Sciweavers

Share
CVPR
2011
IEEE

Action Recognition from a Distributed Representation of Pose and Appearance

8 years 2 months ago
Action Recognition from a Distributed Representation of Pose and Appearance
We present a distributed representation of pose and appearance of people called the “poselet activation vector”. First we show that this representation can be used to estimate the pose of people defined by the 3D orientations of the head and torso in the challenging PASCAL VOC 2010 person detection dataset. Our method is robust to clutter, aspect and viewpoint variation and works even when body parts like faces and limbs are occluded or hard to localize. We combine this representation with other sources of information like interaction with objects and other people in the image and use it for action recognition. We report competitive results on the PASCAL VOC 2010 static image action classification challenge.
Subhransu Maji, Lubomir Bourdev, Jitendra Malik
Added 05 Apr 2011
Updated 29 Apr 2011
Type Journal
Year 2011
Where CVPR
Authors Subhransu Maji, Lubomir Bourdev, Jitendra Malik
Comments (0)
books