A novel facial expression recognition framework using deep learning based dynamic cross-domain dual attention network
PeerJ Computer Science · 09.05.2025 · 11 · e2866
DOI: 10.7717/peerj-cs.2866 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 09.05.2025. Verfasst von Ahmed Omar Alzahrani und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Systems and Technology, College of Computer Science and Engineering, University of Jeddah, Jeddah, Makkah, Saudi Arabia. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Jeddah, Jeddah, Saudi Arabia.
Abstract (Originalsprache)
Variations in domain targets have recently posed significant challenges for facial expression recognition tasks, primarily due to domain shifts. Current methods focus largely on global feature adoption to achieve domain-invariant learning; however, transferring local features across diverse domains remains an ongoing challenge. Additionally, during training on target datasets, these methods often suffer from reduced feature representation in the target domain due to insufficient discriminative supervision. To tackle these challenges, we propose a dynamic cross-domain dual attention network for facial expression recognition. Our model is specifically designed to learn domain-invariant features through separate modules for global and local adversarial learning. We also introduce a semantic-aware module to generate pseudo-labels, which computes semantic labels from both global and local features. We assess our model’s effectiveness through extensive experiments on the Real-world Affective Faces Database (RAF-DB), FER-PLUS, AffectNet, Expression in the Wild (ExpW), SFEW 2.0, and Japanese Female Facial Expression (JAFFE) datasets. The results demonstrate that our scheme outperforms the existing state-of-the-art methods by attaining recognition accuracies 93.18, 92.35, 82.13, 78.37, 72.47, 70.68 respectively.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Information Systems and Technology, College of Computer Science and Engineering, University of Jeddah, Jeddah, Makkah, Saudi Arabia.
- Department of Software Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah, Makkah, Saudi Arabia.
- Department of Computer Science, Government College Women University Sialkot, Sialkot, Punjab, Pakistan.
- Department of Computer Science, Bahria University, Lahore, Punjab, Pakistan.
ORCID-Profile: Ahmed Mohammed Alghamdi, Nadeem Sarwar
Förderung
- University of Jeddah, Jeddah, Saudi Arabia
Zitieren
APA
Alzahrani, A. O., Alghamdi, A. M., Ashraf, M. U., Ilyas, I., Sarwar, N., Alzahrani, A., & Alarood, A. A. S. (2025). A novel facial expression recognition framework using deep learning based dynamic cross-domain dual attention network. PeerJ Computer Science, 11, e2866. https://doi.org/10.7717/peerj-cs.2866
Vancouver
Alzahrani AO, Alghamdi AM, Ashraf MU, Ilyas I, Sarwar N, Alzahrani A, et al. A novel facial expression recognition framework using deep learning based dynamic cross-domain dual attention network. PeerJ Computer Science. 2025;11:e2866. doi:10.7717/peerj-cs.2866
BibTeX
@article{Alzahrani2025,
author = {Alzahrani, Ahmed Omar and Alghamdi, Ahmed Mohammed and Ashraf, M Usman and Ilyas, Iqra and Sarwar, Nadeem and Alzahrani, Abdulrahman and Alarood, Alaa Abdul Salam},
title = {A novel facial expression recognition framework using deep learning based dynamic cross-domain dual attention network},
journal = {PeerJ Computer Science},
year = {2025},
volume = {11},
pages = {e2866},
doi = {10.7717/peerj-cs.2866}
}
EUVIMED