Understanding Action Recognition in Still Images
Abstract
Action recognition in still images is closely related to various other computer vision tasks such as pose estimation, object recognition, image retrieval, video action recognition and frame tagging in videos. This problem is focused on recognizing a person’s action or behavior using a single frame. Unlike action recognition in videos - a relatively very well established area of research where spatio-temporal features are used, these are not available for still images, making the problem more challenging. In the present work only actions that involve objects are considered. A complex action is broken down into components based on semantics. The importance of each of these components in action recognition is systematically studied.
Cite
Text
Girish et al. "Understanding Action Recognition in Still Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00193Markdown
[Girish et al. "Understanding Action Recognition in Still Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/girish2020cvprw-understanding/) doi:10.1109/CVPRW50498.2020.00193BibTeX
@inproceedings{girish2020cvprw-understanding,
title = {{Understanding Action Recognition in Still Images}},
author = {Girish, Deeptha and Singh, Vineeta and Ralescu, Anca L.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {1523-1529},
doi = {10.1109/CVPRW50498.2020.00193},
url = {https://mlanthology.org/cvprw/2020/girish2020cvprw-understanding/}
}