38 search results - page 8 / 8 » Relevant subtask learning by constrained mixture models |
CIVR
2007
Springer
13 years 11 months ago
2007
Springer
Online image repositories such as Flickr contain hundreds of millions of images and are growing quickly. Along with that the needs for supporting indexing, searching and browsing ...
CVPR
2009
IEEE
15 years 16 hour ago
2009
IEEE
This paper exploits the context of natural dynamic scenes
for human action recognition in video. Human actions
are frequently constrained by the purpose and the physical
propert...
PAMI
2006
13 years 4 months ago
2006
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pri...