Papers › Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition

Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition

4 May 2021arXiv:2105.01563archive 2025-07-28

Zhenyue Qin, Yang Liu, Pan Ji, Dongwoo Kim, Lei Wang, Bob McKay, Saeed Anwar, Tom Gedeon

Skeleton sequences are lightweight and compact, and thus are ideal candidates for action recognition on edge devices. Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance. The use of first- and second-order features, i.e., joint and bone representations, has led to high accuracy. Nonetheless, many models are still confused by actions that have similar motion trajectories. To address these issues, we propose fusing higher-order features in the form of angular encoding into modern architectures to robustly capture the relationships between joints and body parts. This simple fusion with popular spatial-temporal graph neural networks achieves new state-of-the-art accuracy in two large benchmarks, including NTU60 and NTU120, while employing fewer parameters and reduced run time. Our source code is publicly available at: https://github.com/ZhenyueQin/Angular-Skeleton-Encoding.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ZhenyueQin/Angular-Skeleton-Encoding officialmentioned in papermentioned on GitHubpytorch 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

Action RecognitionGraph Neural NetworkSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition NTU RGB+D AngNet-JA + BA + JBA + VJBA Accuracy (CS) 91.7 #36 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D AngNet-JA + BA + JBA + VJBA Accuracy (CV) 96.4 #36 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 AngNet-JA + BA + JBA + VJBA Accuracy (Cross-Setup) 89.2% #30 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 AngNet-JA + BA + JBA + VJBA Accuracy (Cross-Subject) 88.2% #30 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 AngNet-JA + BA + JBA + VJBA Ensembled Modalities 4 #30 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

Graph Neural Network

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