Papers › Self-Supervised Video Representation Learning with Meta-Contrastive Network

Self-Supervised Video Representation Learning with Meta-Contrastive Network

19 Aug 2021ICCV 2021 10arXiv:2108.08426archive 2025-07-28

Yuanze Lin, Xun Guo, Yan Lu

Self-supervised learning has been successfully applied to pre-train video representations, which aims at efficient adaptation from pre-training domain to downstream tasks. Existing approaches merely leverage contrastive loss to learn instance-level discrimination. However, lack of category information will lead to hard-positive problem that constrains the generalization ability of this kind of methods. We find that the multi-task process of meta learning can provide a solution to this problem. In this paper, we propose a Meta-Contrastive Network (MCN), which combines the contrastive learning and meta learning, to enhance the learning ability of existing self-supervised approaches. Our method contains two training stages based on model-agnostic meta learning (MAML), each of which consists of a contrastive branch and a meta branch. Extensive evaluations demonstrate the effectiveness of our method. For two downstream tasks, i.e., video action recognition and video retrieval, MCN outperforms state-of-the-art approaches on UCF101 and HMDB51 datasets. To be more specific, with R(2+1)D backbone, MCN achieves Top-1 accuracies of 84.8% and 54.5% for video action recognition, as well as 52.5% and 23.7% for video retrieval.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Action RecognitionContrastive LearningMeta-LearningRepresentation LearningRetrievalSelf-Supervised Action RecognitionSelf-Supervised LearningTemporal Action LocalizationVideo Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Action Recognition HMDB51 MCN (R3D-18; RGB) Frozen false #28 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 MCN (R3D-18; RGB) Pre-Training Dataset UCF101 #28 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 MCN (R3D-18; RGB) Top-1 Accuracy 54.8 #28 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 MCN (R2+1D; RGB) Frozen false #29 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 MCN (R2+1D; RGB) Pre-Training Dataset UCF101 #29 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 MCN (R2+1D; RGB) Top-1 Accuracy 54.5 #29 of 48 Archive leaderboard report
Self-Supervised Action Recognition UCF101 MCN (R3D-18; RGB) 3-fold Accuracy 85.4 #28 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 MCN (R2+1D; RGB) 3-fold Accuracy 84.8 #29 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.

Methods

(2+1)D ConvolutionAverage PoolingBatch NormalizationContrastive LearningDense ConnectionsGlobal Average PoolingR(2+1)DReLUResidual Connection

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