Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation

Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing all object boundaries in a training set. Second, we decompose the contour matrix into eigencontours via the best rank-M approximation. Third, w...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 2657 - 2665
Hlavní autoři: Park, Wonhui, Jin, Dongkwon, Kim, Chang-Su
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.01.2022
Témata:
Approximation algorithms
categorization
Computer vision
grouping and shape analysis; Low-level vision; Recognition: detection
Matrix decomposition
Pattern recognition
retrieval
Segmentation
Training
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing all object boundaries in a training set. Second, we decompose the contour matrix into eigencontours via the best rank-M approximation. Third, we represent an object boundary by a linear combination of the M eigencontours. We also incorporate the eigencontours into an instance segmentation framework. Experimental results demonstrate that the proposed eigencontours can represent object boundaries more effectively and more efficiently than existing descriptors in a low-dimensional space. Furthermore, the proposed algorithm yields meaningful performances on instance segmentation datasets.
AbstractList Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing all object boundaries in a training set. Second, we decompose the contour matrix into eigencontours via the best rank-M approximation. Third, we represent an object boundary by a linear combination of the M eigencontours. We also incorporate the eigencontours into an instance segmentation framework. Experimental results demonstrate that the proposed eigencontours can represent object boundaries more effectively and more efficiently than existing descriptors in a low-dimensional space. Furthermore, the proposed algorithm yields meaningful performances on instance segmentation datasets.
Author Kim, Chang-Su
Park, Wonhui
Jin, Dongkwon
Author_xml – sequence: 1
  givenname: Wonhui
  surname: Park
  fullname: Park, Wonhui
  email: whpark@mcl.korea.ac.kr
  organization: Korea University
– sequence: 2
  givenname: Dongkwon
  surname: Jin
  fullname: Jin, Dongkwon
  email: dongkwonjin@mcl.korea.ac.kr
  organization: Korea University
– sequence: 3
  givenname: Chang-Su
  surname: Kim
  fullname: Kim, Chang-Su
  email: changsukim@korea.ac.kr
  organization: Korea University
BookMark eNotjl1LwzAYhaMouM39Ar3IH2h9kzRp4t2s0wlFZai3I13fSHUmJalf_97CvDo8cHjOmZIjHzwScs4gZwzMRfXyuJZcaZ1z4DwH4MockClTShbKFEockgkDJTJlmDkh85TeAEBwxpTRE7Jadq_ot8EP4TOmS3ofvnBHqz3Ta0zb2PVDiIle2YQtDZ7W4TtbW_9OF30fw0_3YYcu-FNy7Owu4fw_Z-T5ZvlUrbL64fauWtRZNx4bMtsqKA1YDZYp7oQzBQhVGt0U3GFTaORCuxGdBpCNNG0rUFoJWvCx0ogZOdt7O0Tc9HGcj78bo0s9asQfPctOiA
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR52688.2022.00269
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 1665469463
9781665469463
EISSN 1063-6919
EndPage 2665
ExternalDocumentID 9878367
Genre orig-research
GrantInformation_xml – fundername: National Research Foundation of Korea
  grantid: 2021R1A4A1031864,2022R1A2B5B03002310
  funderid: 10.13039/501100003725
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i269t-ad60790a80a162f3f94036798b42feb48e238f98bf8005b59dd3e5a50832b42b3
IEDL.DBID RIE
ISICitedReferencesCount 14
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000867754202090&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:15:11 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i269t-ad60790a80a162f3f94036798b42feb48e238f98bf8005b59dd3e5a50832b42b3
PageCount 9
ParticipantIDs ieee_primary_9878367
PublicationCentury 2000
PublicationDate 2022-01-01
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: 2022-01-01
  day: 01
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.322365
Snippet Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing...
SourceID ieee
SourceType Publisher
StartPage 2657
SubjectTerms Approximation algorithms
categorization
Computer vision
grouping and shape analysis; Low-level vision; Recognition: detection
Matrix decomposition
Pattern recognition
retrieval
Segmentation
Training
Title Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation
URI https://ieeexplore.ieee.org/document/9878367
WOSCitedRecordID wos000867754202090&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED2VioGpQIv4lgdGTJ3ESWw2qFp1QFVVAepWxfVZqkAJStrCz8d2onZhYbMtK1HOcp7vfO8dwB0uI7usWUS1YUhdLQcqEyWpkIoZwwIdo_HFJtLJRMznctqC-x0XBhF98hk-uKa_y9fFcuNCZX3rH4soSQ_gIE2Tmqu1i6dE1pNJpGjYcQGT_cH7dObETFwCV-hkOUOf1byvoeIhZNT538uPobfn4pHpDmVOoIX5KXSawyNptmbVhfHQ62o6OYJNWT2SSbHFTzKo-8S6l_73UJQVebbApUmRk5fim86y_IM8OWHxn1XNYuzB22j4OhjTpkwCXdkvWtNMJyyVLBMsC5LQREZyC0upFIqHBhUXaGHZ2K6xh8NYxVLrCOPM6cCHdoqKzqCdFzmeAwmkViKLNZcWurmy3rET3BMxCm6fo_kFdJ1hFl-1Esaiscnl38NXcOQsXwcsrqG9Ljd4A4fL7XpVlbd--X4BHSmbMQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFH5BNNETKhh_24NHK2M_W29KIBhxIQQNN7LS14RoNrMB-ufbdgtcvHhbl2XL-rJ9fa_v-z6AW5x7OqyJR6VykBovB8pDwSnjwlHK6cgAlTWbiOKYTad8VIO7DRcGEW3zGd6bQ7uXL7P5ypTK2jo_Zl4Y7cCucc6q2Fqbioqnc5mQs4of13F4u_s-Ghs5E9PC5RphTtf2NW9dVCyI9Bv_e_whtLZsPDLa4MwR1DA9hka1fCTVx1k0YdCzyppGkGCVFw8kztb4SbrlmOgE0_4gsrwgTxq6JMlSMsy-6ThJP8ijkRb_WZQ8xha89XuT7oBWRgl0od9oSRMZOhF3EuYkndBVnuK-BqaIM-G7CoXPUAOz0kOll4eBCLiUHgaJUYJ39SXCO4F6mqV4CqTDpWBJIH2uwdsXOj82knssQObr-0j_DJpmYmZfpRbGrJqT879P38D-YPI6nA2f45cLODBRKMsXl1Bf5iu8gr35erko8msbyl9lE556
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%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Eigencontours%3A+Novel+Contour+Descriptors+Based+on+Low-Rank+Approximation&rft.au=Park%2C+Wonhui&rft.au=Jin%2C+Dongkwon&rft.au=Kim%2C+Chang-Su&rft.date=2022-01-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=2657&rft.epage=2665&rft_id=info:doi/10.1109%2FCVPR52688.2022.00269&rft.externalDocID=9878367