Papers › Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture Recognition

Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture Recognition

1 May 2023IEEE Transactions on Multimedia 2023 5archive 2025-07-28

Jinfu Liu, Xinshun Wang, Can Wang, Yuan Gao, Mengyuan Liu

Skeleton-based gesture recognition methods have achieved high success using Graph Convolutional Network (GCN), which commonly uses an adjacency matrix to model the spatial topology of skeletons. However, previous methods use the same adjacency matrix for skeletons from different frames, which limits the flexibility of GCN to model temporal information. To solve this problem, we propose a Temporal Decoupling Graph Convolutional Network (TD-GCN), which applies different adjacency matrices for skeletons from different frames. The main steps of each convolution layer in our proposed TD-GCN are as follows. To extract deep spatiotemporal information from skeleton joints, we first extract high-level spatiotemporal features from skeleton data. Then, channel-dependent and temporal-dependent adjacency matrices corresponding to different channels and frames are calculated to capture the spatiotemporal dependencies between skeleton joints. Finally, to fuse topology information from neighbor skeleton joints, spatiotemporal features of skeleton joints are fused based on channel-dependent and temporal-dependent adjacency matrices. To the best of our knowledge, we are the first to use temporal-dependent adjacency matrices for temporal-sensitive topology learning from skeleton joints. The proposed TD-GCN effectively improves the modeling ability of GCN and achieves state-of-the-art results on gesture datasets including SHREC'17 Track and DHG-14/28. Our code is available at: https://github.com/liujf69/TD-GCN-Gesture .

PaperPDFCode

Code

liujf69/TD-GCN-Gesture mentioned in paperpytorch report

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

Gesture RecognitionHand Gesture RecognitionSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Hand Gesture Recognition DHG-14 TD-GCN Accuracy 93.9 #4 of 13 Archive leaderboard report
Hand Gesture Recognition DHG-28 TD-GCN Accuracy 91.4 #5 of 9 Archive leaderboard report
Skeleton Based Action Recognition N-UCLA TD-GCN Accuracy 97.4 #5 of 25 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D TD-GCN Accuracy (CS) 92.8 #29 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D TD-GCN Accuracy (CV) 96.8 #29 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D TD-GCN Ensembled Modalities 4 #29 of 135 Archive leaderboard report
Skeleton Based Action Recognition SHREC 2017 track on 3D Hand Gesture Recognition TD-GCN 14 gestures accuracy 97.02 #3 of 7 Archive leaderboard report
Skeleton Based Action Recognition SHREC 2017 track on 3D Hand Gesture Recognition TD-GCN 28 gestures accuracy 95.36 #3 of 7 Archive leaderboard report
Skeleton Based Action Recognition UAV-Human TD-GCN CSv1(%) 45.43 #3 of 9 Archive leaderboard report
Skeleton Based Action Recognition UAV-Human TD-GCN CSv2(%) 72.86 #3 of 9 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

ConvolutionGCN

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