Curvature: A Signature for Action Recognition in Video Sequences
Abstract
In this paper, a novel signature of human action recognition, namely the curvature of a video sequence, is introduced. In this way, the distribution of sequential data is modeled, which enables few-shot learning. Instead of depending on recognizing features within images, our algorithm views actions as sequences on the universal time scale across a whole sequence of images. The video sequence, viewed as a curve in pixel space, is aligned by reparameterization using the arclength of the curve in pixel space. Once such curvatures are obtained, statistical indexes are extracted and fed into a learning-based classifier. Overall, our method is simple but powerful. Preliminary experimental results show that our method is effective and achieves state-of-the-art performance in video-based human action recognition.
Cite
Text
Chen and Chirikjian. "Curvature: A Signature for Action Recognition in Video Sequences." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00437Markdown
[Chen and Chirikjian. "Curvature: A Signature for Action Recognition in Video Sequences." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/chen2020cvprw-curvature/) doi:10.1109/CVPRW50498.2020.00437BibTeX
@inproceedings{chen2020cvprw-curvature,
title = {{Curvature: A Signature for Action Recognition in Video Sequences}},
author = {Chen, He and Chirikjian, Gregory S.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {3752-3759},
doi = {10.1109/CVPRW50498.2020.00437},
url = {https://mlanthology.org/cvprw/2020/chen2020cvprw-curvature/}
}