Backing off: hierarchical decomposition of activity for 3D novel pose recovery

For model-based 3D human pose estimation, even simple models of the human body lead to high-dimensional state spaces. Where the class of activity is known a priori, low-dimensional activity models learned from training data make possible a thorough and efficient search for the best pose. Conversely,...

Full description

Bibliographic Details

Main Authors:	John Darby, Baihua Li, Nicholas Costen, David Fleet, Neil Lawrence
Format:	Default Conference proceeding
Published:	2009
Subjects:	Other information and computing sciences not elsewhere classified untagged Information and Computing Sciences not elsewhere classified
Online Access:	https://hdl.handle.net/2134/20286
Tags:	Add Tag No Tags, Be the first to tag this record!