Sub-hypergraph matching based on adjacency tensor

doi:10.1016/j.cviu.2019.03.003

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	Sub-hypergraph matching based on adjacency tensor
	Yang, Jing1,2 ; Yang, Xu2 ; Zhou, Zhang-Bing 1,3; Liu, Zhi-Yong2,4,5
发表期刊	COMPUTER VISION AND IMAGE UNDERSTANDING
ISSN	1077-3142
	2019-06-01
卷号	183 页码:1-10
通讯作者	Yang, Xu() ; Zhou, Zhang-Bing(zhangbing.zhou@gmail.com)
摘要	Point correspondence problem is an important problem in pattern recognition and computer vision, which can be solved by graph matching. Recently, high order graph matching methods have attracted much attention due to their robustness to geometric transformations. Since high order graph matching usually suffers from high complexity, we previously proposed an adjacency tensor based algorithm, which effectively reduced the complexity of high order graph matching, especially high storage complexity. However, this method can only be applied to equal sized hypergraphs, and it cannot be directly extended to hypergraphs with outliers which are common in real world tasks. Aiming at this problem, in this paper we propose a third order subgraph matching method by extending our previous method to deal with partial point correspondence problem with outliers. Specifically, first a novel objective function focusing on the outlier problem is proposed, by encoding the attributes in a hypergraph with an adjacency tensor, and representing vertex assignments with a partial permutation matrix. Then the objective function is transformed and relaxed to a tractable matrix form and solved by a gradient based optimization algorithm. Consequently, the proposed algorithm can not only tackle the outlier vertices in the hypergraphs, but also involve the same low computational and storage complexities with our previous algorithm. Both synthetic data and real image comparisons with the state-of-the-art methods validate the effectiveness of the proposed method.
关键词	Hypergraph matching Subgraph matching High order structure Adjacency tensor
DOI	10.1016/j.cviu.2019.03.003
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2016YFC0300801] ; National Key R&D Program of China[2017YFB1300202] ; National Natural Science Foundation (NSFC) of China[61503383] ; National Natural Science Foundation (NSFC) of China[61633009] ; National Natural Science Foundation (NSFC) of China[U1613213] ; National Natural Science Foundation (NSFC) of China[61773047] ; National Natural Science Foundation (NSFC) of China[61772479] ; National Natural Science Foundation (NSFC) of China[61662021] ; National Natural Science Foundation (NSFC) of China[61662021] ; National Natural Science Foundation (NSFC) of China[61772479] ; National Natural Science Foundation (NSFC) of China[61773047] ; National Natural Science Foundation (NSFC) of China[U1613213] ; National Natural Science Foundation (NSFC) of China[61633009] ; National Natural Science Foundation (NSFC) of China[61503383] ; National Key R&D Program of China[2017YFB1300202] ; National Key R&D Program of China[2016YFC0300801] ; National Key R&D Program of China[2016YFC0300801] ; National Key R&D Program of China[2017YFB1300202] ; National Natural Science Foundation (NSFC) of China[61503383] ; National Natural Science Foundation (NSFC) of China[61633009] ; National Natural Science Foundation (NSFC) of China[U1613213] ; National Natural Science Foundation (NSFC) of China[61773047] ; National Natural Science Foundation (NSFC) of China[61772479] ; National Natural Science Foundation (NSFC) of China[61662021]
项目资助者	National Key R&D Program of China ; National Natural Science Foundation (NSFC) of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000469164200001
出版者	ACADEMIC PRESS INC ELSEVIER SCIENCE
七大方向——子方向分类	模式识别基础
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/24391
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
通讯作者	Yang, Xu; Zhou, Zhang-Bing
作者单位	1.China Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.TELECOM SudParis, Comp Sci Dept, F-91011 Evry, France 4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China 5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Yang, Jing,Yang, Xu,Zhou, Zhang-Bing,et al. Sub-hypergraph matching based on adjacency tensor[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2019,183:1-10.
APA	Yang, Jing,Yang, Xu,Zhou, Zhang-Bing,&Liu, Zhi-Yong.(2019).Sub-hypergraph matching based on adjacency tensor.COMPUTER VISION AND IMAGE UNDERSTANDING,183,1-10.
MLA	Yang, Jing,et al."Sub-hypergraph matching based on adjacency tensor".COMPUTER VISION AND IMAGE UNDERSTANDING 183(2019):1-10.