A Deep Multimodal Model for Predicting Affective Responses Evoked by Movies Based on Shot Segmentation

Table 2

Comparison of state-of-the-art results for experienced emotion prediction.

Method	Arousal		Valence
	MSE	PCC	MSE	PCC
Thao et al. [9]	0.04	0.46	0.06	0.18
Ours (loss1)	0.0275	0.6187	0.0490	0.2828
Ours (loss2)	0.0403	0.5569	0.0632	0.3443