Papers › Motion-aware Contrastive Video Representation Learning via Foreground-background Merging

Motion-aware Contrastive Video Representation Learning via Foreground-background Merging

30 Sep 2021CVPR 2022 1arXiv:2109.15130archive 2025-07-28

Shuangrui Ding, Maomao Li, Tianyu Yang, Rui Qian, Haohang Xu, Qingyi Chen, Jue Wang, Hongkai Xiong

In light of the success of contrastive learning in the image domain, current self-supervised video representation learning methods usually employ contrastive loss to facilitate video representation learning. When naively pulling two augmented views of a video closer, the model however tends to learn the common static background as a shortcut but fails to capture the motion information, a phenomenon dubbed as background bias. Such bias makes the model suffer from weak generalization ability, leading to worse performance on downstream tasks such as action recognition. To alleviate such bias, we propose \textbf{F}oreground-b\textbf{a}ckground \textbf{Me}rging (FAME) to deliberately compose the moving foreground region of the selected video onto the static background of others. Specifically, without any off-the-shelf detector, we extract the moving foreground out of background regions via the frame difference and color statistics, and shuffle the background regions among the videos. By leveraging the semantic consistency between the original clips and the fused ones, the model focuses more on the motion patterns and is debiased from the background shortcut. Extensive experiments demonstrate that FAME can effectively resist background cheating and thus achieve the state-of-the-art performance on downstream tasks across UCF101, HMDB51, and Diving48 datasets. The code and configurations are released at https://github.com/Mark12Ding/FAME.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mark12ding/fame officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionContrastive LearningRepresentation Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Batch NormalizationContrastive LearningInfoNCEMoCo

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections