The Twist Tensor Nuclear Norm for Video Completion

doi:10.1109/TNNLS.2016.2611525

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 人工智能与机器学习（杨雪冰）-技术团队

	The Twist Tensor Nuclear Norm for Video Completion
	Hu, Wenrui1 ; Tao, Dacheng 2; Zhang, Wensheng1 ; Xie, Yuan1 ; Yang, Yehui1 ; Wensheng Zhang
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2017-12-01
卷号	28 期号:12 页码:2961-2973
文章类型	Article
摘要	In 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.
关键词	Low-rank Tensor Estimation (Lrte) Tensor Multirank Tensor Nuclear Norm (Tnn) Twist Tensor Video Completion
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TNNLS.2016.2611525
关键词[WOS]	RANK ; IMAGE ; DECOMPOSITION ; REGULARIZATION ; APPROXIMATION ; FACTORIZATION ; FRAMEWORK
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61402480 ; Australian Research Council(DP-140102164 ; 61432008 ; FT-130101457 ; 61472423 ; LE-140100061) ; 61502495 ; 61532006)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000416261400010
引用统计	被引频次：149[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12255
专题	多模态人工智能系统全国重点实验室_人工智能与机器学习（杨雪冰）-技术团队
通讯作者	Wensheng Zhang
作者单位	1.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
第一作者单位	中国科学院自动化研究所
推荐引用方式 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.

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
07579662.pdf（24685KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载