CAF-Mamba: Mamba-Based Cross-Modal Adaptive Attention Fusion for Multimodal Depression Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911433471557632 |
|---|---|
| author | Zhou, Bowen Fiedler, Marc-André Al-Hamadi, Ayoub |
| author_facet | Zhou, Bowen Fiedler, Marc-André Al-Hamadi, Ayoub |
| contents | Depression is a prevalent mental health disorder that severely impairs daily functioning and quality of life. While recent deep learning approaches for depression detection have shown promise, most rely on limited feature types, overlook explicit cross-modal interactions, and employ simple concatenation or static weighting for fusion. To overcome these limitations, we propose CAF-Mamba, a novel Mamba-based cross-modal adaptive attention fusion framework. CAF-Mamba not only captures cross-modal interactions explicitly and implicitly, but also dynamically adjusts modality contributions through a modality-wise attention mechanism, enabling more effective multimodal fusion. Experiments on two in-the-wild benchmark datasets, LMVD and D-Vlog, demonstrate that CAF-Mamba consistently outperforms existing methods and achieves state-of-the-art performance. Our code is available at https://github.com/zbw-zhou/CAF-Mamba. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21648 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CAF-Mamba: Mamba-Based Cross-Modal Adaptive Attention Fusion for Multimodal Depression Detection Zhou, Bowen Fiedler, Marc-André Al-Hamadi, Ayoub Computer Vision and Pattern Recognition Computers and Society Human-Computer Interaction Depression is a prevalent mental health disorder that severely impairs daily functioning and quality of life. While recent deep learning approaches for depression detection have shown promise, most rely on limited feature types, overlook explicit cross-modal interactions, and employ simple concatenation or static weighting for fusion. To overcome these limitations, we propose CAF-Mamba, a novel Mamba-based cross-modal adaptive attention fusion framework. CAF-Mamba not only captures cross-modal interactions explicitly and implicitly, but also dynamically adjusts modality contributions through a modality-wise attention mechanism, enabling more effective multimodal fusion. Experiments on two in-the-wild benchmark datasets, LMVD and D-Vlog, demonstrate that CAF-Mamba consistently outperforms existing methods and achieves state-of-the-art performance. Our code is available at https://github.com/zbw-zhou/CAF-Mamba. |
| title | CAF-Mamba: Mamba-Based Cross-Modal Adaptive Attention Fusion for Multimodal Depression Detection |
| topic | Computer Vision and Pattern Recognition Computers and Society Human-Computer Interaction |
| url | https://arxiv.org/abs/2601.21648 |