A Multi-layer Composite Model for Human Pose Estimation

Kun Duan, Dhruv Batra, and David Crandall

We propose a new approach for part-based human pose estimation using multi-layer composite models, in which each layer is a tree-structured pictorial structure that models pose at a different scale and with a different graphical structure. At the highest level, the submodel acts as a person detector, while at the lowest level, the body is decomposed into a collection of many local parts. Edges between adjacent layers of the composite model encode cross-model constraints. This multi-layer composite model is able to relax the independence assumptions of traditional  tree-structured pictorial-structure models while permitting efficient inference using dual-decomposition. We propose an optimization procedure for joint learning of the entire composite model. Our approach outperforms the state-of-the-art on the challenging Parse and UIUC Sport datasets.

Figure 1: Illustration of our multi-layer composite part-based model.

Papers and presentations

BibTeX entries:

    author = {Duan, Kun and Batra, Dhruv and Crandall, David},
    title = {Human pose estimation through composite multi-layer models},
    journal = {Signal Processing},
    volume = {110},
    pages = {15--26},
    month = {May},
    year = {2015}

    author = {Duan, Kun and Batra, Dhruv and Crandall, David},
    title = {A Multi-layer Composite Model for Human Pose Estimation},
    booktitle = {British Machine Vision Conference (BMVC)},
    year = {2012}


Code available soon!