English

Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network

Computer Vision and Pattern Recognition 2014-06-16 v1 Machine Learning Neural and Evolutionary Computing

Abstract

We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network. In particular, we simultaneously learn a pose-joint regressor and a sliding-window body-part detector in a deep network architecture. We show that including the body-part detection task helps to regularize the network, directing it to converge to a good solution. We report competitive and state-of-art results on several data sets. We also empirically show that the learned neurons in the middle layer of our network are tuned to localized body parts.

Keywords

Cite

@article{arxiv.1406.3474,
  title  = {Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network},
  author = {Sijin Li and Zhi-Qiang Liu and Antoni B. Chan},
  journal= {arXiv preprint arXiv:1406.3474},
  year   = {2014}
}
R2 v1 2026-06-22T04:37:51.122Z