FRANÇAIS
A showcase of ÉTS researchers’ publications and other contributions
SEARCH

MDN: A deep maximization-differentiation network for spatio-temporal depression detection

Carneirodemelo, Wheidima, Granger, Eric G. and Bordallo Lopez, Miguel. 2023. « MDN: A deep maximization-differentiation network for spatio-temporal depression detection ». IEEE Transactions on Affective Computing, vol. 14, nº 1. pp. 578-590.
Compte des citations dans Scopus : 35.

[thumbnail of Granger-E-2023-22651.pdf]
Preview
PDF
Granger-E-2023-22651.pdf - Published Version
Use licence: Creative Commons CC BY.

Download (1MB) | Preview

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

Item Type: Peer reviewed article published in a journal
Professor:
Professor
Granger, Éric
Affiliation: Génie des systèmes
Date Deposited: 20 May 2021 20:47
Last Modified: 12 Jul 2023 13:35
URI: https://espace2.etsmtl.ca/id/eprint/22651

Actions (login required)

View Item View Item