Research Article
Hierarchical Attention-Based Multimodal Fusion Network for Video Emotion Recognition
Table 7
Performance evaluation of attention mechanism.
| | Methods | No attention accuracy (%) | Attention accuracy (%) |
| | Face | 51.87 | 57.94 | | Scene | 44.16 | 45.09 | | Images | 43.92 | 46.03 | | Fusion | 60.05 | 63.08 |
|
|
