Multimodal Deep Models for Predicting Affective Responses Evoked by Movies

TL;DR

This study develops multimodal deep learning models combining video and audio features to predict viewers' emotional responses to movies, finding audio features more predictive and optical flow more informative than raw video content.

Contribution

Introduces hybrid multimodal models using both visual and audio features, with a comparison of sequential and non-sequential neural network approaches for emotion prediction.

Findings

Audio features outperform video features in emotion prediction.

Optical flow features are more informative than RGB frames.

Predicting emotions independently per time step slightly outperforms LSTM-based sequential models.

Abstract

The goal of this study is to develop and analyze multimodal models for predicting experienced affective responses of viewers watching movie clips. We develop hybrid multimodal prediction models based on both the video and audio of the clips. For the video content, we hypothesize that both image content and motion are crucial features for evoked emotion prediction. To capture such information, we extract features from RGB frames and optical flow using pre-trained neural networks. For the audio model, we compute an enhanced set of low-level descriptors including intensity, loudness, cepstrum, linear predictor coefficients, pitch and voice quality. Both visual and audio features are then concatenated to create audio-visual features, which are used to predict the evoked emotion. To classify the movie clips into the corresponding affective response categories, we propose two approaches based on deep neural network models. The first one is based on fully connected layers without memory on the time component, the second incorporates the sequential dependency with a long short-term memory recurrent neural network (LSTM). We perform a thorough analysis of the importance of each feature set. Our experiments reveal that in our set-up, predicting emotions at each time step independently gives slightly better accuracy performance than with the LSTM. Interestingly, we also observe that the optical flow is more informative than the RGB in videos, and overall, models using audio features are more accurate than those based on video features when making the final prediction of evoked emotions.