Papers › Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition

Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition

29 Jun 2021arXiv:2106.15125archive 2025-07-28

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

One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the recent State-Of-The-Art (SOTA) models for this task tends to be exceedingly sophisticated and over-parameterized. The low efficiency in model training and inference has increased the validation costs of model architectures in large-scale datasets. To address the above issue, recent advanced separable convolutional layers are embedded into an early fused Multiple Input Branches (MIB) network, constructing an efficient Graph Convolutional Network (GCN) baseline for skeleton-based action recognition. In addition, based on such the baseline, we design a compound scaling strategy to expand the model's width and depth synchronously, and eventually obtain a family of efficient GCN baselines with high accuracies and small amounts of trainable parameters, termed EfficientGCN-Bx, where "x" denotes the scaling coefficient. On two large-scale datasets, i.e., NTU RGB+D 60 and 120, the proposed EfficientGCN-B4 baseline outperforms other SOTA methods, e.g., achieving 91.7% accuracy on the cross-subject benchmark of NTU 60 dataset, while being 3.15x smaller and 3.21x faster than MS-G3D, which is one of the best SOTA methods. The source code in PyTorch version and the pretrained models are available at https://github.com/yfsong0709/EfficientGCNv1.

PaperPDFCode

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

Code

yfsong0709/EfficientGCNv1 officialmentioned in papermentioned on GitHub report
yfsong0709/ResGCNv1 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 Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition NTU RGB+D EfficientGCN-B4 Accuracy (CS) 92.1 #34 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D EfficientGCN-B4 Accuracy (CV) 96.1 #34 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D EfficientGCN-B2 Accuracy (CS) 90.9 #45 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D EfficientGCN-B2 Accuracy (CV) 95.5 #45 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D EfficientGCN-B0 Accuracy (CS) 89.9 #57 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D EfficientGCN-B0 Accuracy (CV) 94.7 #57 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 EfficientGCN-B4 Accuracy (Cross-Setup) 89.1 #27 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 EfficientGCN-B4 Accuracy (Cross-Subject) 88.7 #27 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 EfficientGCN-B2 Accuracy (Cross-Setup) 88.0 #31 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 EfficientGCN-B2 Accuracy (Cross-Subject) 87.9 #31 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 EfficientGCN-B0 Accuracy (Cross-Setup) 84.3 #43 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 EfficientGCN-B0 Accuracy (Cross-Subject) 85.9 #43 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