Discriminative hierarchical part-based models for human parsing and action recognition

Yan Wang, Duan Tran, Zicheng Liao, David Forsyth

Research output: Contribution to journalArticlepeer-review


We consider the problem of parsing human poses and recognizing their actions in static images 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. In this paper, we introduce hierarchical poselets-a new representation for modeling the pose configuration of human bodies. 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. The hierarchical poselets are organized in a hierarchical way via a structured model. Human parsing can be achieved by inferring the optimal labeling of this hierarchical model. The pose information captured by this hierarchical model can also be used as a intermediate representation for other high-level tasks. We demonstrate it in action recognition from static images.

Original languageEnglish (US)
Pages (from-to)3075-3102
Number of pages28
JournalJournal of Machine Learning Research
StatePublished - Oct 2012


  • Action recognition
  • Hierarchical poselets
  • Human parsing
  • Maxmargin structured learning
  • Part-based models

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence


Dive into the research topics of 'Discriminative hierarchical part-based models for human parsing and action recognition'. Together they form a unique fingerprint.

Cite this