Knowledge Commons of Institute of Automation,CAS
Dual L-1-Normalized Context Aware Tensor Power Iteration and Its Applications to Multi-object Tracking and Multi-graph Matching | |
Hu, Weiming1,2,3![]() ![]() ![]() ![]() | |
发表期刊 | INTERNATIONAL JOURNAL OF COMPUTER VISION
![]() |
ISSN | 0920-5691 |
2019-10-16 | |
期号 | 128页码:33 |
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. |
关键词 | Multi-dimensional assignment Context hyper-context aware tensor power iteration Multi-object tracking Multi-graph matching |
DOI | 10.1007/s11263-019-01231-y |
关键词[WOS] | ASSIGNMENT ALGORITHM ; MULTITARGET TRACKING ; OPTIMIZATION ; MODEL |
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[61721004] ; Natural Science Foundation of China[61772225] ; NSFC[U1636218] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC040] ; CAS External Cooperation Key Project ; National Natural Science Foundation of Guangdong[2018B030311046] ; Beijing Natural Science Foundation[L172051] ; Natural Science Foundation of China[61751212] ; Natural Science Foundation of China[61721004] ; Natural Science Foundation of China[61772225] ; NSFC[U1636218] ; 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 |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000491042100001 |
出版者 | SPRINGER |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/26601 |
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 | 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 |
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,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(128):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(128),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 .128(2019):33. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Dual_L1-Normalized_C(6300KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论