Data-Free Prior Model for Upper Body Pose Estimation and Tracking

Video based human body pose estimation seeks to estimate the human body pose from an image or a video sequence, which captures a person exhibiting some activities. To handle noise and occlusion, a pose prior model is often constructed and is subsequently combined with the pose estimated from the ima...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing Jg. 22; H. 12; S. 4627 - 4639
Hauptverfasser: Chen, Jixu, Nie, Siqi, Ji, Qiang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York, NY IEEE 01.12.2013
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:1057-7149, 1941-0042, 1941-0042
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Video based human body pose estimation seeks to estimate the human body pose from an image or a video sequence, which captures a person exhibiting some activities. To handle noise and occlusion, a pose prior model is often constructed and is subsequently combined with the pose estimated from the image data to achieve a more robust body pose tracking. Various body prior models have been proposed. Most of them are data-driven, typically learned from 3D motion capture data. In addition to being expensive and time-consuming to collect, these data-based prior models cannot generalize well to activities and subjects not present in the motion capture data. To alleviate this problem, we propose to learn the prior model from anatomic, biomechanics, and physical constraints, rather than from the motion capture data. For this, we propose methods that can effectively capture different types of constraints and systematically encode them into the prior model. Experiments on benchmark data sets show the proposed prior model, compared with data-based prior models, achieves comparable performance for body motions that are present in the training data. It, however, significantly outperforms the data-based prior models in generalization to different body motions and to different subjects.
AbstractList Video based human body pose estimation seeks to estimate the human body pose from an image or a video sequence, which captures a person exhibiting some activities. To handle noise and occlusion, a pose prior model is often constructed and is subsequently combined with the pose estimated from the image data to achieve a more robust body pose tracking. Various body prior models have been proposed. Most of them are data-driven, typically learned from 3D motion capture data. In addition to being expensive and time-consuming to collect, these data-based prior models cannot generalize well to activities and subjects not present in the motion capture data. To alleviate this problem, we propose to learn the prior model from anatomic, biomechanics, and physical constraints, rather than from the motion capture data. For this, we propose methods that can effectively capture different types of constraints and systematically encode them into the prior model. Experiments on benchmark data sets show the proposed prior model, compared with data-based prior models, achieves comparable performance for body motions that are present in the training data. It, however, significantly outperforms the data-based prior models in generalization to different body motions and to different subjects.
Video based human body pose estimation seeks to estimate the human body pose from an image or a video sequence, which captures a person exhibiting some activities. To handle noise and occlusion, a pose prior model is often constructed and is subsequently combined with the pose estimated from the image data to achieve a more robust body pose tracking. Various body prior models have been proposed. Most of them are data-driven, typically learned from 3D motion capture data. In addition to being expensive and time-consuming to collect, these data-based prior models cannot generalize well to activities and subjects not present in the motion capture data. To alleviate this problem, we propose to learn the prior model from anatomic, biomechanics, and physical constraints, rather than from the motion capture data. For this, we propose methods that can effectively capture different types of constraints and systematically encode them into the prior model. Experiments on benchmark data sets show the proposed prior model, compared with data-based prior models, achieves comparable performance for body motions that are present in the training data. It, however, significantly outperforms the data-based prior models in generalization to different body motions and to different subjects.Video based human body pose estimation seeks to estimate the human body pose from an image or a video sequence, which captures a person exhibiting some activities. To handle noise and occlusion, a pose prior model is often constructed and is subsequently combined with the pose estimated from the image data to achieve a more robust body pose tracking. Various body prior models have been proposed. Most of them are data-driven, typically learned from 3D motion capture data. In addition to being expensive and time-consuming to collect, these data-based prior models cannot generalize well to activities and subjects not present in the motion capture data. To alleviate this problem, we propose to learn the prior model from anatomic, biomechanics, and physical constraints, rather than from the motion capture data. For this, we propose methods that can effectively capture different types of constraints and systematically encode them into the prior model. Experiments on benchmark data sets show the proposed prior model, compared with data-based prior models, achieves comparable performance for body motions that are present in the training data. It, however, significantly outperforms the data-based prior models in generalization to different body motions and to different subjects.
Author Qiang Ji
Siqi Nie
Jixu Chen
Author_xml – sequence: 1
  givenname: Jixu
  surname: Chen
  fullname: Chen, Jixu
– sequence: 2
  givenname: Siqi
  surname: Nie
  fullname: Nie, Siqi
– sequence: 3
  givenname: Qiang
  surname: Ji
  fullname: Ji, Qiang
BackLink http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=28088229$$DView record in Pascal Francis
https://www.ncbi.nlm.nih.gov/pubmed/23893728$$D View this record in MEDLINE/PubMed
BookMark eNqN0c9rFDEUB_AgFftD74IgA1LoZdaXH5Mfx1pbLVTcw_YcMskbSZ2drMnsof-9aXer0IN4yjt8vg_yvsfkYEoTEvKWwoJSMB9X18sFA8oXjCmhhH5BjqgRtAUQ7KDO0KlWUWEOyXEpdwBUdFS-IoeMa8MV00fk_LObXXuVEZtljik331LAsRnqdLvZYG4-pXDfLFPB5rLMce3mmKbGTaFZZed_xunHa_JycGPBN_v3hNxeXa4uvrY3379cX5zftF4oObc9eoaDwQ6l4QyEcIb3AnQvOz3onhsYQugcVaE3gxCKBaOC57wH75Tnjp-Qs93eTU6_tlhmu47F4zi6CdO2WCqEVkrJjv8P5YIDSKj0wzN6l7Z5qh-pSnFOgT2q93u17dcY7CbXS-R7-3THCk73wBXvxiG7ycfy12nQmjFTndw5n1MpGQfr4_x40zm7OFoK9qFYW4u1D8XafbE1CM-CT7v_EXm3i0RE_MNlJ5WpX_oNDiOpuw
CODEN IIPRE4
CitedBy_id crossref_primary_10_1016_j_matpr_2020_12_1052
crossref_primary_10_1109_ACCESS_2019_2947201
crossref_primary_10_1109_TIP_2021_3059409
crossref_primary_10_1109_TIP_2015_2473662
crossref_primary_10_1109_TIP_2020_2984373
crossref_primary_10_1109_LRA_2022_3140450
crossref_primary_10_1002_tee_22902
crossref_primary_10_1016_j_patcog_2023_110116
crossref_primary_10_1109_TIP_2018_2834824
crossref_primary_10_1109_TNNLS_2023_3338619
crossref_primary_10_1016_j_patrec_2022_02_010
Cites_doi 10.1109/CVPR.2010.5540157
10.1145/378456.378507
10.1007/s11263-009-0273-6
10.1145/1390156.1390292
10.1109/CVPR.2008.4587360
10.1109/ICCV.2005.193
10.1007/s11263-009-0283-4
10.1109/ICCV.2011.6126500
10.5244/C.21.73
10.1109/CVPR.2008.4587580
10.1109/CVPR.2010.5540140
10.1109/CVPRW.2003.10101
10.1109/CVPR.2008.4587546
10.1023/B:VISI.0000042934.15159.49
10.1109/AFGR.1998.670920
10.1109/TPAMI.2006.21
10.1109/ICCVW.2009.5457532
10.1109/ICCV.2003.1238424
10.1007/978-3-540-75703-0_11
10.1109/CVPR.2005.335
10.1109/CVPR.2003.1211504
10.1109/CVPR.2004.1315063
10.1177/0278364907087172
10.1109/CVPR.2005.229
10.1109/CVPR.2009.5206672
10.1109/ICCV.2007.4409044
10.1214/aos/1176344136
ContentType Journal Article
Copyright 2015 INIST-CNRS
Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Dec 2013
Copyright_xml – notice: 2015 INIST-CNRS
– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Dec 2013
DBID 97E
RIA
RIE
AAYXX
CITATION
IQODW
CGR
CUY
CVF
ECM
EIF
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
F28
FR3
DOI 10.1109/TIP.2013.2274748
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
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
MEDLINE - Academic
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
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
MEDLINE - Academic
Engineering Research Database
ANTE: Abstracts in New Technology & Engineering
DatabaseTitleList MEDLINE
Technology Research Database
Technology Research Database
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 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 Applied Sciences
Engineering
EISSN 1941-0042
EndPage 4639
ExternalDocumentID 3170223721
23893728
28088229
10_1109_TIP_2013_2274748
6567960
Genre orig-research
Journal Article
GroupedDBID ---
-~X
.DC
0R~
29I
4.4
53G
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
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
HZ~
H~9
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
VH1
AAYXX
CITATION
AAYOK
IQODW
RIG
CGR
CUY
CVF
ECM
EIF
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
F28
FR3
ID FETCH-LOGICAL-c476t-bec2ef9e5e6932044a93b408b658f8b390fdd5a17db9f4472d97dc33b0ca7c3a3
IEDL.DBID RIE
ISICitedReferencesCount 19
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000325223300005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1057-7149
1941-0042
IngestDate Mon Sep 29 05:36:05 EDT 2025
Sun Sep 28 06:21:16 EDT 2025
Mon Jun 30 10:20:12 EDT 2025
Tue Dec 02 02:15:33 EST 2025
Wed Apr 02 07:18:32 EDT 2025
Sat Nov 29 03:20:52 EST 2025
Tue Nov 18 21:39:51 EST 2025
Tue Aug 26 16:46:50 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 12
Keywords Performance evaluation
Target tracking
knowledge-based model
body pose model
Video signal
Knowledge base
Video recording
Learning
Biomechanics
Human body model
Body pose estimation
Image sequence
Position measurement
Signal processing
Motion detection
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
CC BY 4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c476t-bec2ef9e5e6932044a93b408b658f8b390fdd5a17db9f4472d97dc33b0ca7c3a3
Notes ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
PMID 23893728
PQID 1473310260
PQPubID 85429
PageCount 13
ParticipantIDs proquest_miscellaneous_1443430060
crossref_citationtrail_10_1109_TIP_2013_2274748
pubmed_primary_23893728
ieee_primary_6567960
pascalfrancis_primary_28088229
proquest_journals_1473310260
proquest_miscellaneous_1448777653
crossref_primary_10_1109_TIP_2013_2274748
PublicationCentury 2000
PublicationDate 2013-12-01
PublicationDateYYYYMMDD 2013-12-01
PublicationDate_xml – month: 12
  year: 2013
  text: 2013-12-01
  day: 01
PublicationDecade 2010
PublicationPlace New York, NY
PublicationPlace_xml – name: New York, NY
– name: United States
– name: New York
PublicationTitle IEEE transactions on image processing
PublicationTitleAbbrev TIP
PublicationTitleAlternate IEEE Trans Image Process
PublicationYear 2013
Publisher IEEE
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: Institute of Electrical and Electronics Engineers
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref37
ref14
ref31
ref30
ref11
ref10
(ref34) 2010
ref2
ref1
ref17
ref38
ref16
ref18
brubaker (ref23) 2009
sidenbladh (ref9) 2000
sigal (ref33) 2010; 87
steindler (ref35) 1955
sminchisescu (ref21) 2001; 1
taylor (ref44) 2007
(ref43) 2010
ref46
ref24
gao (ref36) 2003
chen (ref15) 2009
ref25
ref22
murphy (ref42) 2002
ref28
xu (ref45) 2007
ref27
wang (ref20) 2008
urtasun (ref13) 2006
ref29
ref8
wu (ref26) 2003; 2
ref7
tian (ref12) 2005
bandouch (ref32) 2008
ref4
ref3
koller (ref39) 2009
ref6
ref5
lan (ref19) 2005; 1
ref40
pearl (ref41) 1988
References_xml – start-page: 248
  year: 2008
  ident: ref32
  article-title: Accurate human motion capture using an ergonomics-based anthropometric human model
  publication-title: Proc 5th Int Conf AMDO
– ident: ref1
  doi: 10.1109/CVPR.2010.5540157
– start-page: 710
  year: 2008
  ident: ref20
  article-title: Multiple tree models for occlusion and spatial constraints in human pose estimation
  publication-title: Proc 10th ECCV
– ident: ref38
  doi: 10.1145/378456.378507
– volume: 1
  start-page: -447i
  year: 2001
  ident: ref21
  article-title: Covariance scaled sampling for monocular 3D body tracking
  publication-title: Proc CVPR
– start-page: 702
  year: 2000
  ident: ref9
  article-title: Stochastic tracking of 3D human figures using 2D image motion
  publication-title: Proc ECCV
– volume: 87
  start-page: 4
  year: 2010
  ident: ref33
  article-title: HumanEva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion
  publication-title: Int J Comput Vis
  doi: 10.1007/s11263-009-0273-6
– start-page: 50
  year: 2005
  ident: ref12
  article-title: Articulated pose estimation in a learned smooth space of feasible solutions
  publication-title: Proc IEEE Comput Soc Conf CVPR Learn Workshop
– start-page: 238
  year: 2006
  ident: ref13
  article-title: 3D people tracking with Gaussian process dynamical models
  publication-title: Proc IEEE Comput Soc Conf CVPR
– ident: ref14
  doi: 10.1145/1390156.1390292
– start-page: 1345
  year: 2007
  ident: ref44
  article-title: Modeling human motion using binary latent variables
  publication-title: Proc NIPS
– ident: ref3
  doi: 10.1109/CVPR.2008.4587360
– ident: ref11
  doi: 10.1109/ICCV.2005.193
– ident: ref2
  doi: 10.1007/s11263-009-0283-4
– year: 1988
  ident: ref41
  publication-title: Probabilistic Reasoning in Intelligent Systems
– year: 2010
  ident: ref34
  publication-title: Nasa-Std-3000 Man-Systems Integration Standards
– year: 2002
  ident: ref42
  publication-title: Dynamic Bayesian Networks Representation Inference and Learning
– start-page: 2655
  year: 2009
  ident: ref15
  article-title: Switching Gaussian process dynamic models for simultaneous composite motion tracking and recognition
  publication-title: Proc IEEE Conf CVPR
– year: 2010
  ident: ref43
  publication-title: The Carnegie Mellon University Motion Capture Database
– year: 2009
  ident: ref39
  publication-title: Probabilistic Graphical Models Principles and Techniques
– ident: ref4
  doi: 10.1109/ICCV.2011.6126500
– ident: ref27
  doi: 10.5244/C.21.73
– ident: ref22
  doi: 10.1109/CVPR.2008.4587580
– ident: ref24
  doi: 10.1109/CVPR.2010.5540140
– ident: ref28
  doi: 10.1109/CVPRW.2003.10101
– ident: ref29
  doi: 10.1109/CVPR.2008.4587546
– year: 1955
  ident: ref35
  publication-title: Kinesiology of the Human Body Under Normal and Pathological Conditions
– ident: ref17
  doi: 10.1023/B:VISI.0000042934.15159.49
– ident: ref30
  doi: 10.1109/AFGR.1998.670920
– ident: ref5
  doi: 10.1109/TPAMI.2006.21
– ident: ref31
  doi: 10.1109/ICCVW.2009.5457532
– start-page: 149
  year: 2003
  ident: ref36
  article-title: Virtual face image generation for illumination and pose insensitive face recognition
  publication-title: Proc ICME
– ident: ref7
  doi: 10.1109/ICCV.2003.1238424
– start-page: 1
  year: 2009
  ident: ref23
  article-title: Physics-based human motion modelling for people tracking
  publication-title: Proc ICCV
– ident: ref6
  doi: 10.1007/978-3-540-75703-0_11
– ident: ref16
  doi: 10.1109/CVPR.2005.335
– ident: ref25
  doi: 10.1109/CVPR.2003.1211504
– volume: 2
  start-page: 1094
  year: 2003
  ident: ref26
  article-title: Tracking articulated body by dynamic Markov network
  publication-title: Proc 9th IEEE CVPR
– ident: ref18
  doi: 10.1109/CVPR.2004.1315063
– year: 2007
  ident: ref45
  article-title: Learning motion correlation for tracking articulated human body with a rao-blackwellised particle filter
  publication-title: Proc ICCV
– ident: ref37
  doi: 10.1177/0278364907087172
– volume: 1
  start-page: 470
  year: 2005
  ident: ref19
  article-title: Beyond trees: Common factor models for 2D human pose recovery
  publication-title: Proc 10th IEEE ICCV
– ident: ref8
  doi: 10.1109/CVPR.2005.229
– ident: ref10
  doi: 10.1109/CVPR.2009.5206672
– ident: ref46
  doi: 10.1109/ICCV.2007.4409044
– ident: ref40
  doi: 10.1214/aos/1176344136
SSID ssj0014516
Score 2.2328205
Snippet Video based human body pose estimation seeks to estimate the human body pose from an image or a video sequence, which captures a person exhibiting some...
SourceID proquest
pubmed
pascalfrancis
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 4627
SubjectTerms Applied sciences
Benchmarking
Biological system modeling
Biomechanical Phenomena - physiology
Body pose estimation
body pose model
Data models
Databases, Factual
Detection, estimation, filtering, equalization, prediction
Exact sciences and technology
Human body
Humans
Image processing
Image Processing, Computer-Assisted - methods
Information, signal and communications theory
Knowledge management
knowledge-based model
Models, Biological
Motion perception
Motion pictures
Pose estimation
Posture - physiology
Signal and communications theory
Signal processing
Signal, noise
Small mammals
Telecommunications and information theory
Three dimensional
Tracking
Training data
Transaction processing
Title Data-Free Prior Model for Upper Body Pose Estimation and Tracking
URI https://ieeexplore.ieee.org/document/6567960
https://www.ncbi.nlm.nih.gov/pubmed/23893728
https://www.proquest.com/docview/1473310260
https://www.proquest.com/docview/1443430060
https://www.proquest.com/docview/1448777653
Volume 22
WOSCitedRecordID wos000325223300005&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: 1941-0042
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014516
  issn: 1057-7149
  databaseCode: RIE
  dateStart: 19920101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fa9RAEB7a4oM-WG39Ea3HCr4IppdmN9ndx6o9FKTcQyv3Fja7EyiU5EjuBP97Z5JcrKAF3wK7IZuZnZ1vdnbnA3ingsbEOxVnhMZjlQcTl2eZjgl7BHQWpe_LNX3_pi8vzWpll3vwYboLg4j94TM85cc-lx8av-WtsjlhD02Iex_2tdbDXa0pY8CEs31mkz6kCfbvUpKJnV99XfIZLnmacgimmKIv7f00U7Df8UY9vQofjnQdyacaiC3-jTx7D7Q4_L-xP4HHI9IU58PUeAp7WB_B4Yg6xWjT3RE8ulOS8BjOP7uNixctoli2N00rmCztVhC0FdfrNbbiYxN-imXTobig1WG4-ChcHQR5Pc_77s_genFx9elLPNIsxF7pfBOTFlOsLGaYE5hLlHJWlioxJYGTypTSJlUImTvTobSVUjoNVgcvZUk61l46-RwO6qbGlyBouSDElFdJGowKmTGoUvQYnCsrrW0VwXwn7sKPNciZCuO26GORxBakq4J1VYy6iuD99MZ6qL9xT99jlvvUbxR5BLM_NDq1p4bji9RGcLJTcTFacEchEbNZcsW1CN5OzWR7nFBxNTZb7sP3crmkzb19uORinskIXgzT5_cAxln46u8Dfw0P-feGwzMncLBpt_gGHvgfm5uunZERrMysN4Jfhzf-wA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Ra9RAEB5qFdQHq23V2FpX8EUwvVyyyWYfq_Zo8Tzu4Sp9C5vdCRRKciR3gv_emSSXVmgLvgV2QzY7Ozvf7OzMB_BJOoWBNdKPCY37MnGpn49j5RP2cGg0RrYt1_Rrqmaz9PJSz7fgy5ALg4jt5TM85sc2lu8qu-ajshFhD0WI-xE8jqUMx1221hAzYMrZNrZJn1IE_DdByUCPFudzvsUVHYfshEkm6QtbS80k7LfsUUuwwtcjTUMzVHTUFvdjz9YGTXb-b_Qv4UWPNcVJtzhewRaWu7DT407Ra3WzC89vFSXcg5PvZmX8SY0o5vVVVQumS7sWBG7FxXKJtfhauT9iXjUoTml_6FIfhSmdILtn-eR9Hy4mp4tvZ35PtOBbqZKVT3IMsdAYY0JwLpDS6CiXQZoTPCnSPNJB4VxsxsrlupBShU4rZ6MoJykrG5noNWyXVYlvQdCGQZgpKYLQpdLFaYoyRIvOmLxQShcejDbTndm-CjmTYVxnrTcS6IxklbGssl5WHnwe3lh2FTge6LvH8z7066fcg6N_JDq0hyl7GKH24HAj4qzX4YacIuaz5JprHnwcmkn7OKRiSqzW3Iczc7mozYN9uOhiEkcevOmWz80A-lX47u6Bf4CnZ4uf02x6PvtxAM_4V7urNIewvarX-B6e2N-rq6Y-alXhL-mmAS4
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=Data-free+prior+model+for+upper+body+pose+estimation+and+tracking&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Chen%2C+Jixu&rft.au=Nie%2C+Siqi&rft.au=Ji%2C+Qiang&rft.date=2013-12-01&rft.eissn=1941-0042&rft.volume=22&rft.issue=12&rft.spage=4627&rft_id=info:doi/10.1109%2FTIP.2013.2274748&rft_id=info%3Apmid%2F23893728&rft.externalDocID=23893728
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1057-7149&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1057-7149&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1057-7149&client=summon