Interpretable Multimodal Emotion Recognition using Facial Features and Physiological Signals

TL;DR

This paper presents a multimodal emotion recognition framework combining facial features and physiological signals, demonstrating improved accuracy and interpretability through permutation importance analysis on the IEMOCAP dataset.

Contribution

It introduces a novel multimodal fusion framework with an interpretability technique for emotion recognition, integrating visual and physiological data.

Findings

Enhanced emotion classification accuracy with multimodal fusion

Permutation importance reveals modality contributions

Improved understanding of modality roles in emotion recognition

Abstract

This paper aims to demonstrate the importance and feasibility of fusing multimodal information for emotion recognition. It introduces a multimodal framework for emotion understanding by fusing the information from visual facial features and rPPG signals extracted from the input videos. An interpretability technique based on permutation feature importance analysis has also been implemented to compute the contributions of rPPG and visual modalities toward classifying a given input video into a particular emotion class. The experiments on IEMOCAP dataset demonstrate that the emotion classification performance improves by combining the complementary information from multiple modalities.