BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Part Detection and Species Identification - David Jacobs\, Departm
 ent of Computer Science\, University of Maryland
DTSTART:20140318T100000Z
DTEND:20140318T110000Z
UID:TALK51499@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Species identification is an interesting example of fine-grain
 ed classification\, in which an object must be assigned to one of a large 
 number of very similar classes.  It is also a problem with many practical 
 applications that evokes great interest in the general public.  I will des
 cribe a series of work that we have done aimed at using automatic recognit
 ion in field guides for species identification in a variety of domains.\n\
 nOne of the core technical problems in fine-grained classification is the 
 identification of the parts of animals.  This allows us to make meaningful
  comparisons between objects from similar animals.  I will first describe 
 our work on part detection using a non-parametric model of part configurat
 ions called a consensus of exemplars.  We have applied this to the detecti
 on of fiducial points on human faces\, and to the detection of animal part
 s.  Then I will explain how these parts can be used for fine-grained class
 ification of animal species.  We experiment with this approach using dog b
 reeds as a model problem.  The resulting system is displayed in our iphone
  app Dogsnap\, which uses visual classification to determine the breed of 
 dog in a photograph.  Similar ideas have also been used to develop Birdsna
 p\, which also uses species distribution data to provide a practical field
  guide to birds.  Finally\, I will describe our earlier work developing Le
 afsnap\, the first mobile app for identifying plant species using automati
 c visual recognition.   Leafsnap has been downloaded by over a million use
 rs and has been used in many classrooms and in biodiversity studies.\n\nTh
 is work has been done in collaboration with many people at Columbia Univer
 sity and the Smithsonian Institution National Museum of Natural History\n
LOCATION:Small Lecture Theatre\, Microsoft Research Ltd\, 21 Station Road\
 , Cambridge\, CB1 2FB
END:VEVENT
END:VCALENDAR