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

Table 5

With or without capture changes in audio and visual feature sequences using LSTM.

Model (with Features6)	Experienced arousal (loss1)		Experienced valence (loss2)
	MSE	PCC	MSE	PCC
Ours without LSTM	0.0288	0.5826	0.0751	0.3276
Ours	0.0275	0.6187	0.0632	0.3443