MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation

In this work, we propose a novel and efficient method for articulated human pose estimation in videos using a convolutional network architecture, which incorporates both color and motion features. We propose a new human body pose dataset, FLIC-motion (This dataset can be downloaded from http://cs.ny...

Full description

Saved in:
Bibliographic Details
Published inComputer Vision -- ACCV 2014 Vol. 9004; pp. 302 - 315
Main Authors Jain, Arjun, Tompson, Jonathan, LeCun, Yann, Bregler, Christoph
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2015
Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
Online AccessGet full text
ISBN9783319168074
331916807X
ISSN0302-9743
1611-3349
DOI10.1007/978-3-319-16808-1_21

Cover

Loading…
Abstract In this work, we propose a novel and efficient method for articulated human pose estimation in videos using a convolutional network architecture, which incorporates both color and motion features. We propose a new human body pose dataset, FLIC-motion (This dataset can be downloaded from http://cs.nyu.edu/~ajain/accv2014/.), that extends the FLIC dataset [1] with additional motion features. We apply our architecture to this dataset and report significantly better performance than current state-of-the-art pose detection systems.
AbstractList In this work, we propose a novel and efficient method for articulated human pose estimation in videos using a convolutional network architecture, which incorporates both color and motion features. We propose a new human body pose dataset, FLIC-motion (This dataset can be downloaded from http://cs.nyu.edu/~ajain/accv2014/.), that extends the FLIC dataset [1] with additional motion features. We apply our architecture to this dataset and report significantly better performance than current state-of-the-art pose detection systems.
Author Tompson, Jonathan
Jain, Arjun
Bregler, Christoph
LeCun, Yann
Author_xml – sequence: 1
  givenname: Arjun
  surname: Jain
  fullname: Jain, Arjun
  email: ajain@cs.nyu.edu
– sequence: 2
  givenname: Jonathan
  surname: Tompson
  fullname: Tompson, Jonathan
– sequence: 3
  givenname: Yann
  surname: LeCun
  fullname: LeCun, Yann
– sequence: 4
  givenname: Christoph
  surname: Bregler
  fullname: Bregler, Christoph
BookMark eNqNkMtOQjEQQOszgvIHLvoD1em7dUdQ1ASjJrhuKgyKwu21vcTf917UuHU1mceZzJw-2a9ShYSccjjjAPbcW8ckk9wzbhw4xoPgO6Qv28q24HZJjxvOmZTK75FBO__bs2qf9ECCYN4qeUh6HqzXhoM8IoNS3gCAa-AKRI883qVLxPqCDmkX6QRjrpbVCx3nuMbPlN_pU-nyu9QsU0XHGJtNxkIXKdObzTpW9CEVpFelWa5jN3JCDhZxVXDwE4_JdHw1Hd2wyf317Wg4YbVwrmECQc0tYPvC3Fs593quUc0QQUbl0XtrBDrOLZjoZ9IbBR7QCeW0gMWzPCbie22pc3sf5vCc0nsJHELnL7Q-ggytkbDVFTp_LaS-oTqnjw2WJmBHzbBqclzNXmPdYC7BCG90SwrngxTwX0xrZzT8YV_AKIB1
ContentType Book Chapter
Copyright Springer International Publishing Switzerland 2015
Copyright_xml – notice: Springer International Publishing Switzerland 2015
DBID FFUUA
DEWEY 006.37
DOI 10.1007/978-3-319-16808-1_21
DatabaseName ProQuest Ebook Central - Book Chapters - Demo use only
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
EISBN 3319168088
9783319168081
EISSN 1611-3349
Editor Saito, Hideo
Yang, Ming-Hsuan
Cremers, Daniel
Reid, Ian
Editor_xml – sequence: 1
  fullname: Cremers, Daniel
– sequence: 2
  fullname: Reid, Ian
– sequence: 3
  fullname: Saito, Hideo
– sequence: 4
  fullname: Yang, Ming-Hsuan
EndPage 315
ExternalDocumentID EBC6296519_289_320
EBC5586509_289_320
GroupedDBID 0D6
0DA
38.
AABBV
AAGZE
AAZAK
AAZUS
ABBVZ
ABFTD
ABMNI
ACKNT
ACRRC
AEDXK
AEJLV
AEKFX
AETDV
AEZAY
ALMA_UNASSIGNED_HOLDINGS
APFYR
AZZ
BBABE
CZZ
FFUUA
I4C
IEZ
IY-
LDH
SBO
SFQCF
TMQGW
TPJZQ
TSXQS
TWXRB
Z5O
Z7R
Z7S
Z7U
Z7W
Z7X
Z7Y
Z7Z
Z81
Z82
Z83
Z84
Z85
Z87
Z88
-DT
-GH
-~X
1SB
29L
2HA
2HV
5QI
875
AASHB
ACGFS
ADCXD
AEFIE
EJD
F5P
FEDTE
HVGLF
LAS
P2P
RIG
RNI
RSU
SVGTG
VI1
~02
ID FETCH-LOGICAL-p288t-2e04d70e611d973d95d5e4cee03a49e99762e811706a9c3964090e8248520fb3
ISBN 9783319168074
331916807X
ISSN 0302-9743
IngestDate Tue Jul 29 20:28:09 EDT 2025
Fri Apr 04 22:36:58 EDT 2025
Thu May 29 16:00:04 EDT 2025
IsPeerReviewed true
IsScholarly true
LCCallNum TA1637-1638TA1634Q33
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-p288t-2e04d70e611d973d95d5e4cee03a49e99762e811706a9c3964090e8248520fb3
OCLC 907956103
PQID EBC5586509_289_320
PageCount 14
ParticipantIDs springer_books_10_1007_978_3_319_16808_1_21
proquest_ebookcentralchapters_6296519_289_320
proquest_ebookcentralchapters_5586509_289_320
PublicationCentury 2000
PublicationDate 2015
PublicationDateYYYYMMDD 2015-01-01
PublicationDate_xml – year: 2015
  text: 2015
PublicationDecade 2010
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
– name: Cham
PublicationSeriesSubtitle Image Processing, Computer Vision, Pattern Recognition, and Graphics
PublicationSeriesTitle Lecture Notes in Computer Science
PublicationSeriesTitleAlternate Lect.Notes Computer
PublicationSubtitle 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised Selected Papers, Part II
PublicationTitle Computer Vision -- ACCV 2014
PublicationYear 2015
Publisher Springer International Publishing AG
Springer International Publishing
Publisher_xml – name: Springer International Publishing AG
– name: Springer International Publishing
RelatedPersons Kleinberg, Jon M.
Mattern, Friedemann
Naor, Moni
Mitchell, John C.
Terzopoulos, Demetri
Steffen, Bernhard
Pandu Rangan, C.
Kanade, Takeo
Kittler, Josef
Weikum, Gerhard
Hutchison, David
Tygar, Doug
RelatedPersons_xml – sequence: 1
  givenname: David
  surname: Hutchison
  fullname: Hutchison, David
– sequence: 2
  givenname: Takeo
  surname: Kanade
  fullname: Kanade, Takeo
– sequence: 3
  givenname: Josef
  surname: Kittler
  fullname: Kittler, Josef
– sequence: 4
  givenname: Jon M.
  surname: Kleinberg
  fullname: Kleinberg, Jon M.
– sequence: 5
  givenname: Friedemann
  surname: Mattern
  fullname: Mattern, Friedemann
– sequence: 6
  givenname: John C.
  surname: Mitchell
  fullname: Mitchell, John C.
– sequence: 7
  givenname: Moni
  surname: Naor
  fullname: Naor, Moni
– sequence: 8
  givenname: C.
  surname: Pandu Rangan
  fullname: Pandu Rangan, C.
– sequence: 9
  givenname: Bernhard
  surname: Steffen
  fullname: Steffen, Bernhard
– sequence: 10
  givenname: Demetri
  surname: Terzopoulos
  fullname: Terzopoulos, Demetri
– sequence: 11
  givenname: Doug
  surname: Tygar
  fullname: Tygar, Doug
– sequence: 12
  givenname: Gerhard
  surname: Weikum
  fullname: Weikum, Gerhard
SSID ssj0001501402
ssj0002792
Score 2.1573806
Snippet In this work, we propose a novel and efficient method for articulated human pose estimation in videos using a convolutional network architecture, which...
SourceID springer
proquest
SourceType Publisher
StartPage 302
SubjectTerms Artificial intelligence
Convolutional Layer
Convolutional Network
Image processing
Laplacian Pyramid
Motion Feature
Optical Flow
Pattern recognition
Title MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation
URI http://ebookcentral.proquest.com/lib/SITE_ID/reader.action?docID=5586509&ppg=320
http://ebookcentral.proquest.com/lib/SITE_ID/reader.action?docID=6296519&ppg=320
http://link.springer.com/10.1007/978-3-319-16808-1_21
Volume 9004
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnZ3Pb9MwFMctVi6IA7_FGEM-cIuMnDh24t26rjBNFIFUqt2sxHE5rZtod-Gv33t23PxgEhqXNLLSyMrHcd57ft9nQj6uwYgHQ0MyqYqM5U3TsKoSknGrhVN5bcsCBc6Lb-r8Z35xKS-7re-8umRXf7J_7tWV_A9VaAOuqJJ9ANn9TaEBzoEvHIEwHEfG7zDMGuoKtPsxJCsvD08YS6az2SqBb23eHwiL6zPnboICHc9iSdVfaLSGxKwkJA4s_I4-CVqFt-CF-wzEEOT_jlntc5gNrjqQbagglaNQQQwVjoKNvXjX9MvAvRTwfqYKy-X050vNw4bBf02-_XwL1EbhX8FFNUECPax1LTI-bPSf1PnpTGVagVVpYAwZuOiAHBSlnJDH0_nF11UXPcPlUI5u9r6PbTmlrs89oeR9fRq4FKNVcG9cLJ-Tpyg4oagEgV6-II_c5iV51roHtJ18t9AUice2V-RHgHtCpxR_aURL92ipR0sDWhrRUkBLPVqKaGmH9jVZfp4vZ-es3SSD3WRluWOZ43lTcKfStNGFaLRspMvB9OGiyrXTYG5mDtXEXFXaCq3AoeeuxEp2GV_X4g2ZbK437i2hIpN1VhVlXaR1bq3VjSxFatfrglte6-aQsPjAjF_Jb9OHbXg8WyNlifUYI7p_Xj9CfUiSSMHg5VsTS2oDPiMM4DMen0F87x549yPypHsl3pPJ7vetOwZ7cld_aAfXHQ9UbQ8
linkProvider Library Specific Holdings
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=bookitem&rft.title=Computer+Vision+--+ACCV+2014&rft.atitle=MoDeep%3A+A+Deep+Learning+Framework+Using+Motion+Features+for+Human+Pose+Estimation&rft.date=2015-01-01&rft.pub=Springer+International+Publishing+AG&rft.isbn=9783319168074&rft.volume=9004&rft_id=info:doi/10.1007%2F978-3-319-16808-1_21&rft.externalDBID=320&rft.externalDocID=EBC6296519_289_320
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Febookcentral.proquest.com%2Fcovers%2F5586509-l.jpg
http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Febookcentral.proquest.com%2Fcovers%2F6296519-l.jpg