FAF: A novel multimodal emotion recognition approach integrating face, body and text

TL;DR

This paper introduces a new multimodal emotion recognition approach that combines face, body, and text data, utilizing a large dataset and a novel framework to improve accuracy and provide an online prediction platform.

Contribution

The paper presents a new large multimodal emotion dataset and a 'Feature After Feature' framework for improved emotion recognition accuracy.

Findings

Achieved 83.75% classification accuracy with the proposed method.

Improved recognition performance by 1.83%, 9.38%, and 21.62% over individual modalities.

Effectively utilized complementarity between modalities to enhance emotion recognition.

Abstract

Multimodal emotion analysis performed better in emotion recognition depending on more comprehensive emotional clues and multimodal emotion dataset. In this paper, we developed a large multimodal emotion dataset, named "HED" dataset, to facilitate the emotion recognition task, and accordingly propose a multimodal emotion recognition method. To promote recognition accuracy, "Feature After Feature" framework was used to explore crucial emotional information from the aligned face, body and text samples. We employ various benchmarks to evaluate the "HED" dataset and compare the performance with our method. The results show that the five classification accuracy of the proposed multimodal fusion method is about 83.75%, and the performance is improved by 1.83%, 9.38%, and 21.62% respectively compared with that of individual modalities. The complementarity between each channel is effectively used to improve the performance of emotion recognition. We had also established a multimodal online emotion prediction platform, aiming to provide free emotion prediction to more users.