BMHA-Net: A two-branch multiscale hierarchical attention network for depression severity estimation from facial videos
Authors:
- Yiyun CaoYCYiyun Cao
- Binhui TangBTBinhui Tang
- Caiyun LiCLCaiyun Li
- Bo DaiBDBo Dai
- Jie LingJLJie Ling
- Yuchun LiYLYuchun Li
- Xiaowen LiuXLXiaowen Liu
- 14 October 2026
- journal article
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 131
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62562030)
- National Natural Science Foundation of China (71762010)
- Hainan Normal University (HSZK-KYQD-202430)
- Natural Science Foundation of Hainan Province (825QN308)
This publication has 40 references indexed in Scilit:
- AI-assisted multi-modal information for the screening of depression: a systematic review and meta-analysisnpj Digital Medicine, 2025
- LSCAformer: Long and short-term cross-attention-aware transformer for depression recognition from video sequencesBiomedical Signal Processing and Control, 2024
- A novel multimodal depression diagnosis approach utilizing a new hybrid fusion methodBiomedical Signal Processing and Control, 2024
- Spatial–Temporal Attention Network for Depression Recognition from facial videosExpert Systems with Applications, 2023
- PRA-Net: Part-and-Relation Attention Network for depression recognition from facial expressionComputers in Biology and Medicine, 2023
- Automatic depression recognition using CNN with attention mechanism from videosNeurocomputing, 2021
- Global burden of disease attributable to mental and substance use disorders: findings from the Global Burden of Disease Study 2010The Lancet, 2013
- Marital distress and DSM-IV psychiatric disorders in a population-based national survey.Journal of Abnormal Psychology, 2007
- The PHQ-9Journal of General Internal Medicine, 2001
- Reduced facial expression and social context in major depression: discrepancies between facial muscle activity and self-reported emotionPsychiatry Research, 2000