DepNet: An automated industrial intelligent system using deep learning for video‐based depression analysis

Abstract

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 pretrained models are adopted to represent the low-level features, and Feature Aggregation Module 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

Face hallucination using multisource references and cross‐scale dual residual fusion mechanism

“…LR up LR enh (8) Overall, the cross-scale residual feature fusion module developed in this paper possesses powerful texture feature characterization capability and enhanced discriminativeness of the network without the involvement of prior knowledge. In addition, mining the patchlevel facial semantic correlation of multiple reference sources makes the results more convincing.…”

“…It is widely acknowledged that the content and structure of face images naturally exhibit nonlocal resemblance and symmetry, 6,8,40 including left and right eyes, nose, brows, upper and lower lips, etc. The semantic components of the same identity may, however, deviate greatly in different circumstances due to factors like expression, posture, and multiple viewpoints, but the semantic regions of faces that are not the same identity show a high degree of similarity.…”

“…However, under controlled conditions (such as outdoor video surveillance), the captured facial images usually have a very low‐resolution (LR) with different illumination conditions and arbitrary poses 3 . In reality, there are many uncertainties causing different degrees of image quality degradation, which leads to severe deterioration of the performance in a wide range of practical face‐analysis applications 4–9 . Therefore, it is essential to create a face super‐resolution model that is more practical.…”

“…3 In reality, there are many uncertainties causing different degrees of image quality degradation, which leads to severe deterioration of the performance in a wide range of practical face-analysis applications. [4][5][6][7][8][9] Therefore, it is essential to create a face super-resolution model that is more practical.…”

Ethical Implications of the Use of Language Analysis Technologies for the Diagnosis and Prediction of Psychiatric Disorders

“…RenderX depression estimation from audio, video, and text information [22,23]. Thus, the possibility to "see" mental disorders is, per se, an innovative technology.…”