Papers › InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition
InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition
Hyung-gun Chi, Myoung Hoon Ha, Seunggeun Chi, Sang Wan Lee, QiXing Huang, Karthik Ramani
Human skeleton-based action recognition offers a valuable means to understand the intricacies of human behavior because it can handle the complex relationships between physical constraints and intention. Although several studies have focused on encoding a skeleton, less attention has been paid to embed this information into the latent representations of human action. InfoGCN proposes a learning framework for action recognition combining a novel learning objective and an encoding method. First, we design an information bottleneck-based learning objective to guide the model to learn informative but compact latent representations. To provide discriminative information for classifying action, we introduce attention-based graph convolution that captures the context-dependent intrinsic topology of human action. In addition, we present a multi-modal representation of the skeleton using the relative position of joints, designed to provide complementary spatial information for joints. InfoGCN surpasses the known state-of-the-art on multiple skeleton-based action recognition benchmarks with the accuracy of 93.0% on NTU RGB+D 60 cross-subject split, 89.8% on NTU RGB+D 120 cross-subject split, and 97.0% on NW-UCLA.
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 | N-UCLA | InfoGCN | Accuracy | 97.0 | #9 of 25 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D | InfoGCN | Accuracy (CS) | 93.0 | #22 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D | InfoGCN | Accuracy (CV) | 97.1 | #22 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D | InfoGCN | Ensembled Modalities | 6 | #22 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | InfoGCN | Accuracy (Cross-Setup) | 91.2 | #15 of 83 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | InfoGCN | Accuracy (Cross-Subject) | 89.8 | #15 of 83 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | InfoGCN | Ensembled Modalities | 6 | #15 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.
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