Context-Dependent Random Walk Graph Kernels and Tree Pattern Graph Matching Kernels With Applications to Action Recognition

doi:10.1109/TIP.2018.2849885

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	Context-Dependent Random Walk Graph Kernels and Tree Pattern Graph Matching Kernels With Applications to Action Recognition
	Hu, Weiming1 ; Wu, Baoxin 1; Wang, Pei1 ; Yuan, Chunfeng1 ; Li, Yangxi 2; Maybank, Stephen 3
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2018-10-01
卷号	27 期号:10 页码:5060-5075
通讯作者	Yuan, Chunfeng(cfyuan@nlpr.ia.ac.cn)
摘要	Graphs are effective tools for modeling complex data. Setting out from two basic substructures, random walks and trees, we propose a new family of context-dependent random walk graph kernels and a new family of tree pattern graph matching kernels. In our context-dependent graph kernels, context information is incorporated into primary random walk groups. A multiple kernel learning algorithm with a proposed l(1),(2)-norm regularization is applied to combine context-dependent graph kernels of different orders. This improves the similarity measurement between graphs. In our tree-pattern graph matching kernel, a quadratic optimization with a sparse constraint is proposed to select the correctly matched tree-pattern groups. This augments the discriminative power of the tree-pattern graph matching. We apply the proposed kernels to human action recognition, where each action is represented by two graphs which record the spatiotemporal relations between local feature vectors. Experimental comparisons with state-of-the-art algorithms on several benchmark data sets demonstrate the effectiveness of the proposed kernels for recognizing human actions. It is shown that our kernel based on tree-pattern groups, which have more complex structures and exploit more local topologies of graphs than random walks, yields more accurate results but requires more runtime than the context-dependent walk graph kernel.
关键词	Visual action recognition graph kernel graph matching contexts tree patterns
DOI	10.1109/TIP.2018.2849885
关键词[WOS]	FEATURES
收录类别	SCI
语种	英语
资助项目	Beijing Natural Science Foundation[L172051] ; Natural Science Foundation of China[61751212] ; Natural Science Foundation of China[61472421] ; Natural Science Foundation of China[61721004] ; Natural Science Foundation of China[61772225] ; NSFC[U1636218] ; NSFC[U1736106] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC040] ; CAS External Cooperation Key Project ; Beijing Natural Science Foundation[L172051] ; Natural Science Foundation of China[61751212] ; Natural Science Foundation of China[61472421] ; Natural Science Foundation of China[61721004] ; Natural Science Foundation of China[61772225] ; NSFC[U1636218] ; NSFC[U1736106] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC040] ; CAS External Cooperation Key Project
项目资助者	Beijing Natural Science Foundation ; Natural Science Foundation of China ; NSFC ; Key Research Program of Frontier Sciences, CAS ; CAS External Cooperation Key Project
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000438972400003
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：6[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/173211/26338
专题	多模态人工智能系统全国重点实验室_视频内容安全
通讯作者	Yuan, Chunfeng
作者单位	1.Univ Chinese Acad Sci, Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Inst Automat,Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Coordinat Ctr China, Natl Comp Network Emergency Response Tech Team, Beijing 100055, Peoples R China 3.Univ London, Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Hu, Weiming,Wu, Baoxin,Wang, Pei,et al. Context-Dependent Random Walk Graph Kernels and Tree Pattern Graph Matching Kernels With Applications to Action Recognition[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2018,27(10):5060-5075.
APA	Hu, Weiming,Wu, Baoxin,Wang, Pei,Yuan, Chunfeng,Li, Yangxi,&Maybank, Stephen.(2018).Context-Dependent Random Walk Graph Kernels and Tree Pattern Graph Matching Kernels With Applications to Action Recognition.IEEE TRANSACTIONS ON IMAGE PROCESSING,27(10),5060-5075.
MLA	Hu, Weiming,et al."Context-Dependent Random Walk Graph Kernels and Tree Pattern Graph Matching Kernels With Applications to Action Recognition".IEEE TRANSACTIONS ON IMAGE PROCESSING 27.10(2018):5060-5075.