VideoMoCo
Official pytorch implementation of paper "VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples" (CVPR 2021).
We propose a novel video representation learning framework named VideoMoCo. It largely improves MoCo with temporally robust feature representation for the video-related classification/recognition scenario, which is novel in terms of both temporal representation learning methodology and video scenario.
The code will be made available to the public soon.