中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 视频内容安全团队
Context-Dependent Random Walk Graph Kernels and Tree Pattern Graph Matching Kernels With Applications to Action Recognition

文献类型：期刊论文

作者Hu, Weiming1; Wu, Baoxin1; Wang, Pei1; Yuan, Chunfeng1; Li, Yangxi2; Maybank, Stephen3
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2018-10-01
卷号27期号:10页码:5060-5075
关键词Visual action recognition graph kernel graph matching contexts tree patterns
ISSN号1057-7149
DOI10.1109/TIP.2018.2849885
通讯作者Yuan, Chunfeng(cfyuan@nlpr.ia.ac.cn)
英文摘要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.
WOS关键词FEATURES
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
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000438972400003
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Beijing Natural Science Foundation ; Natural Science Foundation of China ; NSFC ; Key Research Program of Frontier Sciences, CAS ; CAS External Cooperation Key Project
源URL[http://ir.ia.ac.cn/handle/173211/26337]  
专题自动化研究所_模式识别国家重点实验室_视频内容安全团队
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
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。