Micro‐Expression Recognition Under Occlusion Based on Expression Semantic Surface Texture
Annals of the New York Academy of Sciences · 2026
DOI: 10.1111/nyas.70180 ↗Kurz gefasst
Fachartikel in der Zeitschrift Annals of the New York Academy of Sciences, 2026. Verfasst von Maoyuan Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, China. Hauptthemen laut MEDLINE: Facial Expression, Pattern Recognition, Automated. Die Arbeit nennt 45 Literaturangaben. Gefördert von: Key Research Planning Project of National Language Committee.
Abstract (Originalsprache)
Micro‐expression recognition is a fine‐grained task aimed at capturing subtle, brief facial movements. However, facial occlusions in real‐world scenarios significantly challenge existing models, often leading to feature sparsity and disconnection. This arises from both the loss of spatial and temporal information, further disrupting feature dependencies across facial regions. To address these issues, we introduce the concept of expression semantic surface texture, designed to separate and reconstruct expression‐aware and expression‐irrelevant features. We propose a dual‐branch collaborative network: one branch extracts spatial features using optical flow and frame differencing, while the second branch filters out expression‐irrelevant features using occlusion position embedding and reconstructs expression‐aware features in occluded regions. Experiments show that our network effectively restores disrupted features and outperforms recent state‐of‐the‐art methods in occluded micro‐expression recognition.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, China.
- School of Computer Science, Central China Normal University, Wuhan, China.
- National Language Resources Monitoring & Research Center for Network Media, Central China Normal University, Wuhan, China.
- Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, China.
ORCID-Profile: Meng Zheng
Förderung
- Key Research Planning Project of National Language Committee
Zitieren
APA
Zhang, M., Wu, C., Zheng, M., & Chen, Z. (2026). Micro‐Expression Recognition Under Occlusion Based on Expression Semantic Surface Texture. Annals of the New York Academy of Sciences. https://doi.org/10.1111/nyas.70180
Vancouver
Zhang M, Wu C, Zheng M, Chen Z. Micro‐Expression Recognition Under Occlusion Based on Expression Semantic Surface Texture. Annals of the New York Academy of Sciences. 2026. doi:10.1111/nyas.70180
BibTeX
@article{Zhang2026,
author = {Zhang, Maoyuan and Wu, Chen and Zheng, Meng and Chen, Zhuo},
title = {Micro‐Expression Recognition Under Occlusion Based on Expression Semantic Surface Texture},
journal = {Annals of the New York Academy of Sciences},
year = {2026},
doi = {10.1111/nyas.70180}
}
EUVIMED