TIIS (Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
Facial Action Unit Detection with Multilayer Fused Multi-Task and Multi-Label Deep Learning Network |
¿µ¹®Á¦¸ñ(English Title) |
Facial Action Unit Detection with Multilayer Fused Multi-Task and Multi-Label Deep Learning Network |
ÀúÀÚ(Author) |
Jun He
Dongliang Li
Sun Bo
Lejun Yu
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 13 NO. 11 PP. 5546 ~ 5559 (2019. 11) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
Facial action units (AUs) have recently drawn increased attention because they can be used to recognize facial expressions. A variety of methods have been designed for frontal-view AU detection, but few have been able to handle multi-view face images. In this paper we propose a method for multi-view facial AU detection using a fused multilayer, multi-task, and multi-label deep learning network. The network can complete two tasks: AU detection and facial view detection. AU detection is a multi-label problem and facial view detection is a single-label problem. A residual network and multilayer fusion are applied to obtain more representative features. Our method is effective and performs well. The F1 score on FERA 2017 is 13.1% higher than the baseline. The facial view recognition accuracy is 0.991. This shows that our multi-task, multi-label model could achieve good performance on the two tasks.
|
Å°¿öµå(Keyword) |
facial action unit
multi-task learning
multi-label learning
multilayer fusion
deep learning
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|