Recognizing Human Actions from Still Images with Latent Poses
Abstract
We consider the problem of recognizing human actions from still images. We propose a novel approach that treats the pose of the person in the image as latent variables that will help with recognition. Different from other work that learns separate systems for pose estimation and action recognition, then combines them in an ad-hoc fashion, our system is trained in an integrated fashion that jointly considers poses and actions. Our learning objective is designed to directly exploit the pose information for action recognition. Our experimental results demonstrate that by inferring the latent poses, we can improve the final action recognition results.
Cite
Text
Yang et al. "Recognizing Human Actions from Still Images with Latent Poses." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5539879Markdown
[Yang et al. "Recognizing Human Actions from Still Images with Latent Poses." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/yang2010cvpr-recognizing/) doi:10.1109/CVPR.2010.5539879BibTeX
@inproceedings{yang2010cvpr-recognizing,
title = {{Recognizing Human Actions from Still Images with Latent Poses}},
author = {Yang, Weilong and Wang, Yang and Mori, Greg},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2010},
pages = {2030-2037},
doi = {10.1109/CVPR.2010.5539879},
url = {https://mlanthology.org/cvpr/2010/yang2010cvpr-recognizing/}
}