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

Sijin LI, Zhi-Qiang Liu, Antoni B. Chan; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2014, pp. 482-489

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.

Related Material


[pdf]
[bibtex]
@InProceedings{LI_2014_CVPR_Workshops,
author = {LI, Sijin and Liu, Zhi-Qiang and Chan, Antoni B.},
title = {Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2014}
}