In this paper, we propose self-supervised training for video transformers using unlabeled video data. From a given video, we create local and global spatiotemporal views with varying spatial sizes and frame rates. Our self-supervised objective seeks to match the features of these different views representing the same video, to be invariant to spatiotemporal variations in actions. To the best of our knowledge, the proposed approach is the first to alleviate the dependency on negative samples or dedicated memory banks in Self-supervised Video Transformer (SVT). Further, owing to the flexibility of Transformer models, SVT supports slow-fast video processing within a single architecture using dynamically adjusted positional encoding and supports long-term relationship modeling along spatiotemporal dimensions. Our approach performs well on four action recognition benchmarks (Kinetics-400, UCF-101, HMDB-51, and SSv2) and converges faster with small batch sizes. Code: https://git.io/J1juJ
@article{arxiv.2112.01514,
title = {Self-supervised Video Transformer},
author = {Kanchana Ranasinghe and Muzammal Naseer and Salman Khan and Fahad Shahbaz Khan and Michael Ryoo},
journal= {arXiv preprint arXiv:2112.01514},
year = {2022}
}