Multi-Scale Temporal-Frequency Attention Network Based on Ocular Imaging for Depression Detection

Depression is a common and serious mental disorder, characterized by persistent low mood, loss of interest, cognitive dysfunction, and physiological changes. Patients may experience symptoms such as sleep disturbances, changes in appetite, fatigue, and low self-esteem, with severe cases potentially leading to suicidal behavior. There are differences in emotional processing and attention allocation between patients with depression and healthy controls, eye movement characteristics such as fixation patterns, saccade amplitude, and attentional bias have been used as physiological signals for depression detection. Many researchers have developed depression recognition models based on ocular imaging. However, convolutional neural networks, which utilize local receptive fields, can only capture local features in ocular imaging. This paper proposes Multi-Scale Temporal-Frequency Attention Network (MTFNet), which innovatively integrates Multi-Scale time-frequency domain attention into the Video Swin Transformer. Through Multi-Scale Temporal-Frequency Attention Module (MTFAM), MTFNet learns the most important regions in eye movement images, enabling it to capture features more effectively from sequential data and gain a deeper understanding of the structure within eye movement images. Experimental results show that the proposed method achieves a high accuracy of 76. 8% on a self-collected eye movement image dataset, outperforming most models. This work provides a novel approach to research on depression recognition based on eye movement images.

Authors

• Ziru Weng
• Zilin Guo Huazhong University of Science and Technology
• Yujie Gao
• Weihao Zheng
• Yongfeng Tao
• Bin Hu
• Minqiang Yang

Keywords

• Depression
• Feature extraction
• Transformers
• Brain modeling
• Videos
• Data models
• Data mining
• Time-frequency analysis
• Physiology
• Deep learning
• Multi-scale Network
• Detection Of Depression
• Ocular Imaging
• Convolutional Neural Network
• Eye Movements
• Image Regions
• Attention Module
• Saccade Amplitude
• Local Receptive Field
• Differences In Emotional Processing
• Emotional States
• Spatial Information
• Frequency Domain
• Temporal Dimension
• Healthy Control Group
• Imaginary Part
• Spatial Dimensions
• Attention Mechanism
• Eye-tracking
• Temporal Information
• Spatial Attention Module
• Attention Weights
• Spatial Attention
• Linear Embedding
• Long-range Dependencies
• International Affective Picture System
• Manual Extraction
• Channel Attention Module
• Interpretation Of Features
• Vision Transformer
• Depression detection
• multi-scale temporal-frequency attention
• video swin transformer
• Humans
• Neural Networks, Computer
• Adult
• Attention
• Male
• Female
• Image Interpretation, Computer-Assisted
• Young Adult