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.
@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}
}