Dual-Branch Network with Dynamic Time Warping: Enhancing Micro-Expression Recognition Through Temporal Alignment
Symmetry · 01.05.2026 · 18 (5) · 775
DOI: 10.3390/sym18050775 ↗Kurz gefasst
Fachartikel in der Zeitschrift Symmetry, online erschienen am 01.05.2026. Verfasst von Qiaohong Yao und 4 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education of the People's Republic of China.
Abstract (Originalsprache)
Micro-expressions, subtle and often asymmetric facial movements, play a pivotal role in nonverbal emotional communication. Addressing the core challenges of temporal misalignment, fragmented feature extraction, and slow real-time detection in micro-expression recognition (MER), we propose a novel dual-branch spatiotemporal model for dynamic sequence MER. Leveraging MediaPipe for 3D facial feature extraction and Dynamic Time Warping (DTW) for sequence alignment, our method nonlinearly maps variable-length sequences to a fixed length. A hybrid data augmentation technique enhances model robustness, while the dual-branch network simultaneously captures local spatial features and global temporal dynamics. Experimental results on the CASMEII dataset demonstrate state-of-the-art performance with 99.22% accuracy, along with a significant improvement in real-time detection speed. This approach holds substantial practical value for applications in deception detection, mental health assessment, and human–computer interaction.
Förderung
- Ministry of Education of the People's Republic of China
Zitieren
APA
Yao, Q., Wang, M., Chen, D., Liu, D., & Li, Y. (2026). Dual-Branch Network with Dynamic Time Warping: Enhancing Micro-Expression Recognition Through Temporal Alignment. Symmetry, 18(5), 775. https://doi.org/10.3390/sym18050775
Vancouver
Yao Q, Wang M, Chen D, Liu D, Li Y. Dual-Branch Network with Dynamic Time Warping: Enhancing Micro-Expression Recognition Through Temporal Alignment. Symmetry. 2026;18(5):775. doi:10.3390/sym18050775
BibTeX
@article{Yao2026,
author = {Yao, Qiaohong and Wang, Mengmeng and Chen, Dayu and Liu, Dan and Li, Yubin},
title = {Dual-Branch Network with Dynamic Time Warping: Enhancing Micro-Expression Recognition Through Temporal Alignment},
journal = {Symmetry},
year = {2026},
volume = {18},
number = {5},
pages = {775},
doi = {10.3390/sym18050775}
}
EUVIMED