Dual Learning for Joint Facial Landmark Detection and Action Unit Recognition
IEEE Transactions on Affective Computing · 01.04.2023 · 14 (2) · 1404-1416
DOI: 10.1109/taffc.2021.3114158 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Affective Computing, erschienen am 01.04.2023. Verfasst von Shangfei Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Ministry of Science and Technology of the People's Republic of China, Anhui Science and Technology Agency.
Abstract (Originalsprache)
Facial landmark detection and action unit (AU) recognition are two essential tasks in facial analysis. Previous works rarely consider the relationship between these complementary tasks. In this article, we introduce a novel multi-task dual learning framework to exploit the relationship between facial landmark detection and AU recognition while simultaneously addressing both tasks. When both tasks share middle-level features, common patterns can be exploited and middle- and high-level features can be used to perform facial landmark detection and AU recognition, respectively. In addition, a dual learning mechanism is designed to convert the predicted landmarks and AUs of the label space to the corresponding facial image of the image space, further exploring the strong correlations between the tasks. By jointly training the proposed method at both the feature and label levels, each task improves the other. Experiments on two benchmark databases demonstrate that the proposed method can leverage dependencies to boost the generalization of both tasks.
Förderung
- Ministry of Science and Technology of the People's Republic of China
- Anhui Science and Technology Agency
Zitieren
APA
Wang, S., Chang, Y., & Wang, C. (2023). Dual Learning for Joint Facial Landmark Detection and Action Unit Recognition. IEEE Transactions on Affective Computing, 14(2), 1404-1416. https://doi.org/10.1109/taffc.2021.3114158
Vancouver
Wang S, Chang Y, Wang C. Dual Learning for Joint Facial Landmark Detection and Action Unit Recognition. IEEE Transactions on Affective Computing. 2023;14(2):1404-1416. doi:10.1109/taffc.2021.3114158
BibTeX
@article{Wang2023,
author = {Wang, Shangfei and Chang, Yanan and Wang, Can},
title = {Dual Learning for Joint Facial Landmark Detection and Action Unit Recognition},
journal = {IEEE Transactions on Affective Computing},
year = {2023},
volume = {14},
number = {2},
pages = {1404--1416},
doi = {10.1109/taffc.2021.3114158}
}
EUVIMED