BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Latent Hough Transform for Object Detection - Nima Razavi\, ETH Zu
 rich and Intern at Microsoft Research Cambridge
DTSTART:20120829T130000Z
DTEND:20120829T140000Z
UID:TALK39304@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Since the invention of the Hough transform (HT) in 1960's\, th
 is method has become a very popular method for object detection. Originall
 y proposed for detecting parametric objects like lines\, circles\, etc.\, 
 HT has been generalized for detecting arbitrary shapes by parameterizing t
 he objects by a reference point\, e.g. the center of mass\, and accumulati
 ng the votes of local image patches for this point. Although this represen
 tation enforces consistency of patches in their relative locations\, it pr
 oduces false positives by combining votes that are consistent in location 
 but inconsistent in other properties like shape\, pose\, color\, etc. whic
 h is the main reason behind the poor performance of these approaches. This
  all raises several questions about the validity of the center as the only
  parametrization of object categories. In particular\, is voting for the c
 enter necessary? What other criteria can be used for voting? Can we learn 
 the optimal properties from data? \n\n  In this talk\, I will propose the 
 Latent Hough Transform (LHT) for enforcing consistency among votes. The id
 ea behind LHT is to augment the Hough transform with latent variables and 
 perform voting in a latent space instead of voting only for location. This
  way\, only votes that agree on the assignment of the latent variables are
  allowed to support a hypothesis.  I will further show how to learn an opt
 imal latent space from training data by exploiting the linearity of the Ho
 ugh transform based methods. Our extensive experiments on challenging obje
 ct detection benchmarks show that our proposed method outperforms traditio
 nal Hough transform based methods and even leads to state-of-the-art resul
 ts on some categories.
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR