DMCA
Articulated pose estimation with flexible mixturesof-parts
| Venue: | In CVPR |
| Citations: | 179 - 8 self |
BibTeX
@INPROCEEDINGS{Yang_articulatedpose,
author = {Yi Yang and Deva Ramanan},
title = {Articulated pose estimation with flexible mixturesof-parts},
booktitle = {In CVPR},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We describe a method for human pose estimation in static images based on a novel representation of part mod-els. Notably, we do not use articulated limb parts, but rather capture orientation with a mixture of templates for each part. We describe a general, flexible mixture model for capturing contextual co-occurrence relations between parts, augmenting standard spring models that encode spa-tial relations. We show that such relations can capture no-tions of local rigidity. When co-occurrence and spatial rela-tions are tree-structured, our model can be efficiently opti-mized with dynamic programming. We present experimental results on standard benchmarks for pose estimation that in-dicate our approach is the state-of-the-art system for pose estimation, outperforming past work by 50 % while being orders of magnitude faster. 1.
Keyphrases
pose estimation flexible mixturesof-parts standard spring model past work dynamic programming part mod-els standard benchmark capture orientation magnitude faster articulated limb part state-of-the-art system contextual co-occurrence relation static image flexible mixture model present experimental result spatial rela-tions encode spa-tial relation human pose estimation local rigidity novel representation
