Papers › Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video...

Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning

29 Oct 2020arXiv:2010.15464archive 2025-07-28

Li Tao, Xueting Wang, Toshihiko Yamasaki

Recently, pretext-task based methods are proposed one after another in self-supervised video feature learning. Meanwhile, contrastive learning methods also yield good performance. Usually, new methods can beat previous ones as claimed that they could capture "better" temporal information. However, there exist setting differences among them and it is hard to conclude which is better. It would be much more convincing in comparison if these methods have reached as closer to their performance limits as possible. In this paper, we start from one pretext-task baseline, exploring how far it can go by combining it with contrastive learning, data pre-processing, and data augmentation. A proper setting has been found from extensive experiments, with which huge improvements over the baselines can be achieved, indicating a joint optimization framework can boost both pretext task and contrastive learning. We denote the joint optimization framework as Pretext-Contrastive Learning (PCL). The other two pretext task baselines are used to validate the effectiveness of PCL. And we can easily outperform current state-of-the-art methods in the same training manner, showing the effectiveness and the generality of our proposal. It is convenient to treat PCL as a standard training strategy and apply it to many other works in self-supervised video feature learning.

PaperPDFCode

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

Code

BestJuly/Pretext-Contrastive-Learning officialmentioned 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

Contrastive LearningData AugmentationSelf-Supervised Action RecognitionSelf-Supervised LearningSelf-supervised Video RetrievalVideo Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Action Recognition HMDB51 PCL (ResNet-18) Frozen false #35 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 PCL (ResNet-18) Pre-Training Dataset UCF101 #35 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 PCL (ResNet-18) Top-1 Accuracy 43.2 #35 of 48 Archive leaderboard report
Self-Supervised Action Recognition UCF101 PCL (ResNet-18) 3-fold Accuracy 82.3 #32 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 PCL (ResNet-18) Frozen false #32 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 PCL (ResNet-18) Pre-Training Dataset UCF101 #32 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

Contrastive Learning

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