Papers › Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition

Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition

9 Aug 2020arXiv:2008.03791archive 2025-07-28

Yi-Fan Song, Zhang Zhang, Caifeng Shan, Liang Wang

Current methods for skeleton-based human action recognition usually work with complete skeletons. However, in real scenarios, it is inevitable to capture incomplete or noisy skeletons, which could significantly deteriorate the performance of current methods when some informative joints are occluded or disturbed. To improve the robustness of action recognition models, a multi-stream graph convolutional network (GCN) is proposed to explore sufficient discriminative features spreading over all skeleton joints, so that the distributed redundant representation reduces the sensitivity of the action models to non-standard skeletons. Concretely, the backbone GCN is extended by a series of ordered streams which is responsible for learning discriminative features from the joints less activated by preceding streams. Here, the activation degrees of skeleton joints of each GCN stream are measured by the class activation maps (CAM), and only the information from the unactivated joints will be passed to the next stream, by which rich features over all active joints are obtained. Thus, the proposed method is termed richly activated GCN (RA-GCN). Compared to the state-of-the-art (SOTA) methods, the RA-GCN achieves comparable performance on the standard NTU RGB+D 60 and 120 datasets. More crucially, on the synthetic occlusion and jittering datasets, the performance deterioration due to the occluded and disturbed joints can be significantly alleviated by utilizing the proposed RA-GCN.

PaperPDFCode

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

Code

yfsong0709/RA-GCNv2 officialmentioned in papermentioned on GitHubpytorch report
amira-mira/RA-GCNv22 mentioned on GitHubpytorch report
peter-yys-yoon/pegcnv2 mentioned 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 RecognitionSkeleton Based Action RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition NTU RGB+D 3s RA-GCN Accuracy (CS) 87.3 #76 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 3s RA-GCN Accuracy (CV) 93.6 #76 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 3s RA-GCN Accuracy (Cross-Setup) 82.7% #55 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 3s RA-GCN Accuracy (Cross-Subject) 81.1% #55 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

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