Deep High-order Tensor Convolutional Sparse Coding for Stereo Matching

With the rapid development of science and technology, high-dimensional data emerge one after another. High-order tensors can be used to describe high-dimensional data structure, which can retain the hidden structure of data, but cannot obtain the deep features. Therefore, it is very important to est...

Full description

Saved in:
Bibliographic Details
Published in:2021 3rd International Conference on Robotics and Computer Vision (ICRCV) pp. 57 - 62
Main Authors: Cui, Wenjing, Cheng, Chunbo
Format: Conference Proceeding
Language:English
Published: IEEE 06.08.2021
Subjects:
Computer vision
Convolutional codes
convolutional sparse coding
Costs
Data structures
Deep learning
dictionary learning
Encoding
high-order tensor
stereo matching
Tensors
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract With the rapid development of science and technology, high-dimensional data emerge one after another. High-order tensors can be used to describe high-dimensional data structure, which can retain the hidden structure of data, but cannot obtain the deep features. Therefore, it is very important to establish a deep high order tensor model. In this paper, we propose a deep high-order tensor convolutional sparse coding model, which can automatically learn the deep convolutional kernel. Based on the learned deep convolutional kernel, a two-layer deep dictionary learning model is established. Then, the sparse representation coefficients are respectively solved, and a new weighted matching cost method is constructed, which combines shallow and deep features. The experimental results on the Middlebury 2014 dataset show that the proposed deep high-order tensor convolutional sparse coding is effective for stereo matching.
AbstractList With the rapid development of science and technology, high-dimensional data emerge one after another. High-order tensors can be used to describe high-dimensional data structure, which can retain the hidden structure of data, but cannot obtain the deep features. Therefore, it is very important to establish a deep high order tensor model. In this paper, we propose a deep high-order tensor convolutional sparse coding model, which can automatically learn the deep convolutional kernel. Based on the learned deep convolutional kernel, a two-layer deep dictionary learning model is established. Then, the sparse representation coefficients are respectively solved, and a new weighted matching cost method is constructed, which combines shallow and deep features. The experimental results on the Middlebury 2014 dataset show that the proposed deep high-order tensor convolutional sparse coding is effective for stereo matching.
Author Cui, Wenjing
Cheng, Chunbo
Author_xml – sequence: 1
  givenname: Wenjing
  surname: Cui
  fullname: Cui, Wenjing
  email: wjcui@hbpu.edu.cn
  organization: Hubei Polytechnic University,School of Mathematics and Physics,Huangshi,China
– sequence: 2
  givenname: Chunbo
  surname: Cheng
  fullname: Cheng, Chunbo
  email: bccheng@hbpu.edu.cn
  organization: Huazhong University of Science and Technology,School of Mathematics and Statistics,Wuhan,China
BookMark eNotj99KwzAchSPohZt7Ai_MC7TmT5Mml1KdG0yEbYp3I01_2QI1KWkVfPsF3NUH3zkcODN0HWIAhB4oKSkl-nHdbJtPwbSSJSOMllpUUkt-hWZUSlFxydTXLVo-Awx45Y-nIqYOEt5DGGPCTQy_sf-ZfAymx7vBpBGy7Hw4Ypfz3QQJIn4zkz1ld4dunOlHWFw4Rx_Ll32zKjbvr-vmaVN4StVUUKtr1hKolK6c5kxLwk1dW5VJrJOVpRqEbeu6EwIUtM51whGQuSuZIHyO7v93PQAchuS_Tfo7XK7xM2F_SOk
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICRCV52986.2021.9546963
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 166543628X
9781665436281
EndPage 62
ExternalDocumentID 9546963
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i118t-1c972b0e4894f9329603a77c86030cf64c19e5cb77d55e8ebffd5f0e693262503
IEDL.DBID RIE
IngestDate Thu Jun 29 18:37:36 EDT 2023
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i118t-1c972b0e4894f9329603a77c86030cf64c19e5cb77d55e8ebffd5f0e693262503
PageCount 6
ParticipantIDs ieee_primary_9546963
PublicationCentury 2000
PublicationDate 2021-Aug.-6
PublicationDateYYYYMMDD 2021-08-06
PublicationDate_xml – month: 08
  year: 2021
  text: 2021-Aug.-6
  day: 06
PublicationDecade 2020
PublicationTitle 2021 3rd International Conference on Robotics and Computer Vision (ICRCV)
PublicationTitleAbbrev ICRCV
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.7661899
Snippet With the rapid development of science and technology, high-dimensional data emerge one after another. High-order tensors can be used to describe...
SourceID ieee
SourceType Publisher
StartPage 57
SubjectTerms Computer vision
Convolutional codes
convolutional sparse coding
Costs
Data structures
Deep learning
dictionary learning
Encoding
high-order tensor
stereo matching
Tensors
Title Deep High-order Tensor Convolutional Sparse Coding for Stereo Matching
URI https://ieeexplore.ieee.org/document/9546963
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3Pa8MgFJa27LDTNtqx33jYcbZJ1KjnbmU7rJS1G72VqC9QGE3p0v79e9rQMdhlJ4NoxBeJ3_f8no-Qe-mdc0YUzAU_mLDOMmu0YNIKn-CC9g50TDahxmM9n5tJizwcYmEAIIrPoB8e41m-r9w2uMoGRiKZy3mbtJXK97FajWQrTczgZfg2_JCZ0UF5kKX9pvWvtClx1xid_G-8U9L7Cb-jk8PGckZasOqS0SPAmgZZBovXZdIZEtBqQ7HPrlk-xSedrpGoAlaGnhQBKZ2i4aCir_jLDc6mHnkfPc2Gz6xJgsCWiP1rljqjMpuA0EaUCLaQcfBCKaexTFyZC5cakM4q5aUEDbYsvSwTyAMwQ3zDz0lnVa3gglCe8pIDF0Li64QvCoNcwZsM55jpUvFL0g02WKz391wsmulf_V19TY6DmaMYLr8hnXqzhVty5Hb18mtzFz_ON9MokWg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFH5BNNGTGjD-tgePFra13dozSiACIYKGG9nat8TEMILA3-_rXDAmXjx1ado1fWvW73v9Xh_AvXLWWiNTbr0fTGY245nRkqtMuoAWtLOoy2QTyWikZzMzrsHDLhYGEUvxGbb8Y3mW7wq78a6ytlFE5mKxB_s-c1YVrVWJtsLAtPudl86bioz22oMobFXtfyVOKfeN7vH_RjyB5k8AHhvvtpZTqOGiAd1HxCXzwgxeXpjJpkRBixWjPttqAaUfbLIkqopU6XsygqRsQqbDgg3pp-vdTU147T5NOz1epUHg74T-1zy0JomyAKU2Mie4RZxDpEliNZWBzWNpQ4PKZknilEKNWZ47lQcYe2hGCEecQX1RLPAcmAhFLlBIqeh10qWpIbbgTERzjHSeiAtoeBvMl983Xcyr6V_-XX0Hh73pcDAf9EfPV3DkTV5K4-JrqK9XG7yBA7tdv3-ubssP9QWZEJSx
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2021+3rd+International+Conference+on+Robotics+and+Computer+Vision+%28ICRCV%29&rft.atitle=Deep+High-order+Tensor+Convolutional+Sparse+Coding+for+Stereo+Matching&rft.au=Cui%2C+Wenjing&rft.au=Cheng%2C+Chunbo&rft.date=2021-08-06&rft.pub=IEEE&rft.spage=57&rft.epage=62&rft_id=info:doi/10.1109%2FICRCV52986.2021.9546963&rft.externalDocID=9546963