Learning Local Objective Functions for Robust Face Model Fitting

Model-based techniques have proven to be successful in interpreting the large amount of information contained in images. Associated fitting algorithms search for the global optimum of an objective function, which should correspond to the best model fit in a given image. Although fitting algorithms h...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence Vol. 30; no. 8; pp. 1357 - 1370
Main Authors: Wimmer, M., Stulp, F., Pietzsch, S., Radig, B.
Format: Journal Article
Language:English
Published: Los Alamitos, CA IEEE 01.08.2008
IEEE Computer Society
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
ISSN:0162-8828, 1939-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Model-based techniques have proven to be successful in interpreting the large amount of information contained in images. Associated fitting algorithms search for the global optimum of an objective function, which should correspond to the best model fit in a given image. Although fitting algorithms have been the subject of intensive research and evaluation, the objective function is usually designed ad hoc, based on implicit and domain-dependent knowledge. In this article, we address the root of the problem by learning more robust objective functions. First, we formulate a set of desirable properties for objective functions and give a concrete example function that has these properties. Then, we propose a novel approach that learns an objective function from training data generated by manual image annotations and this ideal objective function. In this approach, critical decisions such as feature selection are automated, and the remaining manual steps hardly require domain-dependent knowledge. Furthermore, an extensive empirical evaluation demonstrates that the obtained objective functions yield more robustness. Learned objective functions enable fitting algorithms to determine the best model fit more accurately than with designed objective functions.
AbstractList Model-based techniques have proven to be successful in interpreting the large amount of information contained in images. Associated fitting algorithms search for the global optimum of an objective function, which should correspond to the best model fit in a given image. Although fitting algorithms have been the subject of intensive research and evaluation, the objective function is usually designed ad hoc, based on implicit and domain-dependent knowledge. In this article, we address the root of the problem by learning more robust objective functions. First, we formulate a set of desirable properties for objective functions and give a concrete example function that has these properties. Then, we propose a novel approach that learns an objective function from training data generated by manual image annotations and this ideal objective function. In this approach, critical decisions such as feature selection are automated, and the remaining manual steps hardly require domain-dependent knowledge. Furthermore, an extensive empirical evaluation demonstrates that the obtained objective functions yield more robustness. Learned objective functions enable fitting algorithms to determine the best model fit more accurately than with designed objective functions.
Model-based techniques have proven to be successful in interpreting the large amount of information contained in images. Associated fitting algorithms search for the global optimum of an objective function, which should correspond [abstract truncated by publisher].
Model-based techniques have proven to be successful in interpreting the large amount of information contained in images. Associated fitting algorithms search for the global optimum of an objective function, which should correspond to the best model fit in a given image. Although fitting algorithms have been the subject of intensive research and evaluation, the objective function is usually designed ad hoc, based on implicit and domain-dependent knowledge. In this article, we address the root of the problem by learning more robust objective functions. First, we formulate a set of desirable properties for objective functions and give a concrete example function that has these properties. Then, we propose a novel approach that learns an objective function from training data generated by manual image annotations and this ideal objective function. In this approach, critical decisions such as feature selection are automated, and the remaining manual steps hardly require domain-dependent knowledge. Furthermore, an extensive empirical evaluation demonstrates that the obtained objective functions yield more robustness. Learned objective functions enable fitting algorithms to determine the best model fit more accurately than with designed objective functions.Model-based techniques have proven to be successful in interpreting the large amount of information contained in images. Associated fitting algorithms search for the global optimum of an objective function, which should correspond to the best model fit in a given image. Although fitting algorithms have been the subject of intensive research and evaluation, the objective function is usually designed ad hoc, based on implicit and domain-dependent knowledge. In this article, we address the root of the problem by learning more robust objective functions. First, we formulate a set of desirable properties for objective functions and give a concrete example function that has these properties. Then, we propose a novel approach that learns an objective function from training data generated by manual image annotations and this ideal objective function. In this approach, critical decisions such as feature selection are automated, and the remaining manual steps hardly require domain-dependent knowledge. Furthermore, an extensive empirical evaluation demonstrates that the obtained objective functions yield more robustness. Learned objective functions enable fitting algorithms to determine the best model fit more accurately than with designed objective functions.
[...] we formulate a set of desirable properties for objective functions and give a concrete example function that has these properties.
Author Radig, B.
Pietzsch, S.
Wimmer, M.
Stulp, F.
Author_xml – sequence: 1
  givenname: M.
  surname: Wimmer
  fullname: Wimmer, M.
  organization: Inf. 9-Bildverstehen und Wissensbasierte Syst., Tech. Univ. Munchen, Garching
– sequence: 2
  givenname: F.
  surname: Stulp
  fullname: Stulp, F.
– sequence: 3
  givenname: S.
  surname: Pietzsch
  fullname: Pietzsch, S.
– sequence: 4
  givenname: B.
  surname: Radig
  fullname: Radig, B.
BackLink http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=20492193$$DView record in Pascal Francis
https://www.ncbi.nlm.nih.gov/pubmed/18566491$$D View this record in MEDLINE/PubMed
BookMark eNqF0sFrFDEUBvAgFbttvQuCDIL1NOtLXiaT3FqKWwtbWqSeh2zyRmaZndRkRvC_N9tdK_TQnpLD73uBfO-IHQxhIMbecZhzDubL3e359dVcANTzGmqDr9iMGzQlVmgO2Ay4EqXWQh-yo5TWAFxWgG_YIdeVUtLwGTtbko1DN_wslsHZvrhZrcmN3W8qFtOQL2FIRRti8T2spjQWC-uouA6e-mLRjWPOnbDXre0Tvd2fx-zH4uvdxbdyeXN5dXG-LJ1UZixV67UEh-gByEuPpLRXptZOm1p67mvSVtsV-BbAayThndGAAqXmXlg8Zp93c-9j-DVRGptNlxz1vR0oTKkxgIrXRqoXpa4ryBpMlqfPSmUEZihfhCilRMlFhh-fwHWY4pA_ptFK5Fq4qTP6sEfTakO-uY_dxsY_zb9WMvi0BzblUtpoB9elRydAGpF7zg52zsWQUqT2_yhotgvSPCxIs12Q5mFBckQ9ibhutNuex2i7_rng-12wI6LHdyRWBrXCv3xGw-8
CODEN ITPIDJ
CitedBy_id crossref_primary_10_1007_s10514_009_9152_9
crossref_primary_10_1016_j_imavis_2009_07_012
crossref_primary_10_1007_s00138_014_0627_0
crossref_primary_10_1109_TIP_2015_2424311
crossref_primary_10_1016_j_imavis_2013_04_006
crossref_primary_10_1016_j_patcog_2010_09_004
Cites_doi 10.1023/b:visi.0000029664.99615.94
10.1145/358669.358692
10.1023/A:1008078328650
10.1109/ICCV.1993.378212
10.1109/TPAMI.2002.1017623
10.1016/S1077-3142(03)00081-X
10.1109/TMI.2002.803121
10.1561/0600000001
10.1109/ICIP.2002.1038171
10.1109/ICPR.2006.151
10.5244/C.20.55
10.1007/BFb0054766
10.1109/ICPR.2006.207
10.1109/ICPR.2004.1334629
10.1007/BFb0015549
10.1109/TPAMI.2006.21
10.1109/CVPR.2005.288
10.1109/FGR.2006.50
10.5244/C.20.6
10.1007/3-540-45344-X_14
10.1007/BFb0054760
10.1109/TPAMI.2002.1017625
10.1109/34.895976
10.5244/C.6.28
10.1016/S0004-3702(97)00043-X
10.1109/34.722606
10.5244/C.20.95
10.1109/TPAMI.2003.1227983
10.1109/CVPR.2001.990517
10.1007/11744078_10
10.1109/TPAMI.2005.167
10.1109/CVPR.2007.383181
10.1109/AFGR.2000.840618
10.1117/1.1333056
ContentType Journal Article
Copyright 2008 INIST-CNRS
Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2008
Copyright_xml – notice: 2008 INIST-CNRS
– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2008
DBID 97E
RIA
RIE
AAYXX
CITATION
IQODW
CGR
CUY
CVF
ECM
EIF
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
F28
FR3
7X8
DOI 10.1109/TPAMI.2007.70793
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
Pascal-Francis
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
Engineering Research Database
ANTE: Abstracts in New Technology & Engineering
MEDLINE - Academic
DatabaseTitleList Technology Research Database
Technology Research Database
MEDLINE - Academic

Technology Research Database
MEDLINE
Technology Research Database
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 Electronic Library (IEL)
  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 Engineering
Computer Science
Applied Sciences
EISSN 1939-3539
EndPage 1370
ExternalDocumentID 2322977721
18566491
20492193
10_1109_TPAMI_2007_70793
4359386
Genre orig-research
Journal Article
GroupedDBID ---
-DZ
-~X
.DC
0R~
29I
4.4
53G
5GY
5VS
6IK
97E
9M8
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
ADRHT
AENEX
AETEA
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
FA8
HZ~
H~9
IBMZZ
ICLAB
IEDLZ
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNI
RNS
RXW
RZB
TAE
TN5
UHB
VH1
XJT
~02
AAYXX
CITATION
IQODW
RIG
CGR
CUY
CVF
ECM
EIF
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
F28
FR3
7X8
ID FETCH-LOGICAL-c469t-6fd840c33d00ed4d3e68d6978c8974d1d7e8a8ab0df00d83e2dc980323481d2a3
IEDL.DBID RIE
ISICitedReferencesCount 17
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000256679700004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0162-8828
IngestDate Sun Nov 09 10:40:45 EST 2025
Thu Oct 02 10:20:05 EDT 2025
Wed Oct 01 14:22:58 EDT 2025
Sun Sep 28 01:56:35 EDT 2025
Sun Jun 29 13:15:56 EDT 2025
Mon Jul 21 05:55:12 EDT 2025
Mon Jul 21 09:15:30 EDT 2025
Sat Nov 29 08:10:21 EST 2025
Tue Nov 18 22:30:36 EST 2025
Tue Aug 26 16:47:22 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 8
Keywords Model-based coding
Computer vision
Modeling and recovery of physical attributes
Shape
Image Processing and Computer Vision
Vision and Scene Understanding
Computational models of vision
Real-time systems
Object recognition
Texture
Pattern matching
Face and gesture recognition
Image interpretation
Objective analysis
Gesture recognition
Global optimum
Real time system
Annotation
Search algorithm
face and gesture recognition
Model matching
Scene analysis
real-time systems
vision and scene understanding
Facies
Objective function
Pattern analysis
Artificial intelligence
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
CC BY 4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c469t-6fd840c33d00ed4d3e68d6978c8974d1d7e8a8ab0df00d83e2dc980323481d2a3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
PMID 18566491
PQID 862353197
PQPubID 23500
PageCount 14
ParticipantIDs pubmed_primary_18566491
proquest_miscellaneous_903617946
proquest_miscellaneous_875090309
proquest_journals_862353197
pascalfrancis_primary_20492193
crossref_citationtrail_10_1109_TPAMI_2007_70793
proquest_miscellaneous_69230304
proquest_miscellaneous_34443412
ieee_primary_4359386
crossref_primary_10_1109_TPAMI_2007_70793
PublicationCentury 2000
PublicationDate 2008-08-01
PublicationDateYYYYMMDD 2008-08-01
PublicationDate_xml – month: 08
  year: 2008
  text: 2008-08-01
  day: 01
PublicationDecade 2000
PublicationPlace Los Alamitos, CA
PublicationPlace_xml – name: Los Alamitos, CA
– name: United States
– name: New York
PublicationTitle IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev TPAMI
PublicationTitleAlternate IEEE Trans Pattern Anal Mach Intell
PublicationYear 2008
Publisher IEEE
IEEE Computer Society
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: IEEE Computer Society
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
Grest (ref18)
ref12
Quinlan (ref40) 1993
ref15
ref14
Hanek (ref21) 2004
Messer (ref36) 1999
ref11
ref10
ref17
ref16
ref19
Cootes (ref6) 2004
ref50
ref46
ref48
ref47
ref44
ref8
Belker (ref2) 2004
ref7
ref9
ref4
ref3
Lucey (ref34); 3
Nordstrøm (ref37) 2004
ref5
Tipping (ref45) 2000
ref31
ref30
Stegmann (ref42) 2000
ref33
Hall (ref20)
ref32
ref1
ref39
ref38
Jones (ref25) 2003
Witten (ref49) 2005
Matas (ref35)
ref24
ref23
ref26
ref22
Stulp (ref43)
Romdhani (ref41) 2005
ref28
ref27
ref29
References_xml – ident: ref33
  doi: 10.1023/b:visi.0000029664.99615.94
– start-page: 49
  volume-title: Proc. Computer Vision Winter Workshop
  ident: ref35
  article-title: Randomized Ransac
– ident: ref14
  doi: 10.1145/358669.358692
– ident: ref23
  doi: 10.1023/A:1008078328650
– start-page: 72
  year: 1999
  ident: ref36
  article-title: XM2VTSDB: The Extended M2VTS Database
  publication-title: Audio- and Video-Based Biometric Person Authentication
– ident: ref9
  doi: 10.1109/ICCV.1993.378212
– volume-title: Data Mining: Practical Machine Learning Tools and Techniques
  year: 2005
  ident: ref49
– ident: ref38
  doi: 10.1109/TPAMI.2002.1017623
– volume-title: C4.5: Programs for Machine Learning
  year: 1993
  ident: ref40
– volume: 3
  start-page: 3182
  volume-title: Proc. Int’l Conf. Pattern Recognition
  ident: ref34
  article-title: Initialized Eigenlip Estimator for Fast Lip Tracking Using Linear Regression
– ident: ref5
  doi: 10.1016/S1077-3142(03)00081-X
– ident: ref15
  doi: 10.1109/TMI.2002.803121
– ident: ref30
  doi: 10.1561/0600000001
– ident: ref32
  doi: 10.1109/ICIP.2002.1038171
– volume-title: Proc. Int’l Joint Conf. Artificial Intelligence
  ident: ref43
  article-title: Optimized Execution of Action Chains Using Learned Performance Models of Abstract Actions
– ident: ref48
  doi: 10.1109/ICPR.2006.151
– ident: ref4
  doi: 10.5244/C.20.55
– ident: ref13
  doi: 10.1007/BFb0054766
– ident: ref29
  doi: 10.1109/ICPR.2006.207
– ident: ref16
  doi: 10.1109/ICPR.2004.1334629
– volume-title: technical report, Informatics and Math. Modelling, DTU
  year: 2004
  ident: ref37
  article-title: The IMM Face Database—An Annotated Dataset of 240 Face Images
– ident: ref22
  doi: 10.1007/BFb0015549
– ident: ref1
  doi: 10.1109/TPAMI.2006.21
– ident: ref31
  doi: 10.1109/CVPR.2005.288
– ident: ref10
  doi: 10.1109/FGR.2006.50
– volume-title: Proc. Vision, Modeling, and Visualization
  ident: ref18
  article-title: Human Model Fitting from Monocular Posture Images
– ident: ref17
  doi: 10.5244/C.20.6
– volume-title: PhD dissertation
  year: 2005
  ident: ref41
  article-title: Face Image Analysis Using a Multiple Feature Fitting Strategy
– volume-title: technical report, Univ. of Manchester
  year: 2004
  ident: ref6
  article-title: Statistical Models of Appearance for Computer Vision
– ident: ref24
  doi: 10.1007/3-540-45344-X_14
– ident: ref7
  doi: 10.1007/BFb0054760
– ident: ref26
  doi: 10.1109/TPAMI.2002.1017625
– start-page: 855
  volume-title: Proc. Int’l Conf. Neural Information Processing and Intelligent Information System
  ident: ref20
  article-title: Feature Subset Selection: A Correlation Based Filter Approach
– ident: ref39
  doi: 10.1109/34.895976
– ident: ref8
  doi: 10.5244/C.6.28
– ident: ref27
  doi: 10.1016/S0004-3702(97)00043-X
– ident: ref19
  doi: 10.1109/34.722606
– volume-title: Technical Report TR2003-96, Mitsubishi Electric Research Laboratories
  year: 2003
  ident: ref25
  article-title: Fast Multi-View Face Detection
– ident: ref11
  doi: 10.5244/C.20.95
– ident: ref3
  doi: 10.1109/TPAMI.2003.1227983
– ident: ref46
  doi: 10.1109/CVPR.2001.990517
– volume-title: PhD dissertation
  year: 2004
  ident: ref2
  article-title: Plan Projection, Execution, and Learning for Mobile Robot Control
– volume-title: Advances in Neural Information Processing Systems
  year: 2000
  ident: ref45
  article-title: The Relevance Vector Machine
– ident: ref44
  doi: 10.1007/11744078_10
– ident: ref47
  doi: 10.1109/TPAMI.2005.167
– ident: ref12
  doi: 10.1109/CVPR.2007.383181
– ident: ref28
  doi: 10.1109/AFGR.2000.840618
– volume-title: PhD dissertation
  year: 2004
  ident: ref21
  article-title: Fitting Parametric Curve Models to Images Using Local Self-Adapting Separation Criteria
– volume-title: technical report, Informatics and Math. Modelling, DTU
  year: 2000
  ident: ref42
  article-title: On Properties of Active Shape Models
– ident: ref50
  doi: 10.1117/1.1333056
SSID ssj0014503
Score 2.0869524
Snippet Model-based techniques have proven to be successful in interpreting the large amount of information contained in images. Associated fitting algorithms search...
[...] we formulate a set of desirable properties for objective functions and give a concrete example function that has these properties.
SourceID proquest
pubmed
pascalfrancis
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1357
SubjectTerms Acceleration
Algorithm design and analysis
Algorithms
Applied sciences
Artificial Intelligence
Computational models of vision
Computer science; control theory; systems
Computer Simulation
Computer vision
Concrete
Exact sciences and technology
Face - anatomy & histology
Face and gesture recognition
Face detection
Face recognition
Fittings
Humans
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image Processing and Computer Vision
Imaging, Three-Dimensional - methods
Layout
Learning
Mathematical models
Model-based coding
Modeling and recovery of physical attributes
Models, Anatomic
Object recognition
Optimization
Pattern analysis
Pattern matching
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
Real time systems
Reproducibility of Results
Robustness
Sensitivity and Specificity
Shape
Studies
Subtraction Technique
Texture
Training data
Vision and Scene Understanding
Title Learning Local Objective Functions for Robust Face Model Fitting
URI https://ieeexplore.ieee.org/document/4359386
https://www.ncbi.nlm.nih.gov/pubmed/18566491
https://www.proquest.com/docview/862353197
https://www.proquest.com/docview/34443412
https://www.proquest.com/docview/69230304
https://www.proquest.com/docview/875090309
https://www.proquest.com/docview/903617946
Volume 30
WOSCitedRecordID wos000256679700004&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
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1939-3539
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014503
  issn: 0162-8828
  databaseCode: RIE
  dateStart: 19790101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La9wwEB6SkEN6aJpHWzftRodcCnFXtlRZujWUmgbyoiRhb0YryWFL2C3xbn9_Z2Sv00C20JtBI7BHGs2MZ_R9AEfWOYdGJtGQtEul8Flqs9yn2iljdaZqG9kabs-Kiws9GpmrNTju78KEEGLzWfhEj7GW72duQb_KhujajdBqHdaLQrV3tfqKgfwcWZAxgkELxzRiWZLkZnh9dXJ-2qIVRjw4AgrVGMZIkz3xRpFehZojbYP6qVtii9WRZ_RA5fb_vfsreNlFmuyk3Ro7sBamu7C9ZHFgnVHvwou_IAn34EsHuHrHzsjLscvxz_ZIZCV6wLhJGca57MdsvGjmrLQuMOJTu2flJLZQ78NN-e366_e0Y1lIHabG81TVHpM8J4TnPHjpRVDaK0wuncZcw2e-CNpqO-a-5txrEXLvjOYipyu8PrfiNWxMZ9PwFhjB35lgVObI80fwMOE1N87LjOu6TmC41HblOghyYsK4r2Iqwk0Vl4qoMYsqLlUCH_sZv1r4jX_I7pHae7lO4wkMnixoP55jcoTnNc47WK5w1RlwU2GiJ-h4KhI47EfR8qicYqdhtmgqIaXEGCBfLaEweqbScwJshYSmgI2qXKtFcFjRqYkf8qbdfo-a6Hbxu-e__AC22u4Wald8Dxvzh0X4AJvu93zSPAzQiEZ6EI3oD1EWFJY
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dT9swED8xmLTtAQbsI3z6YS-TltWJjWu_gaZFIEpBUzfxFrm2g0ConUi7v393TpqBtE7aWySfpeTs893lzr8fwAfrnEMjk2hI2qVS-Cy1We5T7ZSxOlOVjWwNPwb94VBfX5urFfjU3YUJIcTms_CZHmMt30_dnH6V9dC1G6HVM1g7kjLnzW2trmYgjyIPMsYwaOOYSCyKktz0RlcnF2cNXmFEhCOoUI2BjDTZE38UCVaoPdLWqKGqobZYHntGH1Rs_N_bv4b1NtZkJ83m2ISVMNmCjQWPA2vNegtePQIl3IbjFnL1hg3Iz7HL8V1zKLICfWDcpgwjXfZtOp7XM1ZYFxgxqt2z4jY2Ub-B78XX0ZfTtOVZSB0mx7NUVR7TPCeE5zx46UVQ2itML53GbMNnvh-01XbMfcW51yLk3hnNRU6XeH1uxVtYnUwn4T0wAsAzwajMke-P8GHCa26clxnXVZVAb6Ht0rUg5MSFcV_GZISbMi4VkWP2y7hUCXzsZvxsADj-IbtNau_kWo0ncPBkQbvxHNMjPLFx3u5ihcvWhOsSUz1BB1Q_gcNuFG2PCip2EqbzuhRSSowC8uUSCuNnKj4nwJZIaArZqM61XASHFZ2b-CHvmu33RxPtLt75-5cfwovT0cWgHJwNz3fhZdPrQs2Le7A6e5iHfXjufs1u64eDaEq_AU2GFvU
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=article&rft.atitle=Learning+Local+Objective+Functions+for+Robust+Face+Model+Fitting&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Wimmer%2C+M&rft.au=Stulp%2C+F&rft.au=Pietzsch%2C+S&rft.au=Radig%2C+B&rft.date=2008-08-01&rft.issn=0162-8828&rft.volume=30&rft.issue=8&rft.spage=1357&rft.epage=1370&rft_id=info:doi/10.1109%2FTPAMI.2007.70793&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon