Papers › Revealing Key Details to See Differences: A Novel Prototypical Perspective for...
Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
Hongda Liu, Yunfan Liu, Min Ren, Hao Wang, Yunlong Wang, Zhenan Sun
In skeleton-based action recognition, a key challenge is distinguishing between actions with similar trajectories of joints due to the lack of image-level details in skeletal representations. Recognizing that the differentiation of similar actions relies on subtle motion details in specific body parts, we direct our approach to focus on the fine-grained motion of local skeleton components. To this end, we introduce ProtoGCN, a Graph Convolutional Network (GCN)-based model that breaks down the dynamics of entire skeleton sequences into a combination of learnable prototypes representing core motion patterns of action units. By contrasting the reconstruction of prototypes, ProtoGCN can effectively identify and enhance the discriminative representation of similar actions. Without bells and whistles, ProtoGCN achieves state-of-the-art performance on multiple benchmark datasets, including NTU RGB+D, NTU RGB+D 120, Kinetics-Skeleton, and FineGYM, which demonstrates the effectiveness of the proposed method. The code is available at https://github.com/firework8/ProtoGCN.
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 | Kinetics-Skeleton dataset | ProtoGCN | Accuracy | 51.9 | #2 of 42 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D | ProtoGCN | Accuracy (CS) | 93.8 | #5 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D | ProtoGCN | Accuracy (CV) | 97.8 | #5 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D | ProtoGCN | Ensembled Modalities | 6 | #5 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | ProtoGCN | Accuracy (Cross-Setup) | 92.2 | #1 of 83 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | ProtoGCN | Accuracy (Cross-Subject) | 90.9 | #1 of 83 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | ProtoGCN | Ensembled Modalities | 6 | #1 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