Supervised learning for parameterized Koopmans-Beckmann's graph matching

doi:10.1016/j.patrec.2020.12.012

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 机器人应用与理论组

	Supervised learning for parameterized Koopmans-Beckmann's graph matching
	Zeng, Shaofeng; Liu, Zhiyong; Yang, Xu
刊名	PATTERN RECOGNITION LETTERS
	2021-03-01
卷号	143 页码:8-13
关键词	Graph matching Koopmans-Beckmann Supervised learning Structured SVM
ISSN号	0167-8655
DOI	10.1016/j.patrec.2020.12.012
通讯作者	Zeng, Shaofeng(shaofeng.zeng@ia.ac.cn)
英文摘要	In this paper, we discuss a novel graph matching problem, namely the parameterized Koopmans- Beckmann's graph matching (KBGMw). KBGMw is defined by a weighted linear combination of a series of Koopmans-Beckmann's graph matching. First, we show that KBGMw can be taken as a special case of the parameterized Lawler's graph matching, subject to certain conditions. Second, based on structured SVM, we propose a supervised learning method for automatically estimating the parameters of KBGMw. Experimental results on both synthetic and real image matching data sets show that the proposed method achieves relatively better performances, even superior to some deep learning methods. (c) 2020 Elsevier B.V. All rights reserved.
资助项目	National Key Research and Development Plan of China[2016YFC0300801] ; National Key Research and Development Plan of China[2017YFB1300202] ; National Natural Science Foundation of China (NSFC)[61503383] ; National Natural Science Foundation of China (NSFC)[61633009] ; National Natural Science Foundation of China (NSFC)[U1613213]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000615785700002
资助机构	National Key Research and Development Plan of China ; National Natural Science Foundation of China (NSFC)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/43284]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组
通讯作者	Zeng, Shaofeng
作者单位	Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zeng, Shaofeng,Liu, Zhiyong,Yang, Xu. Supervised learning for parameterized Koopmans-Beckmann's graph matching[J]. PATTERN RECOGNITION LETTERS,2021,143:8-13.
APA	Zeng, Shaofeng,Liu, Zhiyong,&Yang, Xu.(2021).Supervised learning for parameterized Koopmans-Beckmann's graph matching.PATTERN RECOGNITION LETTERS,143,8-13.
MLA	Zeng, Shaofeng,et al."Supervised learning for parameterized Koopmans-Beckmann's graph matching".PATTERN RECOGNITION LETTERS 143(2021):8-13.