Region-Based Context Enhanced Network for Robust Multiple Face Alignment

doi:10.1109/TMM.2019.2916455

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 生物识别与安全技术

	Region-Based Context Enhanced Network for Robust Multiple Face Alignment
	Lin, Xuxin 1; Liang, Yanyan 1; Wan, Jun2 ; Lin, Chi 3; Li, Stan Z.2
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
	2019-12-01
卷号	21 期号:12 页码:3053-3067
通讯作者	Liang, Yanyan(yyliang@must.edu.mo)
摘要	The recent studies for face alignment have involved developing an isolated algorithm on well-cropped face images. It is difficult to obtain the expected input by using an off-the-shelf face detector in practical applications. In this paper, we attempt to bridge between face detection and face alignment by establishing a novel joint multi-task model, which allows us to simultaneously detect multiple faces and their landmarks on a given scene image. In contrast to the pipeline-based framework by cascading separate models, we aim to propose an end-to-end convolutional network by sharing and transform feature representations between the task-specific modules. To learn a robust landmark estimator for unconstrained face alignment, three types of context enhanced blocks are designed to encode feature maps with multi-level context, multi-scale context, and global context. In the post-processing step, we develop a shape reconstruction algorithm based on point distribution model to refine the landmark outliers. Extensive experiments demonstrate that our results are robust for the landmark location task and insensitive to the location of estimated face regions. Furthermore, our method significantly outperforms recent state-of-the-art methods on several challenging datasets including 300 W, AFLW, and COFW.
关键词	Facial landmark localization face alignment convolutional network point distribution model
DOI	10.1109/TMM.2019.2916455
关键词[WOS]	FACIAL LANDMARK DETECTION
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Plan[2016YFC0801002] ; Chinese National Natural Science Foundation[61876179] ; Chinese National Natural Science Foundation[61872367] ; Science and Technology Development Fund of Macau[152/2017/A] ; Science and Technology Development Fund of Macau[0025/2018/A1] ; Science and Technology Development Fund of Macau[008/2019/A1] ; National Key Research and Development Plan[2016YFC0801002] ; Chinese National Natural Science Foundation[61876179] ; Chinese National Natural Science Foundation[61872367] ; Science and Technology Development Fund of Macau[152/2017/A] ; Science and Technology Development Fund of Macau[0025/2018/A1] ; Science and Technology Development Fund of Macau[008/2019/A1]
项目资助者	National Key Research and Development Plan ; Chinese National Natural Science Foundation ; Science and Technology Development Fund of Macau
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:000512345200007
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：11[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/28585
专题	多模态人工智能系统全国重点实验室_生物识别与安全技术
通讯作者	Liang, Yanyan
作者单位	1.Macau Univ Sci & Technol, Fac Informat Technol, Taipa, Macau, Peoples R China 2.Chinese Acad Sci, Inst Automat, Res & Natl Lab Pattern Recognit, Ctr Biometr & Secur, Beijing 100190, Peoples R China 3.Univ Southern Calif, Los Angeles, CA 90007 USA
推荐引用方式 GB/T 7714	Lin, Xuxin,Liang, Yanyan,Wan, Jun,et al. Region-Based Context Enhanced Network for Robust Multiple Face Alignment[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2019,21(12):3053-3067.
APA	Lin, Xuxin,Liang, Yanyan,Wan, Jun,Lin, Chi,&Li, Stan Z..(2019).Region-Based Context Enhanced Network for Robust Multiple Face Alignment.IEEE TRANSACTIONS ON MULTIMEDIA,21(12),3053-3067.
MLA	Lin, Xuxin,et al."Region-Based Context Enhanced Network for Robust Multiple Face Alignment".IEEE TRANSACTIONS ON MULTIMEDIA 21.12(2019):3053-3067.