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. 重庆绿色智能技术研究院
  3. 中国科学院重庆绿色智能技术研究院
Low-Rank High-Order Tensor Completion With Applications in Visual Data

文献类型：期刊论文

作者Qin, Wenjin3; Wang, Hailin4; Zhang, Feng3; Wang, Jianjun3,5; Luo, Xin2,6; Huang, Tingwen1
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2022
卷号31页码:2433-2448
关键词Low-rank order-d tensor completion order-d tensor singular value decomposition invertible linear transforms convex optimization sparsity measure
ISSN号1057-7149
DOI10.1109/TIP.2022.3155949
通讯作者Wang, Jianjun(wjj@swu.edu.cn)
英文摘要Recently, tensor Singular Value Decomposition (t-SVD)-based low-rank tensor completion (LRTC) has achieved unprecedented success in addressing various pattern analysis issues. However, existing studies mostly focus on third-order tensors while order-d (d >= 4) tensors are commonly encountered in real-world applications, like fourth-order color videos, fourth-order hyper-spectral videos, fifth-order light-field images, and sixth-order bidirectional texture functions. Aiming at addressing this critical issue, this paper establishes an order-d tensor recovery framework including the model, algorithm and theories by innovatively developing a novel algebraic foundation for order-d t-SVD, thereby achieving exact completion for any order-d low t-SVD rank tensors with missing values with an overwhelming probability. Emperical studies on synthetic data and real-world visual data illustrate that compared with other state-of-the-art recovery frameworks, the proposed one achieves highly competitive performance in terms of both qualitative and quantitative metrics. In particular, as the observed data density becomes low, i.e., about 10%, the proposed recovery framework is still significantly better than its peers. The code of our algorithm is released at https://github.com/Qinwenjinswu/TIP-Code
资助项目National Natural Science Foundation of China[12071380] ; National Natural Science Foundation of China[12101512] ; National Natural Science Foundation of China[11971374] ; National Natural Science Foundation of China[62063028] ; National Key Research and Development Program of China[2021YFB3101500] ; China Postdoctoral Science Foundation[2021M692681] ; Natural Science Foundation of Chongqing, China[cstc2021jcyj-bshX0155] ; Fundamental Research Funds for the Central Universities[SWU120078]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000769973200009
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.138/handle/2HOD01W0/15338]  
专题中国科学院重庆绿色智能技术研究院
通讯作者Wang, Jianjun
作者单位1.Texas A&M Univ Qatar, Dept Math, Doha, Qatar
2.Hengrui Chongqing Artificial Intelligence Res Ctr, Dept Big Data Analyses Tech, Chongqing 401331, Peoples R China
3.Southwest Univ, Sch Math & Stat, Chongqing 400715, Peoples R China
4.Xi An Jiao Tong Univ, Sch Math & Stat, Xian 710049, Peoples R China
5.Southwest Univ, Res Inst Intelligent Finance & Digital Econ, Chongqing 400715, Peoples R China
6.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing Key Lab Big Data & Intelligent Comp, Chongqing 400714, Peoples R China
推荐引用方式
GB/T 7714		 Qin, Wenjin,Wang, Hailin,Zhang, Feng,et al. Low-Rank High-Order Tensor Completion With Applications in Visual Data[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2022,31:2433-2448.
APA Qin, Wenjin,Wang, Hailin,Zhang, Feng,Wang, Jianjun,Luo, Xin,&Huang, Tingwen.(2022).Low-Rank High-Order Tensor Completion With Applications in Visual Data.IEEE TRANSACTIONS ON IMAGE PROCESSING,31,2433-2448.
MLA Qin, Wenjin,et al."Low-Rank High-Order Tensor Completion With Applications in Visual Data".IEEE TRANSACTIONS ON IMAGE PROCESSING 31(2022):2433-2448.

入库方式： OAI收割

来源：重庆绿色智能技术研究院

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。