Hierarchical Attention-Based Multimodal Fusion Network for Video Emotion Recognition

Table 8

Top-1 accuracy (%) comparing state-of-the-art methods on MHED.

Method	Result (%)
Quality-aware network [12]	46.03
Barros et al. [22]	53.73
Chen et al. [10]	55.60
Kosti et al. [9]	56.07
Attention clusters [13]	59.81
Ours	63.08