This paper introduces a novel approach to Social Group Activity Recognition (SoGAR) using Self-supervised Transformers network that can effectively utilize unlabeled video data. To extract spatio-temporal information, we created local and global views with varying frame rates. Our self-supervised objective ensures that features extracted from contrasting views of the same video were consistent across spatio-temporal domains. Our proposed approach is efficient in using transformer-based encoders to alleviate the weakly supervised setting of group activity recognition. By leveraging the benefits of transformer models, our approach can model long-term relationships along spatio-temporal dimensions. Our proposed SoGAR method achieved state-of-the-art results on three group activity recognition benchmarks, namely JRDB-PAR, NBA, and Volleyball datasets, surpassing the current numbers in terms of F1-score, MCA, and MPCA metrics.
@article{arxiv.2305.06310,
title = {SoGAR: Self-supervised Spatiotemporal Attention-based Social 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},
journal= {arXiv preprint arXiv:2305.06310},
year = {2024}
}
Comments
Under review for IEEE Access journal; 12 pages, 7 figures. arXiv admin note: text overlap with arXiv:2303.12149