Structural Dependence Learning Based on Self-attention for Face Alignment

doi:10.1007/s11633-023-1465-1

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	Structural Dependence Learning Based on Self-attention for Face Alignment
	Biying Li 1,2; Zhiwei Liu1 ; Wei Zhou 3; Haiyun Guo1 ; Xin Wen 4; Min Huang 2; Jinqiao Wang1,2
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2024
卷号	21 期号:3 页码:514-525
摘要	Self-attention aggregates similar feature information to enhance the features. However, the attention covers nonface areas in face alignment, which may be disturbed in challenging cases, such as occlusions, and fails to predict landmarks. In addition, the learned feature similarity variance is not large enough in the experiment. To this end, we propose structural dependence learning based on self-attention for face alignment (SSFA). It limits the self-attention learning to the facial range and adaptively builds the significant landmark structure dependency. Compared with other state-of-the-art methods, SSFA effectively improves the performance on several standard facial landmark detection benchmarks and adapts more in challenging cases.
关键词	Computer vision, face alignment, self-attention, facial structure, contextual information
DOI	10.1007/s11633-023-1465-1
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/56479
专题	学术期刊_Machine Intelligence Research
作者单位	1.Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100083, China 3.Alpha (Beijing) Private Equity, Beijing 100083, China 4.School of Computer Science, National University of Defense Technology, Changsha 410073, China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Biying Li,Zhiwei Liu,Wei Zhou,et al. Structural Dependence Learning Based on Self-attention for Face Alignment[J]. Machine Intelligence Research,2024,21(3):514-525.
APA	Biying Li.,Zhiwei Liu.,Wei Zhou.,Haiyun Guo.,Xin Wen.,...&Jinqiao Wang.(2024).Structural Dependence Learning Based on Self-attention for Face Alignment.Machine Intelligence Research,21(3),514-525.
MLA	Biying Li,et al."Structural Dependence Learning Based on Self-attention for Face Alignment".Machine Intelligence Research 21.3(2024):514-525.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2022-11-331.pdf（5139KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载