Papers › Multi-View Action Recognition Using Contrastive Learning
Multi-View Action Recognition Using Contrastive Learning
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.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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