BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Physics-Based Human Motion Models for Animation and Tracking - Aar
 on Hertzmann\, University of Toronto
DTSTART:20070911T140000Z
DTEND:20070911T150000Z
UID:TALK7940@talks.cam.ac.uk
CONTACT:Oliver Williams
DESCRIPTION: describe physics-based models of human motion\, with applicat
 ions to computer animation and 3D person tracking. I begin by surveying re
 levant principles of motion from the biomechanics literature. I then descr
 ibe a representation of motion that incorporates passive dynamical element
 s\, relative muscle preferences\, and optimality principles. I then descri
 be Nonlinear Inverse Optimization\, a novel learning algorithm that can be
  used to learn these physical models of motion from data. Once learned\, t
 hese models can then be synthesize new animation. I then describe a tracki
 ng algorithm for on-line estimation of 3D human motion from video sequence
 s that makes use of a physics-based prior model of motion. 
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR