Learning hierarchical poselets for human parsing
- 1 June 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1705-1712
Abstract
We consider the problem of human parsing with part-based models. Most previous work in part-based models only considers rigid parts (e.g. torso, head, half limbs) guided by human anatomy. We argue that this representation of parts is not necessarily appropriate for human parsing. In this paper, we introduce hierarchical poselets-a new representation for human parsing. Hierarchical poselets can be rigid parts, but they can also be parts that cover large portions of human bodies (e.g. torso + left arm). In the extreme case, they can be the whole bodies. We develop a structured model to organize poselets in a hierarchical way and learn the model parameters in a max-margin framework. We demonstrate the superior performance of our proposed approach on two datasets with aggressive pose variations.Keywords
This publication has 14 references indexed in Scilit:
- Fast globally optimal 2D human detection with loopy graph models2010
- Recognizing human actions from still images with latent poses2010
- Adaptive pose priors for pictorial structures2010
- Pictorial structures revisited: People detection and articulated pose estimation2009
- Cutting-plane training of structural SVMsMachine Learning, 2009
- Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation2006
- Strike a Pose: Tracking People by Finding Stylized Poses2005
- Guiding model search using segmentation2005
- Fast pose estimation with parameter-sensitive hashing2003
- Cardboard people: a parameterized model of articulated image motion2002