Fig 1.
Fusion methods.
Fig 2.
The framework of the MAF-Net.
Table 1.
Keypoint names and their indices.
Table 2.
Structure and characteristics of the data.
Fig 3.
Feature selection technique.
Fig 4.
The framework of multi-head self-attention module.
Fig 5.
The framework of multi-head self-attention module.
Table 3.
Analysis in relation to the most effective methods for NTU RGB+D.
Table 4.
Analysis in relation to the most effective methods for SYSU.
Table 5.
Analysis in relation to the most effective methods for UTD-MHAD.
Table 6.
Analysis in relation to the most effective methods for MMACT.
Table 7.
Performance comparison of models with and without data enhancement across multiple datasets.
Fig 6.
The illustration of the skeleton attention mechanism on UTD-MHAD.
Fig 7.
The illustration of the skeleton attention mechanism on SYSU.
Fig 8.
The heatmap of the self-attention on UTD-MHAD.