Research Article

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

Table 1

Comparison of the performance of the two segmentation methods.

FeaturesExperienced arousalExperienced valence
MSEPCCMSEPCC

5 s features4 (loss2)0.04760.45430.07070.2145
Shot features4 (loss2)0.03770.58220.08200.2203

The best result for each indicator is marked in bold.