Table 2 Comparisons between the accuracy (%) of our model and that of each variant on the NTU RGB+D 60 dataset and the Kinetics Skeleton 400 dataset.

From: Spatial-temporal graph neural ODE networks for skeleton-based action recognition

Method

X-Sub

X-view

Kinetics Top1

Kinetics Top5

STG-semantic

80.8

89.0

30.8

53.1

STG-ODE*

81.9

90.1

31.4

53.7

STG-NODE

84.0

91.1

32.6

55.0