BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Research of the new Computer Vision and Mulitmodal Computing at MP
 I Sarrbruecken - Bernt Schiele\, MPI Saarbrueck
DTSTART:20110330T130000Z
DTEND:20110330T140000Z
UID:TALK30516@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:This talk overviews our recent work both in computer vision an
 d multimodal computing.\nObject class recognition is one of the most funda
 mental problems in computer vision and I will discuss several approaches w
 e have been developing. One of these approaches is based on a shape-based 
 model for object class detection that enables explicit knowledge transfer 
 between object classes. Another important problem in computer vision is pe
 ople detection and tracking. In our work we have aimed to integrate detect
 ion and tracking into a common framework that has been recently extended t
 o articulated pose estimation.\nIn the second part of the talk I highlight
  three approaches to enable activity and gesture recognition in realistic 
 scenarios using wearable sensors: the first address the unsupervised disco
 very of daily routines\; the second introduces a novel body-model based hu
 man activity recognition approach\; and the third discusses an approach fo
 r mobile gesture recognition.
LOCATION:Small lecture theatre\, Microsoft Research Ltd\, 7 J J Thomson Av
 enue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR