Papers › DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware...

DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling

21 Jan 2025arXiv:2501.12086archive 2025-07-28

Hu Cui, Renjing Huang, Ruoyu Zhang, Tessai Hayama

Graph convolutional networks (GCNs) have emerged as a powerful tool for skeleton-based action and gesture recognition, thanks to their ability to model spatial and temporal dependencies in skeleton data. However, existing GCN-based methods face critical limitations: (1) they lack effective spatio-temporal topology modeling that captures dynamic variations in skeletal motion, and (2) they struggle to model multiscale structural relationships beyond local joint connectivity. To address these issues, we propose a novel framework called Dynamic Spatial-Temporal Semantic Awareness Graph Convolutional Network (DSTSA-GCN). DSTSA-GCN introduces three key modules: Group Channel-wise Graph Convolution (GC-GC), Group Temporal-wise Graph Convolution (GT-GC), and Multi-Scale Temporal Convolution (MS-TCN). GC-GC and GT-GC operate in parallel to independently model channel-specific and frame-specific correlations, enabling robust topology learning that accounts for temporal variations. Additionally, both modules employ a grouping strategy to adaptively capture multiscale structural relationships. Complementing this, MS-TCN enhances temporal modeling through group-wise temporal convolutions with diverse receptive fields. Extensive experiments demonstrate that DSTSA-GCN significantly improves the topology modeling capabilities of GCNs, achieving state-of-the-art performance on benchmark datasets for gesture and action recognition, including SHREC17 Track, DHG-14\/28, NTU-RGB+D, and NTU-RGB+D-120.

PaperPDFCode

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

Action RecognitionGesture RecognitionHand Gesture RecognitionSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition NTU RGB+D DSTSA-GCN Accuracy (CS) 92.78 #17 of 28 Archive leaderboard report
Action Recognition NTU RGB+D DSTSA-GCN Accuracy (CV) 97.03 #17 of 28 Archive leaderboard report
Action Recognition NTU RGB+D 120 DSTSA-GCN Accuracy (Cross-Setup) 90.97 #12 of 21 Archive leaderboard report
Action Recognition NTU RGB+D 120 DSTSA-GCN Accuracy (Cross-Subject) 89.12 #12 of 21 Archive leaderboard report
Hand Gesture Recognition DHG-14 DSTSA-GCN Accuracy 95.04 #2 of 13 Archive leaderboard report
Hand Gesture Recognition DHG-28 DSTSA-GCN Accuracy 93.57 #1 of 9 Archive leaderboard report
Skeleton Based Action Recognition N-UCLA DSTSA-GCN Accuracy 96.98 #11 of 25 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D DSTSA-GCN Accuracy (CS) 92.78 #30 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D DSTSA-GCN Accuracy (CV) 97.03 #30 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D DSTSA-GCN Ensembled Modalities 4 #30 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 DSTSA-GCN Accuracy (Cross-Setup) 90.97 #22 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 DSTSA-GCN Accuracy (Cross-Subject) 89.12 #22 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 DSTSA-GCN Ensembled Modalities 4 #22 of 83 Archive leaderboard report
Skeleton Based Action Recognition SHREC 2017 track on 3D Hand Gesture Recognition DSTSA-GCN 14 gestures accuracy 97.74 #2 of 7 Archive leaderboard report
Skeleton Based Action Recognition SHREC 2017 track on 3D Hand Gesture Recognition DSTSA-GCN 28 gestures accuracy 95.37 #2 of 7 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

GCN

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