Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

23 Jan 2018Sijie YanYuanjun XiongDahua Lin

Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and difficulties of generalization... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Multimodal Activity Recognition EV-Action ST-GCN (Skeleton Vicon) Accuracy 50.7 # 7
Multimodal Activity Recognition EV-Action ST-GCN (Skeleton Kinect) Accuracy 79.6 # 2
3D Human Pose Estimation Human3.6M ST-GCN Average MPJPE (mm) 57.4 # 31
Action Recognition In Videos ICVL-4 ST-GCN Accuracy 80.23% # 2
Action Recognition In Videos IRD ST-GCN Accuracy 74.03% # 2
Skeleton Based Action Recognition Kinetics-Skeleton dataset ST-GCN Accuracy 30.7 # 14
Skeleton Based Action Recognition NTU RGB+D ST-GCN Accuracy (CV) 88.3 # 38
Accuracy (CS) 81.5 # 37
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton ST-GCN Accuracy (CS) 71% # 2
Accuracy (CV I) 25% # 3
Accuracy (CV II) 56% # 3
Accuracy (AV I) 53% # 2
Accuracy (AV II) 43% # 6