International Journal of Computer Vision

, Volume 93, Issue 1, pp 1–21

Max Margin Learning of Hierarchical Configural Deformable Templates (HCDTs) for Efficient Object Parsing and Pose Estimation

  • Long (Leo) Zhu
  • Yuanhao Chen
  • Chenxi Lin
  • Alan Yuille
Open Access
Article

DOI: 10.1007/s11263-010-0375-1

Cite this article as:
Zhu, L.., Chen, Y., Lin, C. et al. Int J Comput Vis (2011) 93: 1. doi:10.1007/s11263-010-0375-1

Abstract

In this paper we formulate a hierarchical configurable deformable template (HCDT) to model articulated visual objects—such as horses and baseball players—for tasks such as parsing, segmentation, and pose estimation. HCDTs represent an object by an AND/OR graph where the OR nodes act as switches which enables the graph topology to vary adaptively. This hierarchical representation is compositional and the node variables represent positions and properties of subparts of the object. The graph and the node variables are required to obey the summarization principle which enables an efficient compositional inference algorithm to rapidly estimate the state of the HCDT. We specify the structure of the AND/OR graph of the HCDT by hand and learn the model parameters discriminatively by extending Max-Margin learning to AND/OR graphs. We illustrate the three main aspects of HCDTs—representation, inference, and learning—on the tasks of segmenting, parsing, and pose (configuration) estimation for horses and humans. We demonstrate that the inference algorithm is fast and that max-margin learning is effective. We show that HCDTs gives state of the art results for segmentation and pose estimation when compared to other methods on benchmarked datasets.

Keywords

Hierarchy Shape representation Object parsing Segmentation Structure learning Max margin 
Download to read the full article text

Copyright information

© The Author(s) 2010

Authors and Affiliations

  • Long (Leo) Zhu
    • 1
  • Yuanhao Chen
    • 2
  • Chenxi Lin
    • 3
  • Alan Yuille
    • 4
  1. 1.Department of StatisticsUniversity of California at Los AngelesLos AngelesUSA
  2. 2.University of Science and Technology of ChinaHefeiP.R. China
  3. 3.Alibaba Group R&DHangzhouP.R. China
  4. 4.Department of StatisticsPsychology and Computer Science, University of California at Los AngelesLos AngelesUSA

Personalised recommendations