New paper on multimodal emotion prediction models from video and audio

Just published a new article with my PhD student Thao Ha Thi Phuong and Prof. Gemma Roig on 'Multimodal Deep Models for Predicting Affective Responses Evoked by Movies'. The paper will be published in the proceedings of the 2nd International Workshop on Computer Vision for Physiological Measurement as part of ICCV; and will be presented by Thao in Seoul, South Korea. Anybody interested can download the preprint article here (link coming soon!). The source code of our model is available on github.

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.