In this paper, we propose a new, simple, and effective Self-supervised Spatio-temporal Transformers (SPARTAN) approach to Group Activity Recognition (GAR) using unlabeled video data. Given a video, we create local and global Spatio-temporal views with varying spatial patch sizes and frame rates. The proposed self-supervised objective aims to match the features of these contrasting views representing the same video to be consistent with the variations in spatiotemporal domains. To the best of our knowledge, the proposed mechanism is one of the first works to alleviate the weakly supervised setting of GAR using the encoders in video transformers. Furthermore, using the advantage of transformer models, our proposed approach supports long-term relationship modeling along spatio-temporal dimensions. The proposed SPARTAN approach performs well on two group activity recognition benchmarks, including NBA and Volleyball datasets, by surpassing the state-of-the-art results by a significant margin in terms of MCA and MPCA metrics.
The details of our source code will be available soon.
This work is supported by Arkansas Biosciences Institute (ABI) Grant, NSF WVAR-CRESH and NSF Data Science, Data Analytics that are Robust and Trusted (DART).
If you find this code useful for your research, please consider citing:
@misc{chappa2023spartan,
title={SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognition},
author={Naga VS Raviteja Chappa and Pha Nguyen and Alexander H Nelson and Han-Seok Seo and Xin Li and Page Daniel Dobbs and Khoa Luu},
year={2023},
eprint={2303.12149},
archivePrefix={arXiv},
primaryClass={cs.CV}
}