ML Anthology

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

Sijin Li, Zhi-Qiang Liu, Antoni B. Chan
CVPRW 2014 pp. 488-495
doi:10.1109/CVPRW.2014.78 /cvprw/2014/li2014cvprw-heterogeneous/

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.

CVPRW Semantic Scholar

Cite

Text

Li et al. "Heterogeneous Multi-Task Learning for Human Pose Estimation with Deep Convolutional Neural Network." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2014. doi:10.1109/CVPRW.2014.78

Markdown

[Li et al. "Heterogeneous Multi-Task Learning for Human Pose Estimation with Deep Convolutional Neural Network." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2014.](https://mlanthology.org/cvprw/2014/li2014cvprw-heterogeneous/) doi:10.1109/CVPRW.2014.78

BibTeX

@inproceedings{li2014cvprw-heterogeneous,
  title     = {{Heterogeneous Multi-Task Learning for Human Pose Estimation with Deep Convolutional Neural Network}},
  author    = {Li, Sijin and Liu, Zhi-Qiang and Chan, Antoni B.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2014},
  pages     = {488-495},
  doi       = {10.1109/CVPRW.2014.78},
  url       = {https://mlanthology.org/cvprw/2014/li2014cvprw-heterogeneous/}
}