BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Parsing Images the UCLA Way - Tom Stepleton (CMU)
DTSTART:20090430T130000Z
DTEND:20090430T143000Z
UID:TALK18074@talks.cam.ac.uk
CONTACT:Shakir Mohamed
DESCRIPTION:2-D images of natural scenes have a hierarchical structure: sc
 enes are made of objects and other large elements\, objects are made of pa
 rts\, parts can be decomposed into textures and other features\, and these
  components in turn yield the pixels we see on the screen. For decades\, c
 omputer vision experts have attempted to create programs that can identify
  this whole-image-explaining structure as easily as humans can\, but only 
 recently have they achieved notable results. In this talk I will review so
 me of the image parsing work of Song-chun Zhu et al. at UCLA. Zhu is argua
 bly one of the most successful of these new photo parsing pioneers\, and m
 y talk will focus on the stochastic grammars and probabilistic inference m
 ethods employed in his work.\n\nMain paper:\nZ. Tu\, X. Chen\, A. Yuille\,
  S. Zhu. Image parsing: unifying segmentation\, detection\, and recognitio
 n. Intl. Journal Comp. Vis. 63(2):113-140\, 2005.\nhttp://www.stat.ucla.ed
 u/%7Esczhu/papers/reprint_IJCV_parsing.pdf\n\nSome material in the talk wi
 ll also touch on the following papers:\nS. Zhu\, D. Mumford\, A stochastic
  grammar of images. Foundations and Trends in Computer Graphics and Vision
  2(4):259-362\, 2007.\nhttp://www.stat.ucla.edu/%7Esczhu/papers/Reprint_Gr
 ammar.pdf\n\nF. Han\, S. Zhu. Bottom-up/top-down image parsing with attrib
 ute grammar. IEEE PAMI\, 31(1)\, 2009\nhttp://www.stat.ucla.edu/%7Esczhu/p
 apers/PAMI_grammar_reprint.pdf\n
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR