The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
시각적 데이터 수집 중 불가피한 데이터 누락 문제로 인해 제한된 유용한 정보에서 컬러 이미지 및 비디오를 복구하는 것이 중요한 주제가 되었으며, 이전 연구에서 텐서 완성이 유망한 솔루션임이 입증되었습니다. 본 논문에서는 텐서로 표현되는 컬러 이미지와 비디오에서 누락된 항목을 효과적으로 복구할 수 있는 새로운 완성 기법을 제안합니다. 우리는 먼저 시각적 데이터의 텐서에서 상대적으로 중요한 정보 데이터만 보존하는 더 잘 구성되고 균형 잡힌 텐서를 생성하기 위해 TT 순위 개념의 텐서 근사 방식으로 수정된 TT(텐서 트레인) 분해를 사용합니다. 이후에는 텐서 완성 문제에서 가중치 값을 적응적으로 정의할 수 있는 TT 순위 기반 가중치 체계를 추가로 소개합니다. 마지막으로 두 가지 방식을 Tensor Train을 통한 Simple Low Rank Tensor Completion(SiLRTC-TT)과 결합하여 완성 알고리즘인 LRATC-ATT(Adaptive Tensor Train을 통한 Low Rank Approximated Tensor Completion via Adaptive Tensor Train)를 구성합니다. 실험 결과는 제안된 접근 방식이 누락 비율이 높은 시각적 데이터의 텐서를 복구하는 데 있어 일반적인 텐서 완성 알고리즘보다 성능이 우수하다는 것을 검증합니다.
Ying CAO
Nanjing University of Posts and Telecommunications
Lijuan SUN
Nanjing University of Posts and Telecommunications,Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks
Chong HAN
Nanjing University of Posts and Telecommunications,Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks
Jian GUO
Nanjing University of Posts and Telecommunications,Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Ying CAO, Lijuan SUN, Chong HAN, Jian GUO, "A Novel Completion Algorithm for Color Images and Videos Based on Tensor Train Rank" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 3, pp. 609-619, March 2019, doi: 10.1587/transinf.2018EDP7291.
Abstract: Due to the inevitable data missing problem during visual data acquisition, the recovery of color images and videos from limited useful information has become an important topic, for which tensor completion has been proved to be a promising solution in previous studies. In this paper, we propose a novel completion scheme, which can effectively recover missing entries in color images and videos represented by tensors. We first employ a modified tensor train (TT) decomposition as tensor approximation scheme in the concept of TT rank to generate better-constructed and more balanced tensors which preserve only relatively significant informative data in tensors of visual data. Afterwards, we further introduce a TT rank-based weight scheme which can define the value of weights adaptively in tensor completion problem. Finally, we combine the two schemes with Simple Low Rank Tensor Completion via Tensor Train (SiLRTC-TT) to construct our completion algorithm, Low Rank Approximated Tensor Completion via Adaptive Tensor Train (LRATC-ATT). Experimental results validate that the proposed approach outperforms typical tensor completion algorithms in recovering tensors of visual data even with high missing ratios.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDP7291/_p
부
@ARTICLE{e102-d_3_609,
author={Ying CAO, Lijuan SUN, Chong HAN, Jian GUO, },
journal={IEICE TRANSACTIONS on Information},
title={A Novel Completion Algorithm for Color Images and Videos Based on Tensor Train Rank},
year={2019},
volume={E102-D},
number={3},
pages={609-619},
abstract={Due to the inevitable data missing problem during visual data acquisition, the recovery of color images and videos from limited useful information has become an important topic, for which tensor completion has been proved to be a promising solution in previous studies. In this paper, we propose a novel completion scheme, which can effectively recover missing entries in color images and videos represented by tensors. We first employ a modified tensor train (TT) decomposition as tensor approximation scheme in the concept of TT rank to generate better-constructed and more balanced tensors which preserve only relatively significant informative data in tensors of visual data. Afterwards, we further introduce a TT rank-based weight scheme which can define the value of weights adaptively in tensor completion problem. Finally, we combine the two schemes with Simple Low Rank Tensor Completion via Tensor Train (SiLRTC-TT) to construct our completion algorithm, Low Rank Approximated Tensor Completion via Adaptive Tensor Train (LRATC-ATT). Experimental results validate that the proposed approach outperforms typical tensor completion algorithms in recovering tensors of visual data even with high missing ratios.},
keywords={},
doi={10.1587/transinf.2018EDP7291},
ISSN={1745-1361},
month={March},}
부
TY - JOUR
TI - A Novel Completion Algorithm for Color Images and Videos Based on Tensor Train Rank
T2 - IEICE TRANSACTIONS on Information
SP - 609
EP - 619
AU - Ying CAO
AU - Lijuan SUN
AU - Chong HAN
AU - Jian GUO
PY - 2019
DO - 10.1587/transinf.2018EDP7291
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2019
AB - Due to the inevitable data missing problem during visual data acquisition, the recovery of color images and videos from limited useful information has become an important topic, for which tensor completion has been proved to be a promising solution in previous studies. In this paper, we propose a novel completion scheme, which can effectively recover missing entries in color images and videos represented by tensors. We first employ a modified tensor train (TT) decomposition as tensor approximation scheme in the concept of TT rank to generate better-constructed and more balanced tensors which preserve only relatively significant informative data in tensors of visual data. Afterwards, we further introduce a TT rank-based weight scheme which can define the value of weights adaptively in tensor completion problem. Finally, we combine the two schemes with Simple Low Rank Tensor Completion via Tensor Train (SiLRTC-TT) to construct our completion algorithm, Low Rank Approximated Tensor Completion via Adaptive Tensor Train (LRATC-ATT). Experimental results validate that the proposed approach outperforms typical tensor completion algorithms in recovering tensors of visual data even with high missing ratios.
ER -