DMCA
Poselet conditioned pictorial structures (2013)
Cached
Download Links
| Venue: | In CVPR |
| Citations: | 22 - 4 self |
BibTeX
@INPROCEEDINGS{Pishchulin13poseletconditioned,
author = {Leonid Pishchulin and Mykhaylo Andriluka and Peter Gehler and Bernt Schiele},
title = {Poselet conditioned pictorial structures},
booktitle = {In CVPR},
year = {2013}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper we consider the challenging problem of ar-ticulated human pose estimation in still images. We observe that despite high variability of the body articulations, hu-man motions and activities often simultaneously constrain the positions of multiple body parts. Modelling such higher order part dependencies seemingly comes at a cost of more expensive inference, which resulted in their limited use in state-of-the-art methods. In this paper we propose a model that incorporates higher order part dependencies while re-maining efficient. We achieve this by defining a conditional model in which all body parts are connected a-priori, but which becomes a tractable tree-structured pictorial struc-tures model once the image observations are available. In order to derive a set of conditioning variables we rely on the poselet-based features that have been shown to be effective for people detection but have so far found limited appli-cation for articulated human pose estimation. We demon-strate the effectiveness of our approach on three publicly available pose estimation benchmarks improving or being on-par with state of the art in each case. 1.
Keyphrases
pictorial structure poselet-based feature multiple body part body part state-of-the-art method expensive inference limited appli-cation challenging problem articulated human pose estimation re-maining efficient conditional model high variability tractable tree-structured pictorial struc-tures model limited use people detection hu-man motion body articulation ar-ticulated human pose estimation available pose estimation benchmark image observation order part dependency order part
