BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A joint part- and pixel-wise approach to human pose estimation - L
 ubor Ladický\, Oxford Brookes University
DTSTART:20120320T103000Z
DTEND:20120320T113000Z
UID:TALK37048@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:For an object recognition task two standard\, but disparate\, 
 approaches have developed in the field: the first is the part based approa
 ch for layout type problems\, involving optimising an articulated pictoria
 l structure\; the second is the pixel based approach for image labelling i
 nvolving optimising a random field graph defined on the image.\n\nIn this 
 work\, we combine these two models in a principled way in one optimisation
  problem inheriting the advantages of both of them. We apply this formulat
 ion to the problem of detecting humans and estimating their 2D pose in sin
 gle images. In particular\, handling cases of partial visibility where som
 e limbs may be occluded\, a person partially occluding another\, self-occl
 uding or where an image is truncated. Inference method on this joint model
  finds the set of instances of persons in an image\, the location of their
  visible joints\, and a pixel-wise instance and body part labelling.\n
LOCATION:Small lecture theatre\, Microsoft Research Ltd\, 7 J J Thomson Av
 enue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR