DepMamba: Progressive Fusion Mamba for Multimodal Depression Detection

TL;DR

DepMamba introduces a hierarchical and progressive multimodal fusion approach for depression detection, effectively modeling long-range temporal dependencies and improving multimodal integration, leading to superior performance on large datasets.

Contribution

It proposes a novel hierarchical and progressive fusion framework combining SSM and CNNs for improved multimodal depression detection.

Findings

Outperforms existing methods on large-scale datasets

Effectively models long-range temporal dependencies

Enhances multimodal fusion accuracy

Abstract

Depression is a common mental disorder that affects millions of people worldwide. Although promising, current multimodal methods hinge on aligned or aggregated multimodal fusion, suffering two significant limitations: (i) inefficient long-range temporal modeling, and (ii) sub-optimal multimodal fusion between intermodal fusion and intramodal processing. In this paper, we propose an audio-visual progressive fusion Mamba for multimodal depression detection, termed DepMamba. DepMamba features two core designs: hierarchical contextual modeling and progressive multimodal fusion. On the one hand, hierarchical modeling introduces convolution neural networks and Mamba to extract the local-to-global features within long-range sequences. On the other hand, the progressive fusion first presents a multimodal collaborative State Space Model (SSM) extracting intermodal and intramodal information for each modality, and then utilizes a multimodal enhanced SSM for modality cohesion. Extensive experimental results on two large-scale depression datasets demonstrate the superior performance of our DepMamba over existing state-of-the-art methods. Code is available at https://github.com/Jiaxin-Ye/DepMamba.