Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
Abstract
This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in monocular images. The architecture can exploit structural domain constraints such as geometric relationships between body joint locations. We show that joint training of these two model paradigms improves performance and allows us to significantly outperform existing state-of-the-art techniques.
Cite
Text
Tompson et al. "Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation." Neural Information Processing Systems, 2014.Markdown
[Tompson et al. "Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation." Neural Information Processing Systems, 2014.](https://mlanthology.org/neurips/2014/tompson2014neurips-joint/)BibTeX
@inproceedings{tompson2014neurips-joint,
title = {{Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation}},
author = {Tompson, Jonathan J and Jain, Arjun and LeCun, Yann and Bregler, Christoph},
booktitle = {Neural Information Processing Systems},
year = {2014},
pages = {1799-1807},
url = {https://mlanthology.org/neurips/2014/tompson2014neurips-joint/}
}