Enforcing convexity for improved alignment with constrained local models

Constrained local models (CLMs) have recently demonstrated good performance in non-rigid object alignment/ tracking in comparison to leading holistic approaches (e.g., AAMs). A major problem hindering the development of CLMs further, for non-rigid object alignment/tracking, is how to jointly optimiz...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2008 IEEE Conference on Computer Vision and Pattern Recognition Ročník 2008; s. 1 - 8
Hlavní autoři: Yang Wang, Lucey, Simon, Cohn, Jeffrey F.
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 23.06.2008
Témata:
Active appearance model
Active noise reduction
Constraint optimization
Image databases
Lighting
Noise shaping
Optimization methods
Response surface methodology
Robots
Shape
ISBN:9781424422425, 1424422426
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Constrained local models (CLMs) have recently demonstrated good performance in non-rigid object alignment/ tracking in comparison to leading holistic approaches (e.g., AAMs). A major problem hindering the development of CLMs further, for non-rigid object alignment/tracking, is how to jointly optimize the global warp update across all local search responses. Previous methods have either used general purpose optimizers (e.g., simplex methods) or graph based optimization techniques. Unfortunately, problems exist with both these approaches when applied to CLMs. In this paper, we propose a new approach for optimizing the global warp update in an efficient manner by enforcing convexity at each local patch response surface. Furthermore, we show that the classic Lucas-Kanade approach to gradient descent image alignment can be viewed as a special case of our proposed framework. Finally, we demonstrate that our approach receives improved performance for the task of non-rigid face alignment/tracking on the MultiPIE database and the UNBC-McMaster archive.
AbstractList Constrained local models (CLMs) have recently demonstrated good performance in non-rigid object alignment/tracking in comparison to leading holistic approaches (e.g., AAMs). A major problem hindering the development of CLMs further, for non-rigid object alignment/tracking, is how to jointly optimize the global warp update across all local search responses. Previous methods have either used general purpose optimizers (e.g., simplex methods) or graph based optimization techniques. Unfortunately, problems exist with both these approaches when applied to CLMs. In this paper, we propose a new approach for optimizing the global warp update in an efficient manner by enforcing convexity at each local patch response surface. Furthermore, we show that the classic Lucas-Kanade approach to gradient descent image alignment can be viewed as a special case of our proposed framework. Finally, we demonstrate that our approach receives improved performance for the task of non-rigid face alignment/tracking on the MultiPIE database and the UNBC-McMaster archive.
Constrained local models (CLMs) have recently demonstrated good performance in non-rigid object alignment/tracking in comparison to leading holistic approaches (e.g., AAMs). A major problem hindering the development of CLMs further, for non-rigid object alignment/tracking, is how to jointly optimize the global warp update across all local search responses. Previous methods have either used general purpose optimizers (e.g., simplex methods) or graph based optimization techniques. Unfortunately, problems exist with both these approaches when applied to CLMs. In this paper, we propose a new approach for optimizing the global warp update in an efficient manner by enforcing convexity at each local patch response surface. Furthermore, we show that the classic Lucas-Kanade approach to gradient descent image alignment can be viewed as a special case of our proposed framework. Finally, we demonstrate that our approach receives improved performance for the task of non-rigid face alignment/tracking on the MultiPIE database and the UNBC-McMaster archive.Constrained local models (CLMs) have recently demonstrated good performance in non-rigid object alignment/tracking in comparison to leading holistic approaches (e.g., AAMs). A major problem hindering the development of CLMs further, for non-rigid object alignment/tracking, is how to jointly optimize the global warp update across all local search responses. Previous methods have either used general purpose optimizers (e.g., simplex methods) or graph based optimization techniques. Unfortunately, problems exist with both these approaches when applied to CLMs. In this paper, we propose a new approach for optimizing the global warp update in an efficient manner by enforcing convexity at each local patch response surface. Furthermore, we show that the classic Lucas-Kanade approach to gradient descent image alignment can be viewed as a special case of our proposed framework. Finally, we demonstrate that our approach receives improved performance for the task of non-rigid face alignment/tracking on the MultiPIE database and the UNBC-McMaster archive.
Author Cohn, Jeffrey F.
Lucey, Simon
Yang Wang
Author_xml – sequence: 1
  surname: Yang Wang
  fullname: Yang Wang
  email: wangy@cs.cmu.edu
  organization: The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA
– sequence: 2
  givenname: Simon
  surname: Lucey
  fullname: Lucey, Simon
  email: slucey@cs.cmu.edu
  organization: The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA
– sequence: 3
  givenname: Jeffrey F.
  surname: Cohn
  fullname: Cohn, Jeffrey F.
  email: jeffcohn@cs.cmu.edu
  organization: The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/20622926$$D View this record in MEDLINE/PubMed
BookMark eNpVkV1LwzAUhqNO3Jz7ASJIL73pzFfT5EaQMZ0wUES9LWmabpE2mU033b83sjm2c3PgPC_v-ToHHeusBuASwSFCUNyOPl5ehxhCPqQJTznkR2AgUo4ophRjSvAx6CHISMwEEicHDCedPdYFA-8_YQiaEIbYGehiyDAWmPXAZGxL1yhjZ5FydqV_TLuOQiUy9aJxK11EsjIzW2vbRt-mnf-pfNtIYwOqnJJVVLtCV_4CnJay8nqwzX3w_jB-G03i6fPj0-h-GhuCRRuXqKSUSp4KBYsiJ4pIxQUrcl1KWBJc8kTkCcdIpKwUGPGwASFKapErQnNI-uBu47tY5rUuVBiskVW2aEwtm3XmpMkOiTXzbOZWGeZCpDgJBjdbg8Z9LbVvs9p4patKWu2WPkOcJESEAVGQXu_32jX5P18QXG0ERmu9w9t_kV-ISoU1
ContentType Conference Proceeding
Journal Article
DBID 6IE
6IH
CBEJK
RIE
RIO
NPM
7X8
5PM
DOI 10.1109/CVPR.2008.4587808
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP) 1998-present
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList
PubMed

MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
EISBN 9781424422432
1424422434
EISSN 1063-6919
EndPage 8
ExternalDocumentID PMC2899725
20622926
4587808
Genre orig-research
Journal Article
GrantInformation_xml – fundername: NIMH NIH HHS
  grantid: R01 MH051435
GroupedDBID 23M
29F
29O
6IE
6IH
6IK
ABDPE
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CBEJK
IPLJI
M43
RIE
RIO
RNS
NPM
7X8
5PM
ID FETCH-LOGICAL-i329t-f1f444a879c0ddb3c3ac896dbefa0f32f859b5821976f921869133cae9bc34b03
IEDL.DBID RIE
ISBN 9781424422425
1424422426
ISICitedReferencesCount 15
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000259736803044&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1063-6919
IngestDate Thu Aug 21 13:34:01 EDT 2025
Sun Nov 09 09:25:17 EST 2025
Mon Jul 21 05:17:46 EDT 2025
Wed Aug 27 02:30:36 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i329t-f1f444a879c0ddb3c3ac896dbefa0f32f859b5821976f921869133cae9bc34b03
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink http://doi.org/10.1109/CVPR.2008.4587808
PMID 20622926
PQID 1835398791
PQPubID 23479
PageCount 8
ParticipantIDs pubmed_primary_20622926
pubmedcentral_primary_oai_pubmedcentral_nih_gov_2899725
proquest_miscellaneous_1835398791
ieee_primary_4587808
PublicationCentury 2000
PublicationDate 20080623
PublicationDateYYYYMMDD 2008-06-23
PublicationDate_xml – month: 6
  year: 2008
  text: 20080623
  day: 23
PublicationDecade 2000
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle 2008 IEEE Conference on Computer Vision and Pattern Recognition
PublicationTitleAbbrev CVPR
PublicationTitleAlternate Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit
PublicationYear 2008
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000453616
ssj0023720
ssj0003211698
Score 2.3027775
Snippet Constrained local models (CLMs) have recently demonstrated good performance in non-rigid object alignment/ tracking in comparison to leading holistic...
Constrained local models (CLMs) have recently demonstrated good performance in non-rigid object alignment/tracking in comparison to leading holistic approaches...
SourceID pubmedcentral
proquest
pubmed
ieee
SourceType Open Access Repository
Aggregation Database
Index Database
Publisher
StartPage 1
SubjectTerms Active appearance model
Active noise reduction
Constraint optimization
Image databases
Lighting
Noise shaping
Optimization methods
Response surface methodology
Robots
Shape
Title Enforcing convexity for improved alignment with constrained local models
URI https://ieeexplore.ieee.org/document/4587808
https://www.ncbi.nlm.nih.gov/pubmed/20622926
https://www.proquest.com/docview/1835398791
https://pubmed.ncbi.nlm.nih.gov/PMC2899725
Volume 2008
WOSCitedRecordID wos000259736803044&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/eLvHCXMwlV1LT-QwDLYAceAEu7wGFtSVOFJomzSPMwJxQGi0WtDcRkmawFw6aDqD-PnY6QNYcdlb81LT2E0c258NcOYrqbjjLDXEwZwH_KWUVSkvLbJzmVnGIlD4Tt7fq8lEj9fgfMDCeO-j85m_oMdoy6_mbkWqskteKqkI2bsupWixWoM-BUUTJjpRh8oMbzZCDxaFgrKxRMunYKnQue5BXgWdUX3sp65cdubPPNOXV4_jP63LZfd2Ch-ciaLQFI8hZmT5Tjj918fy06F1s_1_n7sDex_ov2Q8nGs_YM3XP2G7E1eTbjNosKrPCNHX7cLtNaGbHA5Lojv7G8r4CdYks6i7wOEo9j9FB4SENMDUq4lZKrApHqtJTM3T7MHDzfXfq9u0y9WQzlihl2nIA-fcKKldVlWWOWac0qKyPpgssCKoUlsC5aL4E3RMhIW3Y2e8to5xm7F92KjntT-EpOLG4D4S8jJ47ozVKFQaa4QMmXNKmhHs0lpNX9pwHNNumUbwu6fCFH8RsnuY2s9XzRR3rZJpnFo-goOWKsPgnpQjkF_oNXSg8NtfW-rZcwzDTVdVWZRH30_nGLZa1xKRFuwXbCwXK38Cm-51OWsWp8jBE3UaOfgd_GvnuA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5VpRKcSh_AtpQGiWNDEz8S-1y1WsR2tUKl6i2yHRv2kkXNLuLnM-M8aKteuMUvxfE4ns_zBPjk61IJJ3hqaAcLEfCXUlalQlrczjKznEdH4Vk5n6u7O73YgrPRF8Z7H43P_Gd6jLr8euU2JCo7F1KVijx7X0ghWNZ5a40SFQQnvOjBDpU53m0KPeoUGOVjibrPgqeFzvXg5sWISw3Rn_qy7BWgeabPL24X3zqjy_79FEA4KxjTFJEh5mR5Dp4-tbJ8wLaudv_vg1_D4T__v2QxcrY92PLNPuz2gDXpj4MWq4acEEPdAUwvyb_J4bAkGrT_QZSfYE2yjNILHI7A_0c0QUhIBky92pinApsiY01icp72EL5fXd5cTNM-W0O65Eyv05AHIYRRpXZZXVvuuHFKF7X1wWSBs6CktuSWiwAo6JgKC-_HznhtHRc2429gu1k1_h0ktTAGT5KQy-CFM1YjrDTWFGXInFOlmcABrVX1qwvIUfXLNIGPAxUq_ElI82Eav9q0FZ5bkmucWj6Btx1VxsEDKSdQPqLX2IECcD9uaZY_YyBuuqyWTB49P51TeDm9uZ5Vsy_zr8fwqjM0KVLG38P2-n7jT2DH_V4v2_sPcR__BbtP6hc
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=2008+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=Enforcing+convexity+for+improved+alignment+with+constrained+local+models&rft.au=Yang+Wang&rft.au=Lucey%2C+Simon&rft.au=Cohn%2C+Jeffrey+F.&rft.date=2008-06-23&rft.pub=IEEE&rft.isbn=9781424422425&rft.issn=1063-6919&rft.eissn=1063-6919&rft.spage=1&rft.epage=8&rft_id=info:doi/10.1109%2FCVPR.2008.4587808&rft_id=info%3Apmid%2F20622926&rft.externalDocID=4587808
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6919&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6919&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6919&client=summon