CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition

TL;DR

This paper introduces CARAT, a novel method for multi-modal multi-label emotion recognition that uses contrastive reconstruction and aggregation to better model label-specific features and modality dependencies, outperforming existing methods.

Contribution

The paper proposes a contrastive feature reconstruction and aggregation framework that captures label-specific and modality-dependent features for improved MMER performance.

Findings

CARAT outperforms state-of-the-art methods on CMU-MOSEI and M3ED datasets.

The reconstruction-based fusion improves modality-to-label dependency modeling.

Shuffle-based aggregation enhances label co-occurrence collaboration.

Abstract

Multi-modal multi-label emotion recognition (MMER) aims to identify relevant emotions from multiple modalities. The challenge of MMER is how to effectively capture discriminative features for multiple labels from heterogeneous data. Recent studies are mainly devoted to exploring various fusion strategies to integrate multi-modal information into a unified representation for all labels. However, such a learning scheme not only overlooks the specificity of each modality but also fails to capture individual discriminative features for different labels. Moreover, dependencies of labels and modalities cannot be effectively modeled. To address these issues, this paper presents ContrAstive feature Reconstruction and AggregaTion (CARAT) for the MMER task. Specifically, we devise a reconstruction-based fusion mechanism to better model fine-grained modality-to-label dependencies by contrastively learning modal-separated and label-specific features. To further exploit the modality complementarity, we introduce a shuffle-based aggregation strategy to enrich co-occurrence collaboration among labels. Experiments on two benchmark datasets CMU-MOSEI and M3ED demonstrate the effectiveness of CARAT over state-of-the-art methods. Code is available at https://github.com/chengzju/CARAT.