A Flow Model for Joint Action Recognition and Identity Maintenance

Sameh Khamis, Vlad I. Morariu, Larry S. Davis

CVPR 2012 pp. 1218-1225

doi:10.1109/CVPR.2012.6247804 /cvpr/2012/khamis2012cvpr-flow/

Abstract

We propose a framework that performs action recognition and identity maintenance of multiple targets simultaneously. Instead of first establishing tracks using an appearance model and then performing action recognition, we construct a network flow-based model that links detected bounding boxes across video frames while inferring activities, thus integrating identity maintenance and action recognition. Inference in our model reduces to a constrained minimum cost flow problem, which we solve exactly and efficiently. By leveraging both appearance similarity and action transition likelihoods, our model improves on state-of-the-art results on action recognition for two datasets.

PDF CVPR Semantic Scholar

Cite

Text

Khamis et al. "A Flow Model for Joint Action Recognition and Identity Maintenance." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6247804

Markdown

[Khamis et al. "A Flow Model for Joint Action Recognition and Identity Maintenance." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/khamis2012cvpr-flow/) doi:10.1109/CVPR.2012.6247804

BibTeX

@inproceedings{khamis2012cvpr-flow,
  title     = {{A Flow Model for Joint Action Recognition and Identity Maintenance}},
  author    = {Khamis, Sameh and Morariu, Vlad I. and Davis, Larry S.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {1218-1225},
  doi       = {10.1109/CVPR.2012.6247804},
  url       = {https://mlanthology.org/cvpr/2012/khamis2012cvpr-flow/}
}