BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Non-Parametric Conditional Random Fields in Computer Vision and Im
 age Processing - Jeremy Jancsary (Microsoft Research Cambridge)
DTSTART:20130808T100000Z
DTEND:20130808T110000Z
UID:TALK46545@talks.cam.ac.uk
CONTACT:Novi Quadrianto
DESCRIPTION:In this talk\, I will discuss ongoing work on non-parametric r
 andom fields at the computer vision group of Microsoft Research Cambridge.
  The models I will present can be considered as conditional random fields\
 , the clique potentials of which depend linearly on the model parameters\,
  but non-linearly on the input features. The main focus of the talk will b
 e on how such non-linear maps from features to clique potentials can be le
 arned efficiently and jointly with the model parameters\, under a common o
 bjective function.  I will present such models for both continuous and dis
 crete output variables\, yielding an empirically successful framework for 
 many structured prediction tasks arising in computer vision and image proc
 essing. The utility of the approach will be exemplified by means of severa
 l applications where our approach achieves state-of-the-art results\, incl
 uding denoising\, deblurring/deconvolution and image inpainting.
LOCATION:Engineering Department\, CBL Room BE-438
END:VEVENT
END:VCALENDAR