Max-Margin Hidden Conditional Random Fields for Human Action Recognition
Abstract
We present a new method for classification with structured latent variables. Our model is formulated using the max-margin formalism in the discriminative learning literature. We propose an efficient learning algorithm based on the cutting plane method and decomposed dual optimization. We apply our model to the problem of recognizing human actions from video sequences, where we model a human action as a global root template and a constellation of several "parts". We show that our model outperforms another similar method that uses hidden conditional random fields, and is comparable to other state-of-the-art approaches. More importantly, our proposed work is quite general and can potentially be applied in a wide variety of vision problems that involve various complex, interdependent latent structures.
Cite
Text
Wang and Mori. "Max-Margin Hidden Conditional Random Fields for Human Action Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009. doi:10.1109/CVPR.2009.5206709Markdown
[Wang and Mori. "Max-Margin Hidden Conditional Random Fields for Human Action Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009.](https://mlanthology.org/cvpr/2009/wang2009cvpr-max/) doi:10.1109/CVPR.2009.5206709BibTeX
@inproceedings{wang2009cvpr-max,
title = {{Max-Margin Hidden Conditional Random Fields for Human Action Recognition}},
author = {Wang, Yang and Mori, Greg},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2009},
pages = {872-879},
doi = {10.1109/CVPR.2009.5206709},
url = {https://mlanthology.org/cvpr/2009/wang2009cvpr-max/}
}