Papers › USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature...
USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation
Wanjiang Weng, Hongsong Wang, JunBo Wang, Lei He, GuoSen Xie
Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating additional momentum encoder and memory bank to get negative samples, which increases the difficulty of model training. Furthermore, these methods primarily concentrate on learning a global representation for recognition and retrieval tasks, while overlooking the rich and detailed local representations that are crucial for dense prediction tasks. To alleviate these issues, we introduce a Unified Skeleton-based Dense Representation Learning framework based on feature decorrelation, called USDRL, which employs feature decorrelation across temporal, spatial, and instance domains in a multi-grained manner to reduce redundancy among dimensions of the representations to maximize information extraction from features. Additionally, we design a Dense Spatio-Temporal Encoder (DSTE) to capture fine-grained action representations effectively, thereby enhancing the performance of dense prediction tasks. Comprehensive experiments, conducted on the benchmarks NTU-60, NTU-120, PKU-MMD I, and PKU-MMD II, across diverse downstream tasks including action recognition, action retrieval, and action detection, conclusively demonstrate that our approach significantly outperforms the current state-of-the-art (SOTA) approaches. Our code and models are available at https://github.com/wengwanjiang/USDRL.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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 |
|---|---|---|---|---|---|---|---|
| Skeleton Based Action Recognition | NTU RGB+D | 3s-USDRL (DSTE) This work | Accuracy (CS) | 87.1 | #78 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D | 3s-USDRL (DSTE) This work | Accuracy (CV) | 93.2 | #78 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | 3s-USDRL (DSTE) This work | Accuracy (Cross-Setup) | 79.3 | #56 of 83 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | 3s-USDRL (DSTE) This work | Accuracy (Cross-Subject) | 80.6 | #56 of 83 | 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