Self-Supervised Video Transformer

Kanchana Ranasinghe, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan, Michael S. Ryoo; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 2874-2884


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 is available at:

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Ranasinghe_2022_CVPR, author = {Ranasinghe, Kanchana and Naseer, Muzammal and Khan, Salman and Khan, Fahad Shahbaz and Ryoo, Michael S.}, title = {Self-Supervised Video Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2874-2884} }