Corpus ID: 236170901

Deep 3D-CNN for Depression Diagnosis with Facial Video Recording of Self-Rating Depression Scale Questionnaire

  title={Deep 3D-CNN for Depression Diagnosis with Facial Video Recording of Self-Rating Depression Scale Questionnaire},
  author={Wanqing Xie and Lizhong Liang and Yao Lu and Hui Luo and Xiaofeng Liu},
  • Wanqing Xie, Lizhong Liang, +2 authors Xiaofeng Liu
  • Published 2021
  • Computer Science
  • ArXiv
The Self-Rating Depression Scale (SDS) questionnaire is commonly utilized for effective depression preliminary screening. The uncontrolled self-administered measure, on the other hand, maybe readily influenced by insouciant or dishonest responses, yielding different findings from the clinician-administered diagnostic. Facial expression (FE) and behaviors are important in clinicianadministered assessments, but they are underappreciated in self-administered evaluations. We use a new dataset of… Expand

Figures and Tables from this paper


Interpreting Depression From Question-wise Long-term Video Recording of SDS Evaluation
  • Wanqing Xie, Lizhong Liang, +4 authors Xiaofeng Liu
  • Computer Science, Medicine
  • IEEE journal of biomedical and health informatics
  • 2021
This work proposes an end-to-end hierarchical framework for the long-term variable-length video, which utilizes a 3D CNN for local temporal pattern exploration and a redundancy-aware self-attention scheme for question-wise global feature aggregation. Expand
Nonverbal behavior and childhood depression.
The present findings suggest less robust relationships between depression and nonverbal behavior for children than those obtained with adults. Expand
Adaptive metric learning with deep neural networks for video-based facial expression recognition
This work proposes the adaptive (N+M)-tuplet clusters loss function and optimize it with the softmax loss simultaneously in the training phrase to reduce the variation introduced by personal attributes in video-based facial expression recognition. Expand
Automatic Assessment of Depression Based on Visual Cues: A Systematic Review
The review outlines methods and algorithms for visual feature extraction, dimensionality reduction, decision methods for classification and regression approaches, as well as different fusion strategies, for automatic depression assessment utilizing visual cues alone or in combination with vocal or verbal cues. Expand
Identity-aware Facial Expression Recognition in Compressed Video
This paper targets to explore the inter-subject variations eliminated facial expression representation in the compressed video domain and can achieve comparable or better performance than the recent decoded image based methods on the typical FER benchmarks with about 3× faster inference with compressed data. Expand
Adaptive Deep Metric Learning for Identity-Aware Facial Expression Recognition
Better FER performance can be achieved by combining the deep metric loss and softmax loss in a unified two fully connected layer branches framework via joint optimization, which reduces the computational burden of deep metric learning, and alleviates the difficulty of threshold validation and anchor selection. Expand
Classification-aware Semi-supervised Domain Adaptation
A semi-supervised adversarial network is proposed that allows the knowledge transfer from the labeled videos to the heterogeneous labeled audio domain hence enhancing the audio emotion recognition performance. Expand
Hard negative generation for identity-disentangled facial expression recognition
A novel FER framework, named identity-disentangled facial expression recognition machine (IDFERM), is proposed, in which the identity is untangled from a query sample by exploiting its difference from its references. Expand
  • W. Zung
  • Psychology, Medicine
  • Archives of general psychiatry
  • 1965
The general depression scales used were felt to be insufficient for the purpose of this research project and the more specific scales were also inadequate. Expand
Action Recognition in Video Sequences using Deep Bi-Directional LSTM With CNN Features
A novel action recognition method by processing the video data using convolutional neural network (CNN) and deep bidirectional LSTM (DB-LSTM) network that is capable of learning long term sequences and can process lengthy videos by analyzing features for a certain time interval. Expand