CASIA OpenIR  > 精密感知与控制研究中心  > 人工智能与机器学习
The Twist Tensor Nuclear Norm for Video Completion
Hu, Wenrui1; Tao, Dacheng2; Zhang, Wensheng1; Xie, Yuan1; Yang, Yehui1; Wensheng Zhang
Source PublicationIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
2017-12-01
Volume28Issue:12Pages:2961-2973
SubtypeArticle
AbstractIn this paper, we propose a new low-rank tensor model based on the circulant algebra, namely, twist tensor nuclear norm (t-TNN). The twist tensor denotes a three-way tensor representation to laterally store 2-D data slices in order. On one hand, t-TNN convexly relaxes the tensor multirank of the twist tensor in the Fourier domain, which allows an efficient computation using fast Fourier transform. On the other, t-TNN is equal to the nuclear norm of block circulant matricization of the twist tensor in the original domain, which extends the traditional matrix nuclear norm in a block circulant way. We test the t-TNN model on a video completion application that aims to fill missing values and the experiment results validate its effectiveness, especially when dealing with video recorded by a nonstationary panning camera. The block circulant matricization of the twist tensor can be transformed into a circulant block representation with nuclear norm invariance. This representation, after transformation, exploits the horizontal translation relationship between the frames in a video, and endows the t-TNN model with a more powerful ability to reconstruct panning videos than the existing state-of-the-art low-rank models.
KeywordLow-rank Tensor Estimation (Lrte) Tensor Multirank Tensor Nuclear Norm (Tnn) Twist Tensor Video Completion
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TNNLS.2016.2611525
WOS KeywordRANK ; IMAGE ; DECOMPOSITION ; REGULARIZATION ; APPROXIMATION ; FACTORIZATION ; FRAMEWORK
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(61402480 ; Australian Research Council(DP-140102164 ; 61432008 ; FT-130101457 ; 61472423 ; LE-140100061) ; 61502495 ; 61532006)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000416261400010
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12255
Collection精密感知与控制研究中心_人工智能与机器学习
Corresponding AuthorWensheng Zhang
Affiliation1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Univ Technol Sydney, Fac Engn & Informat Technol, Ctr Quantum Computat & Intelligent Syst, Ultimo, NSW 2007, Australia
Recommended Citation
GB/T 7714
Hu, Wenrui,Tao, Dacheng,Zhang, Wensheng,et al. The Twist Tensor Nuclear Norm for Video Completion[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2017,28(12):2961-2973.
APA Hu, Wenrui,Tao, Dacheng,Zhang, Wensheng,Xie, Yuan,Yang, Yehui,&Wensheng Zhang.(2017).The Twist Tensor Nuclear Norm for Video Completion.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,28(12),2961-2973.
MLA Hu, Wenrui,et al."The Twist Tensor Nuclear Norm for Video Completion".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 28.12(2017):2961-2973.
Files in This Item: Download All
File Name/Size DocType Version Access License
07579662.pdf(24685KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Hu, Wenrui]'s Articles
[Tao, Dacheng]'s Articles
[Zhang, Wensheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hu, Wenrui]'s Articles
[Tao, Dacheng]'s Articles
[Zhang, Wensheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hu, Wenrui]'s Articles
[Tao, Dacheng]'s Articles
[Zhang, Wensheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 07579662.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.