Predicting depression by using a novel deep learning model and video-audio-text multimodal data
These results underscore the robustness and precision of the IMDD-Net, highlighting the importance of integrating local and global features across multiple modalities for accurate depression prediction.
Authors
- Shouliang Qi (ORCID: https://orcid.org/0000-0003-0977-1939)
- Yifu Li (ORCID: https://orcid.org/0000-0002-0040-1205)
- Qian Wei (ORCID: https://orcid.org/0000-0001-6854-7289)
- Meng Zhao (ORCID: https://orcid.org/0009-0006-8449-8935)
- Yudong Yao (ORCID: https://orcid.org/0000-0001-6442-7079)
- Jiangtao Wang (ORCID: https://orcid.org/0000-0002-1222-164X)
- Xueping Yang (ORCID: https://orcid.org/0000-0002-0681-5812)
Institutions
- Stevens Institute of Technology (US)
- Liaoning Provincial People's Hospital (CN)
- Northeastern University (CN)
Publication Details
- Journal
- Frontiers in Psychiatry
- Published
- 2025-09-24
- DOI
- https://doi.org/10.3389/fpsyt.2025.1602650
- Citations
- 2
- Primary Topic
- Emotion and Mood Recognition
- Type
- article
- Field-Weighted Citation Impact
- 4.24
Funders
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities