ML Anthology

Anticipating Human Actions by Correlating past with the Future with Jaccard Similarity Measures

Basura Fernando, Samitha Herath
CVPR 2021 pp. 13224-13233
doi:10.1109/CVPR46437.2021.01302 /cvpr/2021/fernando2021cvpr-anticipating/

Abstract

We propose a framework for early action recognition and anticipation by correlating past features with the future using three novel similarity measures called Jaccard vector similarity, Jaccard cross-correlation and Jaccard Frobenius inner product over covariances. Using these combinations of novel losses and using our framework, we obtain state-of-the-art results for early action recognition in UCF101 and JHMDB datasets by obtaining 91.7 % and 83.5 % accuracy respectively for an observation percentage of 20. Similarly, we obtain state-of-the-art results for Epic-Kitchen55 and Breakfast datasets for action anticipation by obtaining 20.35 and 41.8 top-1 accuracy respectively.

PDF CVPR Semantic Scholar

Cite

Text

Fernando and Herath. "Anticipating Human Actions by Correlating past with the Future with Jaccard Similarity Measures." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.01302

Markdown

[Fernando and Herath. "Anticipating Human Actions by Correlating past with the Future with Jaccard Similarity Measures." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/fernando2021cvpr-anticipating/) doi:10.1109/CVPR46437.2021.01302

BibTeX

@inproceedings{fernando2021cvpr-anticipating,
  title     = {{Anticipating Human Actions by Correlating past with the Future with Jaccard Similarity Measures}},
  author    = {Fernando, Basura and Herath, Samitha},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  pages     = {13224-13233},
  doi       = {10.1109/CVPR46437.2021.01302},
  url       = {https://mlanthology.org/cvpr/2021/fernando2021cvpr-anticipating/}
}