Geometric Graph Representation With Learnable Graph Structure and Adaptive AU Constraint for Micro-Expression Recognition
IEEE Transactions on Affective Computing · 2024-07 · 15 (3) · 1343-1357
DOI: 10.1109/taffc.2023.3340016 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Affective Computing, 2024-07. Verfasst von Jinsheng Wei und 5 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: National Association of public funds Natural Science Research Start up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications, Nanjing Science and Technology Innovation Foundation for Overseas Students, National Natural Science Foundation of China.
Abstract (Originalsprache)
Micro-expression recognition (MER) holds significance in uncovering hidden emotions. Most works take image sequences as input and cannot effectively explore ME information because subtle ME-related motions are easily submerged in unrelated information. Instead, the facial landmark is a lowdimensional and compact modality, which achieves lower computational cost and potentially concentrates on ME-related movement features. However, the discriminability of facial landmarks for MER is unclear. Thus, this paper investigates the contribution of facial landmarks and proposes a novel framework to efficiently recognize MEs with facial landmarks. Firstly, a geometric twostream graph network is constructed to aggregate the low-order and high-order geometric movement information from facial landmarks to obtain discriminative ME representation. Secondly, a self-learning fashion is introduced to automatically model the dynamic relationship between nodes even long-distance nodes. Furthermore, an adaptive action unit loss is proposed to reasonably build a strong correlation between landmarks, facial action units and MEs. Notably, this work provides a novel idea with much higher efficiency to promote MER, only utilizing graphbased geometric features. The experimental results demonstrate that the proposed method achieves competitive performance with a significantly reduced computational cost. Furthermore, facial landmarks significantly contribute to MER and are worth further study for high-efficient ME analysis.
Förderung
- National Association of public funds Natural Science Research Start up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications
- Nanjing Science and Technology Innovation Foundation for Overseas Students
- National Natural Science Foundation of China
- China Scholarship Council
- Research Council of Finland
- Academy of Finland
- Academy Professor project EmotionAI
- ICT 2023 project TrustFace
Zitieren
APA
Wei, J., Peng, W., Lu, G., Li, Y., Yan, J., & Zhao, G. (2024). Geometric Graph Representation With Learnable Graph Structure and Adaptive AU Constraint for Micro-Expression Recognition. IEEE Transactions on Affective Computing, 15(3), 1343-1357. https://doi.org/10.1109/taffc.2023.3340016
Vancouver
Wei J, Peng W, Lu G, Li Y, Yan J, Zhao G. Geometric Graph Representation With Learnable Graph Structure and Adaptive AU Constraint for Micro-Expression Recognition. IEEE Transactions on Affective Computing. 2024;15(3):1343-1357. doi:10.1109/taffc.2023.3340016
BibTeX
@article{Wei2024,
author = {Wei, Jinsheng and Peng, Wei and Lu, Guanming and Li, Yante and Yan, Jingjie and Zhao, Guoying},
title = {Geometric Graph Representation With Learnable Graph Structure and Adaptive AU Constraint for Micro-Expression Recognition},
journal = {IEEE Transactions on Affective Computing},
year = {2024},
volume = {15},
number = {3},
pages = {1343--1357},
doi = {10.1109/taffc.2023.3340016}
}
EUVIMED