Papers › Masked Motion Encoding for Self-Supervised Video Representation Learning

Masked Motion Encoding for Self-Supervised Video Representation Learning

12 Oct 2022CVPR 2023 1arXiv:2210.06096archive 2025-07-28

Xinyu Sun, Peihao Chen, LiangWei Chen, Changhao Li, Thomas H. Li, Mingkui Tan, Chuang Gan

How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions. However, simply masking and recovering appearance contents may not be sufficient to model temporal clues as the appearance contents can be easily reconstructed from a single frame. To overcome this limitation, we present Masked Motion Encoding (MME), a new pre-training paradigm that reconstructs both appearance and motion information to explore temporal clues. In MME, we focus on addressing two critical challenges to improve the representation performance: 1) how to well represent the possible long-term motion across multiple frames; and 2) how to obtain fine-grained temporal clues from sparsely sampled videos. Motivated by the fact that human is able to recognize an action by tracking objects' position changes and shape changes, we propose to reconstruct a motion trajectory that represents these two kinds of change in the masked regions. Besides, given the sparse video input, we enforce the model to reconstruct dense motion trajectories in both spatial and temporal dimensions. Pre-trained with our MME paradigm, the model is able to anticipate long-term and fine-grained motion details. Code is available at https://github.com/XinyuSun/MME.

PaperPDFConference PDFCode

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

Code

xinyusun/mme officialmentioned in papermentioned on GitHubpytorch report
XinyuSun/M3Video mentioned on GitHubpytorch 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

MMEOptical Flow EstimationRepresentation LearningSelf-Supervised Action RecognitionSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Action Recognition HMDB51 M3Video Frozen false #2 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 M3Video Pre-Training Dataset Kinetics400 #2 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 M3Video Top-1 Accuracy 78.0 #2 of 48 Archive leaderboard report
Self-Supervised Action Recognition UCF101 M3Video 3-fold Accuracy 96.5 #4 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 M3Video Frozen false #4 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 M3Video Pre-Training Dataset Kinetics400 #4 of 53 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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