BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Discovering the Structure of Visual Categories from Weak Annotatio
 ns - Subhransu Maji\, Toyota Technological Institute at Chicago
DTSTART:20131108T140000Z
DTEND:20131108T150000Z
UID:TALK48804@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:In order for an automatic system to answer queries like "birds
  with short beaks and blue wings" or "planes with engines on the nose" one
  would expect underlying representations of these categories via their par
 ts and attributes. However\, building such models is challenging because e
 xhaustive labeling of these parts and attributes can be very expensive. In
  this talk I'll present two projects that aim to discover these from weak 
 annotations that can be effectively collected via crowd-sourcing. The firs
 t aims to discover parts that represent discriminative patterns from spars
 e landmark annotations. These parts which we call "poselets"\, examples of
  which include faces of humans\, or wheels of bicycles\, etc.\, can serve 
 as a basis for a range of recognition tasks such as detection\, segmentati
 on\, pose estimation and attribute recognition\, outperforming the state o
 f the art in some. I'll also describe some recent work that simplifies thi
 s annotation task even further\, and extending it to categories for which 
 landmarks are hard to define. The second aims to discover describable attr
 ibutes suitable for fine-grained discrimination. We propose a novel annota
 tion task which consists of asking annotators to describe the differences 
 between images and develop a structured topic model to analyze these descr
 iptions. The output of this are clusters of words into parts and modifiers
 \, and relations between clusters that represent attributes.
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR