Automatic Depression Detection via Learning and Fusing Features from Visual Cues

TL;DR

This paper introduces a novel automatic depression detection method using visual cues, employing a Temporal Dilated Convolutional Network and feature-wise attention to improve accuracy on long video sequences.

Contribution

It proposes a new ADD approach that effectively learns and fuses long-range temporal visual features with attention mechanisms, achieving state-of-the-art results.

Findings

Achieved state-of-the-art performance on DAIC_WOZ dataset.

Effectively captures long-range temporal information from video sequences.

Enhances depression detection accuracy through feature fusion and attention.

Abstract

Depression is one of the most prevalent mental disorders, which seriously affects one's life. Traditional depression diagnostics commonly depends on rating with scales, which can be labor-intensive and subjective. In this context, Automatic Depression Detection (ADD) has been attracting more attention for its low cost and objectivity. ADD systems are able to detect depression automatically from some medical records, like video sequences. However, it remains challenging to effectively extract depression-specific information from long sequences, thereby hindering a satisfying accuracy. In this paper, we propose a novel ADD method via learning and fusing features from visual cues. Specifically, we firstly construct Temporal Dilated Convolutional Network (TDCN), in which multiple Dilated Convolution Blocks (DCB) are designed and stacked, to learn the long-range temporal information from sequences. Then, the Feature-Wise Attention (FWA) module is adopted to fuse different features extracted from TDCNs. The module learns to assign weights for the feature channels, aiming to better incorporate different kinds of visual features and further enhance the detection accuracy. Our method achieves the state-of-the-art performance on the DAIC_WOZ dataset compared to other visual-feature-based methods, showing its effectiveness.