DEP-Former: Multimodal Depression Recognition Based on Facial Expressions and Audio Features via Emotional Changes

• Published in: IEEE transactions on circuits and systems for video technology Vol. 35; no. 3; pp. 2087 - 2100
• Main Authors: Ye, Jiayu, Yu, Yanhong, Lu, Lin, Wang, Hao, Zheng, Yunshao, Liu, Yang, Wang, Qingxiang
• Format: Journal Article
• Language: English
• Published: IEEE 01.03.2025
• Subjects: audio features; Circuits and systems; Data collection; Data models; Deep learning; DEP-Former; Depression; depression recognition; Emotion recognition; EWRE; Face recognition; facial expressions; Feature extraction; Indexes; Mental health

Clinical research has demonstrated that exploring behavioral signal differences between depressed patients and non-depressed people using audiovisual technology is an effective approach for achieving depression recognition. Hence, in this paper we propose an emotion word reading experiment (EWRE), a...