-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fernando_2021_CVPR, author = {Fernando, Basura and Herath, Samitha}, title = {Anticipating Human Actions by Correlating Past With the Future With Jaccard Similarity Measures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {13224-13233} }
Anticipating Human Actions by Correlating Past With the Future With Jaccard Similarity Measures
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.
Related Material