Papers › Multi-View Action Recognition Using Contrastive Learning

Multi-View Action Recognition Using Contrastive Learning

3 Jan 2023IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023 1archive 2025-07-28

Ketul Shah, Anshul Shah, Chun Pong Lau, Celso M. de Melo, Rama Chellappa

In this work, we present a method for RGB-based action recognition using multi-view videos. We present a supervised contrastive learning framework to learn a feature embedding robust to changes in viewpoint, by effectively leveraging multi-view data. We use an improved supervised contrastive loss and augment the positives with those coming from synchronized viewpoints. We also propose a new approach to use classifier probabilities to guide the selection of hard negatives in the contrastive loss, to learn a more discriminative representation. Negative samples from confusing classes based on posterior are weighted higher. We also show that our method leads to better domain generalization compared to the standard supervised training based on synthetic multi-view data. Extensive experiments on real (NTU-60, NTU-120, NUMA) and synthetic (RoCoG) data demonstrate the effectiveness of our approach.

PaperPDFCode

Code

kshah33/viewcon officialmentioned in paper 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 LearningDomain Generalization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition NTU RGB+D ViewCon (RGB + Pose) Accuracy (CS) 93.7 #14 of 28 Archive leaderboard report
Action Recognition NTU RGB+D ViewCon (RGB + Pose) Accuracy (CV) 98.9 #14 of 28 Archive leaderboard report
Action Recognition NTU RGB+D 120 ViewCon (RGB) Accuracy (Cross-Setup) 87.5 #15 of 21 Archive leaderboard report
Action Recognition NTU RGB+D 120 ViewCon (RGB) Accuracy (Cross-Subject) 85.6 #15 of 21 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 LearningSupervised Contrastive Loss

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