Self-Supervised Spatiotemporal Representation Learning by Exploiting Video Continuity


  • Hanwen Liang Huawei Noah's Ark Laboratory
  • Niamul Quader Huawei Noah's Ark Laboratory
  • Zhixiang Chi Huawei Noah's Ark Laboratory
  • Lizhe Chen Huawei Noah's Ark Laboratory
  • Peng Dai Huawei Noah's Ark Laboratory
  • Juwei Lu Huawei Noah's Ark Laboratory
  • Yang Wang Huawei Noah's Ark Laboratory University of Manitoba, Canada



Computer Vision (CV), Machine Learning (ML)


Recent self-supervised video representation learning methods have found significant success by exploring essential properties of videos, e.g. speed, temporal order, etc. This work exploits an essential yet under-explored property of videos, the \textit{video continuity}, to obtain supervision signals for self-supervised representation learning. Specifically, we formulate three novel continuity-related pretext tasks, i.e. continuity justification, discontinuity localization, and missing section approximation, that jointly supervise a shared backbone for video representation learning. This self-supervision approach, termed as Continuity Perception Network (CPNet), solves the three tasks altogether and encourages the backbone network to learn local and long-ranged motion and context representations. It outperforms prior arts on multiple downstream tasks, such as action recognition, video retrieval, and action localization. Additionally, the video continuity can be complementary to other coarse-grained video properties for representation learning, and integrating the proposed pretext task to prior arts can yield much performance gains.




How to Cite

Liang, H., Quader, N., Chi, Z., Chen, L., Dai, P., Lu, J., & Wang, Y. (2022). Self-Supervised Spatiotemporal Representation Learning by Exploiting Video Continuity. Proceedings of the AAAI Conference on Artificial Intelligence, 36(2), 1564-1573.



AAAI Technical Track on Computer Vision II