MDN: A Deep Maximization-Differentiation Network for Spatio-Temporal Depression Detection

Wheidima Carneirodemelo, Eric G. Granger, Miguel Bordallo Lopez

Research output: Contribution to journalArticleScientificpeer-review

26 Citations (Scopus)

Abstract

Deep learning (DL) models have been successfully applied in video-based affective computing, allowing, for instance, to recognize emotions and mood, or to estimate the intensity of pain or stress of individuals based on their facial expressions. Despite the recent advances with state-of-the-art DL models for spatio-temporal recognition of facial expressions associated with depressive behaviour, some key challenges remain in the cost-effective application of 3D-CNNs: (1) 3D convolutions usually employ structures with fixed temporal depth that decreases the potential to extract discriminative representations due to the usually small difference of spatio-temporal variations along different depression levels; and (2) the computational complexity of these models with consequent susceptibility to overfitting. To address these challenges, we propose a novel DL architecture called the Maximization and Differentiation Network (MDN) in order to effectively represent facial expression variations that are relevant for depression assessment. The MDN, operating without 3D convolutions, explores multiscale temporal information using a maximization block that captures smooth facial variations and a difference block that encodes sudden facial variations. Extensive experiments using our proposed MDN with models with 100 and 152 layers result in improved performance while reducing the number of parameters by more than 3× when compared with 3D ResNet models. Our model also outperforms other 3D models and achieves state-of-the-art results for depression detection. Code available at: https://github.com/wheidima/MDN.

Original languageEnglish
Pages (from-to)578-590
Number of pages13
JournalIEEE Transactions on Affective Computing
Volume14
Issue number1
DOIs
Publication statusPublished - 1 Jan 2023
MoE publication typeA1 Journal article-refereed

Keywords

  • Affective Computing
  • Computational modeling
  • Computer architecture
  • Convolutional Neural Networks
  • Deep Learning
  • Depression
  • Depression Detection
  • Face Analysis
  • Face recognition
  • Feature extraction
  • Solid modeling
  • Three-dimensional displays
  • depression detection
  • Affective computing
  • deep learning
  • face analysis
  • convolutional neural networks

Fingerprint

Dive into the research topics of 'MDN: A Deep Maximization-Differentiation Network for Spatio-Temporal Depression Detection'. Together they form a unique fingerprint.

Cite this