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. 模式识别国家重点实验室
  5. 视频内容安全团队
Dual L-1-Normalized Context Aware Tensor Power Iteration and Its Applications to Multi-object Tracking and Multi-graph Matching

文献类型：期刊论文

作者Hu, Weiming1,2,3; Shi, Xinchu1,2,3; Zhou, Zongwei1,2,3; Xing, Junliang1,2,3; Ling, Haibin4; Maybank, Stephen5
刊名INTERNATIONAL JOURNAL OF COMPUTER VISION
出版日期2019-10-16
页码33
ISSN号0920-5691
关键词Multi-dimensional assignment Context hyper-context aware tensor power iteration Multi-object tracking Multi-graph matching
DOI10.1007/s11263-019-01231-y
通讯作者Hu, Weiming(wmhu@nlpr.ia.ac.cn)
英文摘要The multi-dimensional assignment problem is universal for data association analysis such as data association-based visual multi-object tracking and multi-graph matching. In this paper, multi-dimensional assignment is formulated as a rank-1 tensor approximation problem. A dual L-1-normalized context/hyper-context aware tensor power iteration optimization method is proposed. The method is applied to multi-object tracking and multi-graph matching. In the optimization method, tensor power iteration with the dual unit norm enables the capture of information across multiple sample sets. Interactions between sample associations are modeled as contexts or hyper-contexts which are combined with the global affinity into a unified optimization. The optimization is flexible for accommodating various types of contextual models. In multi-object tracking, the global affinity is defined according to the appearance similarity between objects detected in different frames. Interactions between objects are modeled as motion contexts which are encoded into the global association optimization. The tracking method integrates high order motion information and high order appearance variation. The multi-graph matching method carries out matching over graph vertices and structure matching over graph edges simultaneously. The matching consistency across multi-graphs is based on the high-order tensor optimization. Various types of vertex affinities and edge/hyper-edge affinities are flexibly integrated. Experiments on several public datasets, such as the MOT16 challenge benchmark, validate the effectiveness of the proposed methods.
WOS关键词ASSIGNMENT ALGORITHM ; MULTITARGET TRACKING ; OPTIMIZATION ; MODEL
资助项目NSFC[U1636218] ; Natural Science Foundation of China[61751212] ; Natural Science Foundation of China[61721004] ; Natural Science Foundation of China[61772225] ; Beijing Natural Science Foundation[L172051] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC040] ; CAS External cooperation key project ; National Natural Science Foundation of Guangdong[2018B030311046]
WOS研究方向Computer Science
语种英语
出版者SPRINGER
WOS记录号WOS:000491042100001
资助机构NSFC ; Natural Science Foundation of China ; Beijing Natural Science Foundation ; Key Research Program of Frontier Sciences, CAS ; CAS External cooperation key project ; National Natural Science Foundation of Guangdong
源URL[http://ir.ia.ac.cn/handle/173211/26600]  
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Hu, Weiming
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
2.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
4.SUNY Stony Brook, Dept Comp Sci, Stony Brook, NY 11794 USA
5.Birkbeck Coll, Dept Comp Sci & Informat Syst, Malet St, London WC1E 7HX, England
推荐引用方式
GB/T 7714		 Hu, Weiming,Shi, Xinchu,Zhou, Zongwei,et al. Dual L-1-Normalized Context Aware Tensor Power Iteration and Its Applications to Multi-object Tracking and Multi-graph Matching[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2019:33.
APA Hu, Weiming,Shi, Xinchu,Zhou, Zongwei,Xing, Junliang,Ling, Haibin,&Maybank, Stephen.(2019).Dual L-1-Normalized Context Aware Tensor Power Iteration and Its Applications to Multi-object Tracking and Multi-graph Matching.INTERNATIONAL JOURNAL OF COMPUTER VISION,33.
MLA Hu, Weiming,et al."Dual L-1-Normalized Context Aware Tensor Power Iteration and Its Applications to Multi-object Tracking and Multi-graph Matching".INTERNATIONAL JOURNAL OF COMPUTER VISION (2019):33.

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。