TY - JOUR
T1 - DepNet: An Automated Intelligent System using Deep Learning for Video-based Depression Analysis
AU - PANDEY, HARI MOHAN
AU - He, Lang
AU - Guo, Chenguang
AU - Tiwari, Prayag
AU - Su, Rui
AU - Dang, Wei
PY - 2021/10/6
Y1 - 2021/10/6
N2 - As a common mental disorder, depression has attracted many researchers from affective computing field to estimate the depression severity. However, existing approaches based on Deep Learning (DL) are mainly focused on single facial image without considering the sequence information for predicting the depression scale. In this paper, an integrated framework, termed DepNet, for automatic diagnosis of depression that adopts facial images sequence from videos is proposed. Specifically, several pre-trained models are adopted to represent the Low Level features (LLF), and Feature Aggregation Module (FAM) is proposed to capture the high level characteristic information for depression analysis. More importantly, the discriminative characteristic of depression on faces can be mined to assist the clinicians to diagnose the severity of the depressed subjects. Multi-scale experiments, carried out on AVEC2013 and AVEC2014 databases have shown the excellent performance of the intelligent approach. The root mean square error (RMSE) between the predicted values and the BDI-II scores is 9.17 and 9.01 on the two databases, respectively, which are lower that those of the state of the art video-based depression recognition methods.
AB - As a common mental disorder, depression has attracted many researchers from affective computing field to estimate the depression severity. However, existing approaches based on Deep Learning (DL) are mainly focused on single facial image without considering the sequence information for predicting the depression scale. In this paper, an integrated framework, termed DepNet, for automatic diagnosis of depression that adopts facial images sequence from videos is proposed. Specifically, several pre-trained models are adopted to represent the Low Level features (LLF), and Feature Aggregation Module (FAM) is proposed to capture the high level characteristic information for depression analysis. More importantly, the discriminative characteristic of depression on faces can be mined to assist the clinicians to diagnose the severity of the depressed subjects. Multi-scale experiments, carried out on AVEC2013 and AVEC2014 databases have shown the excellent performance of the intelligent approach. The root mean square error (RMSE) between the predicted values and the BDI-II scores is 9.17 and 9.01 on the two databases, respectively, which are lower that those of the state of the art video-based depression recognition methods.
KW - Depression
KW - Industrial intelligent system (IIS)
KW - Deep Learning (DL)
KW - Pattern recognition
KW - Feature aggregation module (FAM)
U2 - https://doi.org/10.1002/int.22704
DO - https://doi.org/10.1002/int.22704
M3 - Article (journal)
SN - 0884-8173
JO - International Journal of Intelligent Systems
JF - International Journal of Intelligent Systems
M1 - INT2.20210482R3
ER -