Lightweight Representation of Motion-Magnified Facial Dynamics for Micro Expression Sensing
Sensors · 11.06.2026 · 26 (12) · 3727
DOI: 10.3390/s26123727 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 11.06.2026. Verfasst von Seungho Lee und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Future Technology, Korea University of Technology and Education, Cheonan 31253, Republic of Korea. Hauptthemen laut MEDLINE: Facial Expression, Face. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation, Korea government, Education and Research promotion program (10%) of KOREATECH.
Abstract (Originalsprache)
Reliable monitoring of spontaneous affect is essential in biomedical sensing, where involuntary facial signals serve as objective indicators of physiological states. Micro expression recognition (MER) is particularly challenging due to the sub-second, low amplitude nature of these signals. Many existing MER methods rely on apex (peak) frame detection, making them sensitive to temporal localization errors and difficult to deploy in unconstrained settings. To address this, we propose an apex-free framework that analyzes facial dynamics by structuring motion-magnified features along a newly introduced magnification intensity axis. By applying Eulerian motion magnification across multiple discrete levels and collapsing the sequences into single accumulation images, we generate a multi-level representation of subtle facial dynamics without requiring frame-level annotations. A lightweight shared temporal mixer (STM) is employed to analyze the dynamic evolution of motion across the magnification intensity axis. Subsequently, a dual-branch convolutional neural network (CNN), processing low- and high-amplification regimes respectively, integrates a convolutional block attention module (CBAM) to capture subtle facial motion while effectively filtering out irrelevant noise. Our model is highly efficient, requiring only 0.94 M parameters and 262 MFLOPs, which is significantly lower than the computational demands of standard backbones such as ResNet18 or VGG16. To ensure the model generalizes to new individuals, we evaluated it by testing on subjects whose data was entirely excluded from the training process. Under this rigorous setup, the proposed method achieves approximately 80% and 70% accuracy on the CASME II and SMIC datasets respectively, showing performance comparable to, or in some cases, slightly above current state-of-the-art methods. Considering both the competitive accuracy and high computational efficiency, the proposed framework holds significant potential for practical integration into real-time affect monitoring systems, particularly within biomedical applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Future Technology, Korea University of Technology and Education, Cheonan 31253, Republic of Korea.
- School of Industrial Management, Korea University of Technology and Education, Cheonan 31253, Republic of Korea.
Förderung
- Institute of Information & Communications Technology Planning & Evaluation
- Korea government
- Education and Research promotion program (10%) of KOREATECH
Zitieren
APA
Lee, S., & Lee, S. (2026). Lightweight Representation of Motion-Magnified Facial Dynamics for Micro Expression Sensing. Sensors, 26(12), 3727. https://doi.org/10.3390/s26123727
Vancouver
Lee S, Lee S. Lightweight Representation of Motion-Magnified Facial Dynamics for Micro Expression Sensing. Sensors. 2026;26(12):3727. doi:10.3390/s26123727
BibTeX
@article{Lee2026,
author = {Lee, Seungho and Lee, Sangkon},
title = {Lightweight Representation of Motion-Magnified Facial Dynamics for Micro Expression Sensing},
journal = {Sensors},
year = {2026},
volume = {26},
number = {12},
pages = {3727},
doi = {10.3390/s26123727}
}
EUVIMED