BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The persistence of structure: Layers\, time\, and the estimation o
 f optical flow - Michael J. Black \, Max Planck Institute for Intelligent 
 Systems
DTSTART:20140130T140000Z
DTEND:20140130T150000Z
UID:TALK50632@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Optical flow represents the apparent 2D motion of the 3D world
  as captured in a sequence of video frames.  This flow is related to physi
 cal structure in the world and is useful for applications as diverse as ro
 bot navigation\, human motion understanding\, and video compression. This 
 talk will review several recent advances that have led to significant impr
 ovements in optical flow accuracy and will explore the principles behind t
 hese.  Long range spatial correlations in the optical flow prove particula
 rly important to model and several methods for doing so will be presented.
   Among these\, layered models of the scene prove particularly useful beca
 use the spatial correlations are captured by the per-pixel layer assignmen
 t\, the layers capture the occlusion relationships in the scene\, and the 
 motion within layers can be fairly simply described.  Additionally\, tempo
 ral coherence is important to understand occlusion boundaries and what is 
 consistent over time is not the motion but the scene structure represented
  by the layers.  The talk will also introduce the MPI-Sintel dataset\, whi
 ch provides a challenging benchmark for flow algorithms and reveals curren
 t limitations.  Finally\, the talk will show that optical flow is now accu
 rate enough to enable applications such as human motion analysis. In parti
 cular\, the talk will introduce "flowing puppets" that use optical flow to
  improve 2D body pose estimation.\n\nThis is joint work with many co-autho
 rs\, including Deqing Sun\, Stefan Roth\, Erik Sudderth\, Jonas Wulff\, Si
 lvia Zuffi\, Javier Romero\,  Dan Butler\, Hans-Peter Pfister\, and Cordel
 ia Schmid.\n\nRelated papers:  \n\nA Quantitative Analysis of Current Prac
 tices in Optical Flow Estimation and the Principles behind Them\, IJCV'13\
 nhttp://link.springer.com/content/pdf/10.1007%2Fs11263-013-0644-x.pdf\n\nA
  fully-connected layered model of foreground and background flow\, CVPR'13
 \nhttp://files.is.tue.mpg.de/black/papers/SunCVPR2013.pdf\n\nLayered segme
 ntation and optical flow estimation over time\, CVPR'12\nhttp://www.cs.bro
 wn.edu/~dqsun/pubs/cvpr_2012_layer.pdf\n\nA naturalistic open source movie
  for optical flow evaluation\, ECCV'12\nhttp://files.is.tue.mpg.de/black/p
 apers/ButlerECCV2012-corrected.pdf\n\nEstimating human pose with flowing p
 uppets\, ICCV'13 \nhttp://files.is.tue.mpg.de/black/papers/ZuffiICCV2013.p
 df 
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR