ST-GCN + AS-GCN w/DH-TCN

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots2 results

Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2019-12-20
78.3
best: 96.7 (DSCNet (RGB + Pose))
Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition arXiv:1912.09745
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2019-12-20
79.2
best: 95.6 (DSCNet (RGB + Pose))
Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition arXiv:1912.09745

Time Series2 results

Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2019-12-20
78.3
best: 96.7 (DSCNet (RGB + Pose))
Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition arXiv:1912.09745
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2019-12-20
79.2
best: 95.6 (DSCNet (RGB + Pose))
Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition arXiv:1912.09745