALENDAR