EMID: An Emotional Aligned Dataset in Audio-Visual Modality

TL;DR

This paper introduces EMID, a new dataset for emotional alignment of music and images, enhancing cross-modal tasks by emphasizing emotional consistency based on a detailed 13-dimension model, validated through psychological experiments.

Contribution

The paper presents EMID, a novel dataset emphasizing emotional matching in audio-visual data, and introduces EMI-Adapter to improve cross-modal alignment methods.

Findings

Emotional alignment improves cross-modal matching accuracy.

Psychological experiments validate the effectiveness of emotional consistency.

EMID facilitates research in psychotherapy and emotion-aware AI.

Abstract

In this paper, we propose Emotionally paired Music and Image Dataset (EMID), a novel dataset designed for the emotional matching of music and images, to facilitate auditory-visual cross-modal tasks such as generation and retrieval. Unlike existing approaches that primarily focus on semantic correlations or roughly divided emotional relations, EMID emphasizes the significance of emotional consistency between music and images using an advanced 13-dimension emotional model. By incorporating emotional alignment into the dataset, it aims to establish pairs that closely align with human perceptual understanding, thereby raising the performance of auditory-visual cross-modal tasks. We also design a supplemental module named EMI-Adapter to optimize existing cross-modal alignment methods. To validate the effectiveness of the EMID, we conduct a psychological experiment, which has demonstrated that considering the emotional relationship between the two modalities effectively improves the accuracy of matching in abstract perspective. This research lays the foundation for future cross-modal research in domains such as psychotherapy and contributes to advancing the understanding and utilization of emotions in cross-modal alignment. The EMID dataset is available at https://github.com/ecnu-aigc/EMID.