DMCA
Detecting actions, poses, and objects with relational phraselets. ECCV (2012)
Cached
Download Links
| Citations: | 34 - 3 self |
BibTeX
@MISC{Desai12detectingactions,,
author = {Chaitanya Desai and Deva Ramanan},
title = {Detecting actions, poses, and objects with relational phraselets. ECCV},
year = {2012}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. We present a novel approach to modeling human pose, together with interacting objects, based on compositional models of local visual interactions and their relations. Skeleton models, while flexible enough to capture large articulations, fail to accurately model selfocclusions and interactions. Poselets and Visual Phrases address this limitation, but do so at the expense of requiring a large set of templates. We combine all three approaches with a compositional model that is flexible enough to model detailed articulations but still captures occlusions and object interactions. Unlike much previous work on action classification, we do not assume test images are labeled with a person, and instead present results for “action detection ” in an unlabeled image. Notably, for each detection, our model reports back a detailed description including an action label, articulated human pose, object poses, and occlusion flags. We demonstrate that modeling occlusion is crucial for recognizing human-object interactions. We present results on the PASCAL Action
Keyphrases
relational phraselets human pose present result compositional model detailed articulation human-object interaction unlabeled image action detection novel approach pascal action action label action classification visual phrase address model report large articulation object pose local visual interaction skeleton model detailed description test image large set object interaction interacting object occlusion flag much previous work
