VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples

1 code implementation • CVPR 2021 • Tian Pan, Yibing Song, Tianyu Yang, Wenhao Jiang, Wei Liu

By empowering the temporal robustness of the encoder and modeling the temporal decay of the keys, our VideoMoCo improves MoCo temporally based on contrastive learning.

Action Recognition Contrastive Learning +1