Hierarchical Attention-Based Multimodal Fusion Network for Video Emotion Recognition

Table 9

Top-1 accuracy (%) comparing state-of-the-art methods on Ekman-6 and VideoEmotion-8.

Method	Ekman (%)	VideoEmotion-8 (%)
Emotion in context [10]	51.8	50.6
Xu et al. [33]	50.4	46.7
Kernelized feature [26]	54.4	49.7
Concept selection [27]	54.40	50.82
Graph-based network [36]	55.01	51.77
CAAN [37]	56.23	52.5
Ours	57.7	53.13