CVPR 2011 (2011)
June 20, 2011 to June 25, 2011
Yang Wang , Dept. of Comput. Sci., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Duan Tran , Dept. of Comput. Sci., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Zicheng Liao , Dept. of Comput. Sci., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
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.
max-margin framework, hierarchical poselets, human parsing, part-based model, rigid parts, human anatomy, structured model
Duan Tran, Zicheng Liao and Yang Wang, "Learning hierarchical poselets for human parsing," CVPR 2011(CVPR), Providence, RI, 2011, pp. 1705-1712.