3D Human pose estimation: A review of the literature and analysis of covariates

•Review of the recent literature in 3D human pose estimation from RGB images and videos.•Release of a challenging, publicly available, 3D pose estimation synthetic dataset.•Extensive experimental evaluation of some representative state-of-the-art methods. Estimating the pose of a human in 3D given a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Computer vision and image understanding Jg. 152; S. 1 - 20
Hauptverfasser:	Sarafianos, Nikolaos, Boteanu, Bogdan, Ionescu, Bogdan, Kakadiaris, Ioannis A.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Inc 01.11.2016
Schlagworte:	3D Human pose estimation Anthropometry Articulated tracking Human motion analysis Human motion analysis Anthropometry Articulated tracking 3D Human pose estimation
ISSN:	1077-3142, 1090-235X
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	•Review of the recent literature in 3D human pose estimation from RGB images and videos.•Release of a challenging, publicly available, 3D pose estimation synthetic dataset.•Extensive experimental evaluation of some representative state-of-the-art methods. Estimating the pose of a human in 3D given an image or a video has recently received significant attention from the scientific community. The main reasons for this trend are the ever increasing new range of applications (e.g., human-robot interaction, gaming, sports performance analysis) which are driven by current technological advances. Although recent approaches have dealt with several challenges and have reported remarkable results, 3D pose estimation remains a largely unsolved problem because real-life applications impose several challenges which are not fully addressed by existing methods. For example, estimating the 3D pose of multiple people in an outdoor environment remains a largely unsolved problem. In this paper, we review the recent advances in 3D human pose estimation from RGB images or image sequences. We propose a taxonomy of the approaches based on the input (e.g., single image or video, monocular or multi-view) and in each case we categorize the methods according to their key characteristics. To provide an overview of the current capabilities, we conducted an extensive experimental evaluation of state-of-the-art approaches in a synthetic dataset created specifically for this task, which along with its ground truth is made publicly available for research purposes. Finally, we provide an in-depth discussion of the insights obtained from reviewing the literature and the results of our experiments. Future directions and challenges are identified.
AbstractList	•Review of the recent literature in 3D human pose estimation from RGB images and videos.•Release of a challenging, publicly available, 3D pose estimation synthetic dataset.•Extensive experimental evaluation of some representative state-of-the-art methods. Estimating the pose of a human in 3D given an image or a video has recently received significant attention from the scientific community. The main reasons for this trend are the ever increasing new range of applications (e.g., human-robot interaction, gaming, sports performance analysis) which are driven by current technological advances. Although recent approaches have dealt with several challenges and have reported remarkable results, 3D pose estimation remains a largely unsolved problem because real-life applications impose several challenges which are not fully addressed by existing methods. For example, estimating the 3D pose of multiple people in an outdoor environment remains a largely unsolved problem. In this paper, we review the recent advances in 3D human pose estimation from RGB images or image sequences. We propose a taxonomy of the approaches based on the input (e.g., single image or video, monocular or multi-view) and in each case we categorize the methods according to their key characteristics. To provide an overview of the current capabilities, we conducted an extensive experimental evaluation of state-of-the-art approaches in a synthetic dataset created specifically for this task, which along with its ground truth is made publicly available for research purposes. Finally, we provide an in-depth discussion of the insights obtained from reviewing the literature and the results of our experiments. Future directions and challenges are identified.
Author	Boteanu, Bogdan Kakadiaris, Ioannis A. Sarafianos, Nikolaos Ionescu, Bogdan
Author_xml	– sequence: 1 givenname: Nikolaos surname: Sarafianos fullname: Sarafianos, Nikolaos email: nsarafianos@uh.edu organization: Computational Biomedicine Lab, Department of Computer Science, University of Houston, 4800 Calhoun Rd. Houston, TX 77004, United States – sequence: 2 givenname: Bogdan surname: Boteanu fullname: Boteanu, Bogdan organization: Image Processing and Analysis Lab, University Politehnica of Bucharest, 61071 Romania – sequence: 3 givenname: Bogdan surname: Ionescu fullname: Ionescu, Bogdan organization: Image Processing and Analysis Lab, University Politehnica of Bucharest, 61071 Romania – sequence: 4 givenname: Ioannis A. surname: Kakadiaris fullname: Kakadiaris, Ioannis A. email: ikakadia@central.uh.edu organization: Computational Biomedicine Lab, Department of Computer Science, University of Houston, 4800 Calhoun Rd. Houston, TX 77004, United States
BookMark	eNp9kM9qwzAMh83oYG23F9jJL5DMihOnHruU7k8HhV422M0ojsJc2qTYbkfffsm20w49CAnEJ_T7JmzUdi0xdgsiBQHqbpPaozukWT-nQqdCZBdsDEKLJJPFx2iYyzKRkGdXbBLCRgiAXMOYreUjXx522PJ9F4hTiG6H0XXtPZ9zT0dHX7xrePwkvnWRPMaDJ45t3RduT8GFYW27I3qHkcI1u2xwG-jmr0_Z-_PT22KZrNYvr4v5KrFSqZgUdamxRo0I0OSiaiRYWYpcQJZTXlZgG4nSzpRQdaWU0oUuSyhI2xqKokI5ZbPfu9Z3IXhqjHXx5_Ho0W0NCDOIMRsziDGDGCO06cX0aPYP3fs-tD-dhx5-IepD9Va8CdZRa6l2nmw0defO4d-nFn8J
CitedBy_id	crossref_primary_10_1016_j_conb_2019_10_008 crossref_primary_10_1016_j_jvcir_2023_103781 crossref_primary_10_1007_s13735_023_00269_6 crossref_primary_10_1109_TAES_2024_3379492 crossref_primary_10_1007_s10462_024_11089_3 crossref_primary_10_1016_j_patrec_2018_03_018 crossref_primary_10_1109_ACCESS_2019_2962833 crossref_primary_10_26599_TST_2021_9010068 crossref_primary_10_1016_j_iot_2024_101465 crossref_primary_10_1016_j_imavis_2025_105437 crossref_primary_10_1007_s11263_021_01570_9 crossref_primary_10_1145_3533384 crossref_primary_10_1007_s11760_024_03028_0 crossref_primary_10_3390_app14041646 crossref_primary_10_1109_TFUZZ_2022_3177028 crossref_primary_10_1109_ACCESS_2020_3011697 crossref_primary_10_1016_j_jvcir_2019_01_033 crossref_primary_10_7717_peerj_12995 crossref_primary_10_1109_JSEN_2021_3133108 crossref_primary_10_1177_0954406218757809 crossref_primary_10_1016_j_measurement_2024_114857 crossref_primary_10_3390_s23218997 crossref_primary_10_3390_app11094183 crossref_primary_10_1007_s00521_020_05086_0 crossref_primary_10_1016_j_apmr_2023_10_018 crossref_primary_10_1155_2022_5277157 crossref_primary_10_1016_j_dsp_2022_103628 crossref_primary_10_3390_s20236887 crossref_primary_10_1007_s11263_023_01756_3 crossref_primary_10_1016_j_cag_2019_03_010 crossref_primary_10_3390_s22218335 crossref_primary_10_3390_s25030934 crossref_primary_10_1016_j_cviu_2018_10_006 crossref_primary_10_1016_j_cviu_2021_103278 crossref_primary_10_1007_s13735_022_00261_6 crossref_primary_10_20965_ijat_2019_p0506 crossref_primary_10_1145_3524497 crossref_primary_10_1007_s12369_020_00739_5 crossref_primary_10_1016_j_patcog_2018_02_028 crossref_primary_10_3390_s20185426 crossref_primary_10_1080_00207543_2023_2286627 crossref_primary_10_1007_s11042_023_15057_x crossref_primary_10_1016_j_cviu_2025_104297 crossref_primary_10_1007_s11042_024_20495_2 crossref_primary_10_1002_cav_1887 crossref_primary_10_1016_j_neucom_2025_131004 crossref_primary_10_3390_app13042700 crossref_primary_10_1016_j_displa_2024_102838 crossref_primary_10_1002_cpe_4934 crossref_primary_10_1007_s13198_021_01094_y crossref_primary_10_1016_j_autcon_2024_105452 crossref_primary_10_3390_s23010062 crossref_primary_10_1007_s00530_021_00754_0 crossref_primary_10_1109_ACCESS_2020_3011360 crossref_primary_10_1007_s11042_020_09700_0 crossref_primary_10_1007_s00530_022_01019_0 crossref_primary_10_1109_ACCESS_2021_3063028 crossref_primary_10_1016_j_cviu_2019_04_011 crossref_primary_10_1016_j_jnca_2022_103566 crossref_primary_10_3390_civileng4010013 crossref_primary_10_1111_1365_2656_13932 crossref_primary_10_1007_s11042_018_5998_1 crossref_primary_10_1002_tal_2120 crossref_primary_10_1109_TPAMI_2018_2816031 crossref_primary_10_3390_s20236940 crossref_primary_10_1016_j_displa_2022_102225 crossref_primary_10_1016_j_engappai_2021_104260 crossref_primary_10_1109_TPAMI_2022_3158902 crossref_primary_10_1145_3386569_3392410 crossref_primary_10_3390_heritage5010025 crossref_primary_10_1016_j_inffus_2023_102154 crossref_primary_10_1145_3715093 crossref_primary_10_1109_TIM_2023_3286000 crossref_primary_10_1109_TIP_2020_2972104 crossref_primary_10_1145_3377552 crossref_primary_10_3390_jimaging9120275 crossref_primary_10_3233_WOR_205204 crossref_primary_10_1007_s10462_024_11019_3 crossref_primary_10_1007_s11042_019_08363_w crossref_primary_10_1109_TPAMI_2019_2894422 crossref_primary_10_1109_TPAMI_2020_2976014 crossref_primary_10_4103_ijoy_ijoy_137_22 crossref_primary_10_1007_s11548_022_02762_5 crossref_primary_10_1016_j_sna_2024_115752 crossref_primary_10_1109_JBHI_2021_3107532 crossref_primary_10_3390_electronics10182267 crossref_primary_10_1007_s11263_021_01436_0 crossref_primary_10_1109_TCSVT_2019_2928813 crossref_primary_10_4103_ijoy_ijoy_97_22 crossref_primary_10_1145_3272127_3275108 crossref_primary_10_3390_app11094143 crossref_primary_10_1007_s13042_020_01138_y crossref_primary_10_1016_j_cviu_2019_102897 crossref_primary_10_32604_cmes_2022_020857 crossref_primary_10_1016_j_neucom_2023_126827 crossref_primary_10_1016_j_jneumeth_2021_109199 crossref_primary_10_1145_3757733 crossref_primary_10_1038_s41598_024_79707_2 crossref_primary_10_1109_ACCESS_2022_3155179 crossref_primary_10_3390_mi9080411 crossref_primary_10_1109_ACCESS_2020_2980316 crossref_primary_10_1109_ACCESS_2022_3177623 crossref_primary_10_3390_heritage5010006 crossref_primary_10_1007_s11263_024_01984_1 crossref_primary_10_1145_3494675 crossref_primary_10_1109_ACCESS_2022_3190500 crossref_primary_10_1109_ACCESS_2025_3567337 crossref_primary_10_3390_s23198330 crossref_primary_10_1007_s11042_023_16225_9 crossref_primary_10_26634_jcom_12_2_20637 crossref_primary_10_1038_s41598_024_66165_z crossref_primary_10_1016_j_imavis_2021_104282 crossref_primary_10_1016_j_bspc_2024_106508 crossref_primary_10_3390_electronics14071307 crossref_primary_10_1109_TNNLS_2020_3009448 crossref_primary_10_3390_electronics9091368 crossref_primary_10_1109_JSEN_2024_3522105 crossref_primary_10_1049_iet_cvi_2017_0536 crossref_primary_10_3390_app12104806 crossref_primary_10_1016_j_cviu_2021_103225 crossref_primary_10_1108_IR_04_2024_0134 crossref_primary_10_3390_s22134846 crossref_primary_10_1145_3580883 crossref_primary_10_1016_j_jer_2025_07_007 crossref_primary_10_1109_TPAMI_2021_3087695 crossref_primary_10_1155_2022_6858822 crossref_primary_10_1016_j_yebeh_2018_07_028 crossref_primary_10_1007_s00371_019_01740_4 crossref_primary_10_1016_j_cviu_2019_102792 crossref_primary_10_1109_ACCESS_2023_3258417 crossref_primary_10_1108_IR_06_2020_0129 crossref_primary_10_1016_j_patcog_2023_109714 crossref_primary_10_1016_j_jcp_2025_114127
Cites_doi	10.1007/s11263-008-0158-0 10.1007/s00138-011-0344-x 10.1016/j.patcog.2009.02.012 10.1109/TPAMI.2006.21 10.1016/j.imavis.2012.06.009 10.1007/s11263-012-0524-9 10.1109/JSTSP.2012.2196975 10.1038/nature14539 10.1109/34.895978 10.1016/j.cviu.2014.10.005 10.1016/j.cviu.2010.11.007 10.1109/TIP.2015.2487860 10.1007/s11263-009-0205-5 10.1109/TPAMI.2012.241 10.1007/s11263-011-0451-1 10.1109/TPAMI.2013.248 10.1007/978-3-642-33765-9_41 10.1109/TVCG.2010.272 10.1109/TCYB.2013.2276430 10.1023/B:VISI.0000042934.15159.49 10.1109/TPAMI.2016.2557779 10.1109/TSMCC.2009.2027608 10.1007/s11263-008-0204-y 10.1006/cviu.1998.0716 10.1007/978-3-642-12307-8_5 10.1109/TPAMI.2011.21 10.1016/B978-0-12-374633-7.00016-1 10.1007/s11263-006-5165-4 10.1016/j.sigpro.2014.08.028 10.1561/2200000006 10.1016/j.patcog.2013.05.019 10.1007/s11263-011-0493-4 10.1016/j.cviu.2006.10.012 10.1007/978-0-387-31439-6_584 10.1007/s12369-011-0099-6 10.1016/j.cviu.2011.08.007 10.1109/CVPR.2014.303 10.1145/2133366.2133371 10.1561/2000000039 10.1109/TPAMI.2007.1173 10.1109/TPAMI.2009.167 10.1016/j.cviu.2006.08.002 10.1109/CVPR.2017.373 10.1007/s00138-002-0088-8 10.1126/science.1127647 10.1109/TIP.2013.2271850 10.1007/s11263-009-0293-2 10.1007/978-3-642-15558-1_34 10.1145/2398356.2398381 10.1162/neco.2006.18.7.1527 10.1007/s11263-015-0818-9 10.1016/j.cviu.2006.10.016 10.1007/s11263-009-0273-6 10.1109/TPAMI.2013.50
ContentType	Journal Article
Copyright	2016 Elsevier Inc.
Copyright_xml	– notice: 2016 Elsevier Inc.
DBID	AAYXX CITATION
DOI	10.1016/j.cviu.2016.09.002
DatabaseName	CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences Engineering Computer Science
EISSN	1090-235X
EndPage	20
ExternalDocumentID	10_1016_j_cviu_2016_09_002 S1077314216301369
GroupedDBID	--K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 6TJ 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADFGL ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CAG COF CS3 DM4 DU5 EBS EFBJH EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HF~ HVGLF HZ~ IHE J1W JJJVA KOM LG5 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSV SSZ T5K TN5 XPP ZMT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS SST ~HD
ID	FETCH-LOGICAL-c366t-5d79ada9aa11f40bf31c37040124e47b1cf3a3c8606db6669597715e9cd155ba3
ISICitedReferencesCount	215
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000387630900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1077-3142
IngestDate	Tue Nov 18 21:56:36 EST 2025 Sat Nov 29 06:43:52 EST 2025 Fri Feb 23 02:26:56 EST 2024
IsPeerReviewed	true
IsScholarly	true
Keywords	Human motion analysis Anthropometry Articulated tracking 3D Human pose estimation
Language	English
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c366t-5d79ada9aa11f40bf31c37040124e47b1cf3a3c8606db6669597715e9cd155ba3
PageCount	20
ParticipantIDs	crossref_citationtrail_10_1016_j_cviu_2016_09_002 crossref_primary_10_1016_j_cviu_2016_09_002 elsevier_sciencedirect_doi_10_1016_j_cviu_2016_09_002
PublicationCentury	2000
PublicationDate	November 2016 2016-11-00
PublicationDateYYYYMMDD	2016-11-01
PublicationDate_xml	– month: 11 year: 2016 text: November 2016
PublicationDecade	2010
PublicationTitle	Computer vision and image understanding
PublicationYear	2016
Publisher	Elsevier Inc
Publisher_xml	– name: Elsevier Inc
References	Pons-Moll, Taylor, Shotton, Hertzmann, Fitzgibbon (bib0161) 2015; 113 Wang, Wang, Lin, Yuille, Gao (bib0143) 2014 Simo-Serra, Torras, Moreno-Noguer (bib0122) 2015 Kazemi, Burenius, Azizpour, Sullivan (bib0075) 2013 Pons-Moll, Taylor, Shotton, Hertzmann, Fitzgibbon (bib0162) 2013 SAE International. CAESAR: Civilian American and European Surface Anthropometry Resource database. Available online at Erol, Bebis, Nicolescu, Boyle, Twombly (bib0043) 2007; 108 Yamada, Sigal, Raptis (bib0145) 2012 Amin, Andriluka, Rohrbach, Schiele (bib0007) 2013 Tekin, Rozantsev, Lepetit, Fua (bib0132) 2016 Zuffi, Black (bib0159) 2015 arXiv preprint. Pugliese, Förger, Takala (bib0096) 2015 Müller, Arens (bib0089) 2010 Agarwal, Triggs (bib0003) 2004 Helten, Baak, Müller, Theobalt (bib0056) 2013 Yang, Baker, Kannan, Ramanan (bib0147) 2012 Gall, Stoll, De Aguiar, Theobalt, Rosenhahn, Seidel (bib0048) 2009 Pons-Moll, Fleet, Rosenhahn (bib0094) 2014 Bengio (bib0017) 2009; 2 Ramakrishna, Kanade, Sheikh (bib0099) 2012 Chen, Zhuang, Nie, Yang, Wu, Xiao (bib0031) 2011; 17 Elhayek, de Aguiar, Jain, Tompson, Pishchulin, Andriluka, Bregler, Schiele, Theobalt (bib0042) 2016 Chen, Yang, Nie, Odobez (bib0030) 2011; 115 Daubney, Xie (bib0036) 2011 Kakadiaris, Sarafianos, Christophoros (bib0074) 2016 Kostrikov, Gall (bib0076) 2014 Radwan, Dhall, Goecke (bib0097) 2013 Kakadiaris, Metaxas (bib0073) 2000; 22 Pishchulin, Andriluka, Gehler, Schiele (bib0093) 2013 Wandt, Ackermann, Rosenhahn (bib0141) 2015 . Tian, Sigal, De la Torre, Jia (bib0134) 2013; 31 LeCun, Bengio, Hinton (bib0078) 2015; 521 Bishop, Lasserre (bib0021) 2007; 8 Sedai, Bennamoun, Huynh (bib0109) 2010 Chen, Gallagher, Girod (bib0032) 2012 Marinoiu, Papava, Sminchisescu (bib0084) 2013 Sminchisescu (bib0123) 2002 Berclaz, Fleuret, Tretken, Fua (bib0019) 2011 Sedai, Bennamoun, Huynh (bib0111) 2013; 22 Bo, L., Sminchisescu, C., (2010b). Source code for Twin gaussian processes for structured prediction. Available online at Van der Aa, Luo, Giezeman, Tan, Veltkamp (bib0002) 2011 Holte, Tran, Trivedi, Moeslund (bib0061) 2012; 6 Song, Demirdjian, Davis (bib0125) 2012; 2 Poppe (bib0095) 2007; 108 Greif, Lienhart, Sengupta (bib0052) 2011 Elhayek, de Aguiar, Jain, Tompson, Pishchulin, Andriluka, Bregler, Schiele, Theobalt (bib0041) 2015 Yamaguchi, Kiapour, Ortiz, Berg (bib0146) 2012 Taylor, Sigal, Fleet, Hinton (bib0130) 2010 Deng, Yu (bib0037) 2014; 7 Szegedy, Toshev, Erhan (bib0128) 2013 Hofmann, Gavrila (bib0059) 2009 Liu, Stoll, Gall, Seidel, Theobalt (bib0082) 2011 Tompson, Jain, LeCun, Bregler (bib0135) 2014 Ferrari, Marin-Jimenez, Zisserman (bib0047) 2008 Ramakrishna, V., Kanade, T., Sheikh, Y., 2012b. Source code for Reconstructing 3D human pose from 2D image landmarks. Available online at Moeslund, Hilton, Krüger (bib0086) 2006; 104 Gupta, Satkin, Efros, Hebert (bib0055) 2011 Sigal (bib0114) 2014 Bray, Kohli, Torr (bib0027) 2006 Ek, Torr, Lawrence (bib0040) 2008 Li, Chan (bib0079) 2014 Amin, Müller, Bulling, Andriluka (bib0008) 2014 Felzenszwalb, Huttenlocher (bib0045) 2005; 61 Aggarwal, Cai (bib0005) 1997 Chen, Yuille (bib0034) 2014 Gupta, Mittal, Davis (bib0054) 2008; 30 Yao, Gall, Gool, Urtasun (bib0149) 2011 Sedai, Bennamoun, Huynh (bib0108) 2009 Salzmann, Urtasun (bib0106) 2010 Guo, Patras (bib0053) 2009 Barron, Kakadiaris (bib0012) 2000 Sminchisescu (bib0124) 2008 Stoll, Hasler, Gall, Seidel, Theobalt (bib0126) 2011 Wang, C., Wang, Y., Lin, Z., Yuille, A. L., Gao, W., 2014b. Source code for Robust estimation of 3D human poses from a single image. Available online at Belagiannis, Wang, Schiele, Fua, Ilic, Navab (bib0016) 2014 Rosales, Sclaroff (bib0104) 2006; 67 Simo-Serra, Ramisa, Alenyà, Torras, Moreno-Noguer (bib0121) 2012 Sigal, Black (bib0117) 2006 Tekin, Katircioglu, Salzmann, Lepetit, Fua (bib0131) 2016 Moutzouris, Martinez-del Rincon, Nebel, Makris (bib0088) 2015; 132 Pons-Moll, Baak, Gall, Leal-Taixe, Mueller, Seidel, Rosenhahn (bib0165) 2011 Valmadre, Lucey (bib0140) 2010 Zhou, Leonardos, Hu, Daniilidis (bib0156) 2015 Hong, Yu, Tao, Wan, Wang (bib0062) 2015 Huang, Yang (bib0065) 2009 Felzenszwalb, Girshick, McAllester, Ramanan (bib0046) 2010; 32 Johnson, Everingham (bib0072) 2010 Sigal, Isard, Haussecker, Black (bib0119) 2012; 98 Yang, Ramanan (bib0148) 2011 Jiang (bib0070) 2010 Sigal, Bhatia, Roth, Black, Isard (bib0116) 2004 Andriluka, Sigal (bib0010) 2012 Sedai, Bennamoun, Huynh (bib0110) 2013; 46 Agarwal, Triggs (bib0004) 2006; 28 Zheng, Liu, Dorsey, Mitra (bib0154) 2015 Bo, Sminchisescu (bib0024) 2010; 87 Toshev, Szegedy (bib0136) 2014 Wandt, Ackermann, Rosenhahn (bib0167) 2016; 38(8) Zhou, Leonardos, Hu, Daniilidis (bib0155) 2015 MakeHuman, (2000). Makehuman open source software for the modelling of 3-dimensional humanoid characters. Available online at Zhou, Zhu, Leonardos, Derpanis, Daniilidis (bib0158) 2016 Chen, Wang, Li, Su, Lischinsk, Cohen-Or, Chen (bib0033) 2016 Hinton, Salakhutdinov (bib0058) 2006; 313 Jaeggli, Koller-Meier, Van Gool (bib0068) 2009; 83 Rius, Gonzàlez, Varona, Xavier Roca (bib0101) 2009; 42 Krizhevsky, Sutskever, Hinton (bib0077) 2012 Daubney, Gibson, Campbell (bib0035) 2012; 116 Sigal, Balan, Black (bib0115) 2010; 87 Sigal, Black (bib0118) 2010; 87 Yasin, Iqbal, Krüger, Weber, Gall (bib0151) 2016 Ning, Xu, Gong, Huang (bib0090) 2008 Belagiannis, Amin, Andriluka, Schiele, Navab, Ilic (bib0014) 2014 Charles, Pfister, Magee, Hogg, Zisserman (bib0029) 2016 Van den Bergh, Koller-Meier, Kehl, Van Gool (bib0020) 2009; 335 Simo-Serra, Quattoni, Torras, Moreno-Noguer (bib0120) 2013 Moeslund, Hilton, Krüger, Sigal (bib0087) 2011 Urtasun, Darrell (bib0138) 2008 Zhou, Zhu, Leonardos, Daniilidis (bib0163) 2016 McColl, Zhang, Nejat (bib0085) 2011; 3 Taigman, Yang, Ranzato, Wolf (bib0129) 2014 Burenius, Sullivan, Carlsson (bib0028) 2013 Hofmann, Gavrila (bib0060) 2012; 96 Ionescu, Papava, Olaru, Sminchisescu (bib0067) 2014; 36 von Marcard, Pons-Moll, Rosenhahn (bib0166) 2016 Ramanan (bib0100) 2006 Bengio, Courville, Vincent (bib0018) 2013; 35 Pons-Moll, Baak, Helten, Müller, Seidel, Rosenhahn (bib0164) 2010 Andriluka, Roth, Schiele (bib0009) 2010 Fastovets, Guillemaut, Hilton (bib0044) 2013 Belagiannis, Amin, Andriluka, Schiele, Navab, Ilic (bib0015) 2015 Gkioxari, Arbeláez, Bourdev, Malik (bib0050) 2013 Blender Foundation, (2002). Blender open source 3D creation suite. Available online at Gavrila (bib0049) 1999; 73 Suma, Lange, Rizzo, Krum, Bolas (bib0127) 2011 Liu, Liu, Dauwels, Seah (bib0081) 2015; 110 Shotton, Girshick, Fitzgibbon, Sharp, Cook, Finocchio, Moore, Kohli, Criminisi, Kipman, A. (bib0112) 2013; 35 Ji, Liu (bib0069) 2010; 40 Rohrbach, Amin, Andriluka, Schiele (bib0103) 2012 Rogez, G., Schmid, C., 2016. Mocap-guided data augmentation for 3D pose estimation in the wild. Jiang, H., Grauman, K., 2016. Seeing invisible poses: Estimating 3D body pose from egocentric video. Peursum, Venkatesh, West (bib0092) 2010; 87 Zuffi, Freifeld, Black (bib0160) 2012 Boteanu, B., Sarafianos, N., Ionescu, B., Kakadiaris, I., (2016). Synpose 300 dataset and ground truth. Available online at Barmpoutis (bib0011) 2013; 43 Barron, Kakadiaris (bib0013) 2003; 14 Ionescu, Li, Sminchisescu (bib0066) 2011 Eichner, Marin-Jimenez, Zisserman, Ferrari (bib0039) 2012; 99 Hinton, Osindero, Teh (bib0057) 2006; 18 Zhou, Zhu, Leonardos, Derpanis, Daniilidis (bib0157) 2016 Wei, Chai (bib0144) 2009 Ye, Zhang, Wang, Zhu, Yang, Gall (bib0152) 2013 Howe (bib0063) 2011; 22 Huang, J.-B., Yang, M.-H., (2009b). Source code for Estimating human pose from occluded images. Available online at Okada, Soatto (bib0091) 2008 Zhang, Han, Ren, Umetani, Tong, Liu, Shiratori, Cao (bib0153) 2013 Brauer, Hübner, Arens (bib0026) 2012 Unzueta, Goenetxea, Rodriguez, Linaza (bib0137) 2014 Yasin, Iqbal, Krüger, Weber, Gall (bib0150) 2016 Grauman, Shakhnarovich, Darrell (bib0051) 2003 Valmadre, J., Lucey, S., (2010b). Source code for Deterministic 3D human pose estimation using rigid structure. Available online at Droeschel, Behnke (bib0038) 2011 Carnegie Mellon University Graphics Lab. MoCap: motion capture database. (available online at Tenorth, Bandouch, Beetz (bib0133) 2009 Shotton, Sharp, Kipman, Fitzgibbon, Finocchio, Blake, Cook, Moore (bib0113) 2013; 56 Akhter, Black (bib0006) 2015 Schick, Stiefelhagen (bib0107) 2015 Li, Zhang, Chan (bib0080) 2015 Yasin (10.1016/j.cviu.2016.09.002_bib0150) 2016 Salzmann (10.1016/j.cviu.2016.09.002_bib0106) 2010 Simo-Serra (10.1016/j.cviu.2016.09.002_bib0121) 2012 10.1016/j.cviu.2016.09.002_bib0022 Ionescu (10.1016/j.cviu.2016.09.002_bib0066) 2011 10.1016/j.cviu.2016.09.002_bib0142 10.1016/j.cviu.2016.09.002_bib0023 10.1016/j.cviu.2016.09.002_bib0025 Holte (10.1016/j.cviu.2016.09.002_bib0061) 2012; 6 Sedai (10.1016/j.cviu.2016.09.002_bib0109) 2010 Sminchisescu (10.1016/j.cviu.2016.09.002_bib0124) 2008 Gupta (10.1016/j.cviu.2016.09.002_bib0055) 2011 Daubney (10.1016/j.cviu.2016.09.002_bib0036) 2011 Sigal (10.1016/j.cviu.2016.09.002_bib0114) 2014 Ning (10.1016/j.cviu.2016.09.002_bib0090) 2008 Kazemi (10.1016/j.cviu.2016.09.002_bib0075) 2013 Brauer (10.1016/j.cviu.2016.09.002_bib0026) 2012 Felzenszwalb (10.1016/j.cviu.2016.09.002_bib0045) 2005; 61 Ionescu (10.1016/j.cviu.2016.09.002_bib0067) 2014; 36 Zhou (10.1016/j.cviu.2016.09.002_bib0155) 2015 LeCun (10.1016/j.cviu.2016.09.002_bib0078) 2015; 521 Yamaguchi (10.1016/j.cviu.2016.09.002_bib0146) 2012 Grauman (10.1016/j.cviu.2016.09.002_bib0051) 2003 Yang (10.1016/j.cviu.2016.09.002_bib0147) 2012 Rohrbach (10.1016/j.cviu.2016.09.002_bib0103) 2012 Bengio (10.1016/j.cviu.2016.09.002_bib0018) 2013; 35 Belagiannis (10.1016/j.cviu.2016.09.002_bib0015) 2015 Poppe (10.1016/j.cviu.2016.09.002_bib0095) 2007; 108 Sedai (10.1016/j.cviu.2016.09.002_bib0110) 2013; 46 Liu (10.1016/j.cviu.2016.09.002_bib0082) 2011 Sigal (10.1016/j.cviu.2016.09.002_bib0115) 2010; 87 Felzenszwalb (10.1016/j.cviu.2016.09.002_bib0046) 2010; 32 Liu (10.1016/j.cviu.2016.09.002_bib0081) 2015; 110 Unzueta (10.1016/j.cviu.2016.09.002_bib0137) 2014 Agarwal (10.1016/j.cviu.2016.09.002_bib0004) 2006; 28 Elhayek (10.1016/j.cviu.2016.09.002_bib0041) 2015 Schick (10.1016/j.cviu.2016.09.002_bib0107) 2015 Pishchulin (10.1016/j.cviu.2016.09.002_bib0093) 2013 Barron (10.1016/j.cviu.2016.09.002_bib0012) 2000 Rosales (10.1016/j.cviu.2016.09.002_bib0104) 2006; 67 Li (10.1016/j.cviu.2016.09.002_bib0080) 2015 Akhter (10.1016/j.cviu.2016.09.002_bib0006) 2015 Erol (10.1016/j.cviu.2016.09.002_bib0043) 2007; 108 Ye (10.1016/j.cviu.2016.09.002_bib0152) 2013 10.1016/j.cviu.2016.09.002_bib0083 Van den Bergh (10.1016/j.cviu.2016.09.002_bib0020) 2009; 335 Rius (10.1016/j.cviu.2016.09.002_bib0101) 2009; 42 Van der Aa (10.1016/j.cviu.2016.09.002_bib0002) 2011 Suma (10.1016/j.cviu.2016.09.002_bib0127) 2011 10.1016/j.cviu.2016.09.002_bib0001 Helten (10.1016/j.cviu.2016.09.002_bib0056) 2013 Tenorth (10.1016/j.cviu.2016.09.002_bib0133) 2009 Berclaz (10.1016/j.cviu.2016.09.002_bib0019) 2011 Moeslund (10.1016/j.cviu.2016.09.002_bib0087) 2011 Moutzouris (10.1016/j.cviu.2016.09.002_bib0088) 2015; 132 Pons-Moll (10.1016/j.cviu.2016.09.002_bib0161) 2015; 113 von Marcard (10.1016/j.cviu.2016.09.002_bib0166) 2016 Fastovets (10.1016/j.cviu.2016.09.002_bib0044) 2013 Valmadre (10.1016/j.cviu.2016.09.002_bib0140) 2010 Zhou (10.1016/j.cviu.2016.09.002_bib0157) 2016 Chen (10.1016/j.cviu.2016.09.002_bib0031) 2011; 17 Barron (10.1016/j.cviu.2016.09.002_bib0013) 2003; 14 Barmpoutis (10.1016/j.cviu.2016.09.002_bib0011) 2013; 43 Tompson (10.1016/j.cviu.2016.09.002_bib0135) 2014 Deng (10.1016/j.cviu.2016.09.002_bib0037) 2014; 7 Jiang (10.1016/j.cviu.2016.09.002_bib0070) 2010 Taylor (10.1016/j.cviu.2016.09.002_bib0130) 2010 Eichner (10.1016/j.cviu.2016.09.002_bib0039) 2012; 99 McColl (10.1016/j.cviu.2016.09.002_bib0085) 2011; 3 Bo (10.1016/j.cviu.2016.09.002_bib0024) 2010; 87 Ferrari (10.1016/j.cviu.2016.09.002_bib0047) 2008 Gupta (10.1016/j.cviu.2016.09.002_bib0054) 2008; 30 Elhayek (10.1016/j.cviu.2016.09.002_bib0042) 2016 10.1016/j.cviu.2016.09.002_bib0098 Shotton (10.1016/j.cviu.2016.09.002_bib0113) 2013; 56 Zhang (10.1016/j.cviu.2016.09.002_bib0153) 2013 Taigman (10.1016/j.cviu.2016.09.002_bib0129) 2014 Ji (10.1016/j.cviu.2016.09.002_bib0069) 2010; 40 Zhou (10.1016/j.cviu.2016.09.002_bib0158) 2016 Zhou (10.1016/j.cviu.2016.09.002_bib0163) 2016 Hinton (10.1016/j.cviu.2016.09.002_bib0058) 2006; 313 10.1016/j.cviu.2016.09.002_bib0139 Wang (10.1016/j.cviu.2016.09.002_bib0143) 2014 Wandt (10.1016/j.cviu.2016.09.002_bib0141) 2015 Yamada (10.1016/j.cviu.2016.09.002_bib0145) 2012 Bengio (10.1016/j.cviu.2016.09.002_bib0017) 2009; 2 Shotton (10.1016/j.cviu.2016.09.002_bib0112) 2013; 35 Kakadiaris (10.1016/j.cviu.2016.09.002_bib0073) 2000; 22 10.1016/j.cviu.2016.09.002_bib0064 Sedai (10.1016/j.cviu.2016.09.002_bib0108) 2009 Belagiannis (10.1016/j.cviu.2016.09.002_bib0016) 2014 Pons-Moll (10.1016/j.cviu.2016.09.002_bib0165) 2011 Szegedy (10.1016/j.cviu.2016.09.002_bib0128) 2013 Ramanan (10.1016/j.cviu.2016.09.002_bib0100) 2006 10.1016/j.cviu.2016.09.002_bib0102 10.1016/j.cviu.2016.09.002_bib0105 Sigal (10.1016/j.cviu.2016.09.002_bib0116) 2004 Pugliese (10.1016/j.cviu.2016.09.002_bib0096) 2015 Wei (10.1016/j.cviu.2016.09.002_bib0144) 2009 Tekin (10.1016/j.cviu.2016.09.002_bib0132) 2016 Andriluka (10.1016/j.cviu.2016.09.002_bib0009) 2010 Gkioxari (10.1016/j.cviu.2016.09.002_bib0050) 2013 Guo (10.1016/j.cviu.2016.09.002_bib0053) 2009 Agarwal (10.1016/j.cviu.2016.09.002_bib0003) 2004 Chen (10.1016/j.cviu.2016.09.002_bib0034) 2014 Pons-Moll (10.1016/j.cviu.2016.09.002_bib0162) 2013 Yang (10.1016/j.cviu.2016.09.002_bib0148) 2011 Burenius (10.1016/j.cviu.2016.09.002_bib0028) 2013 10.1016/j.cviu.2016.09.002_bib0071 Sedai (10.1016/j.cviu.2016.09.002_bib0111) 2013; 22 Gall (10.1016/j.cviu.2016.09.002_bib0048) 2009 Jaeggli (10.1016/j.cviu.2016.09.002_bib0068) 2009; 83 Johnson (10.1016/j.cviu.2016.09.002_bib0072) 2010 Zuffi (10.1016/j.cviu.2016.09.002_bib0160) 2012 Yasin (10.1016/j.cviu.2016.09.002_bib0151) 2016 Daubney (10.1016/j.cviu.2016.09.002_bib0035) 2012; 116 Simo-Serra (10.1016/j.cviu.2016.09.002_bib0122) 2015 Simo-Serra (10.1016/j.cviu.2016.09.002_bib0120) 2013 Sigal (10.1016/j.cviu.2016.09.002_bib0118) 2010; 87 Hinton (10.1016/j.cviu.2016.09.002_bib0057) 2006; 18 Tian (10.1016/j.cviu.2016.09.002_bib0134) 2013; 31 Howe (10.1016/j.cviu.2016.09.002_bib0063) 2011; 22 Krizhevsky (10.1016/j.cviu.2016.09.002_bib0077) 2012 Droeschel (10.1016/j.cviu.2016.09.002_bib0038) 2011 Song (10.1016/j.cviu.2016.09.002_bib0125) 2012; 2 Wandt (10.1016/j.cviu.2016.09.002_bib0167) 2016; 38(8) Zhou (10.1016/j.cviu.2016.09.002_bib0156) 2015 Sminchisescu (10.1016/j.cviu.2016.09.002_bib0123) 2002 Stoll (10.1016/j.cviu.2016.09.002_bib0126) 2011 Toshev (10.1016/j.cviu.2016.09.002_bib0136) 2014 Ek (10.1016/j.cviu.2016.09.002_bib0040) 2008 Yao (10.1016/j.cviu.2016.09.002_bib0149) 2011 Aggarwal (10.1016/j.cviu.2016.09.002_bib0005) 1997 Zheng (10.1016/j.cviu.2016.09.002_bib0154) 2015 Hong (10.1016/j.cviu.2016.09.002_bib0062) 2015 Belagiannis (10.1016/j.cviu.2016.09.002_bib0014) 2014 Sigal (10.1016/j.cviu.2016.09.002_bib0119) 2012; 98 Chen (10.1016/j.cviu.2016.09.002_bib0030) 2011; 115 Hofmann (10.1016/j.cviu.2016.09.002_bib0059) 2009 Urtasun (10.1016/j.cviu.2016.09.002_bib0138) 2008 Chen (10.1016/j.cviu.2016.09.002_bib0032) 2012 Amin (10.1016/j.cviu.2016.09.002_bib0008) 2014 Li (10.1016/j.cviu.2016.09.002_bib0079) 2014 Bray (10.1016/j.cviu.2016.09.002_bib0027) 2006 Huang (10.1016/j.cviu.2016.09.002_bib0065) 2009 Zuffi (10.1016/j.cviu.2016.09.002_bib0159) 2015 Kakadiaris (10.1016/j.cviu.2016.09.002_bib0074) 2016 Bishop (10.1016/j.cviu.2016.09.002_bib0021) 2007; 8 Sigal (10.1016/j.cviu.2016.09.002_bib0117) 2006 Andriluka (10.1016/j.cviu.2016.09.002_bib0010) 2012 Moeslund (10.1016/j.cviu.2016.09.002_bib0086) 2006; 104 Peursum (10.1016/j.cviu.2016.09.002_bib0092) 2010; 87 Hofmann (10.1016/j.cviu.2016.09.002_bib0060) 2012; 96 Pons-Moll (10.1016/j.cviu.2016.09.002_bib0094) 2014 Greif (10.1016/j.cviu.2016.09.002_bib0052) 2011 Müller (10.1016/j.cviu.2016.09.002_bib0089) 2010 Radwan (10.1016/j.cviu.2016.09.002_bib0097) 2013 Gavrila (10.1016/j.cviu.2016.09.002_bib0049) 1999; 73 Pons-Moll (10.1016/j.cviu.2016.09.002_bib0164) 2010 Tekin (10.1016/j.cviu.2016.09.002_bib0131) 2016 Marinoiu (10.1016/j.cviu.2016.09.002_bib0084) 2013 Ramakrishna (10.1016/j.cviu.2016.09.002_bib0099) 2012 Amin (10.1016/j.cviu.2016.09.002_bib0007) 2013 Charles (10.1016/j.cviu.2016.09.002_bib0029) 2016 Kostrikov (10.1016/j.cviu.2016.09.002_bib0076) 2014 Okada (10.1016/j.cviu.2016.09.002_bib0091) 2008 Chen (10.1016/j.cviu.2016.09.002_bib0033) 2016
References_xml	– reference: MakeHuman, (2000). Makehuman open source software for the modelling of 3-dimensional humanoid characters. Available online at: – start-page: 663 year: 2010 end-page: 670 ident: bib0164 article-title: Multisensor-fusion for publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA – start-page: 641 year: 2003 end-page: 647 ident: bib0051 article-title: Inferring 3D structure with a statistical image-based shape model publication-title: Proc. 9th IEEE International Conference on Computer Vision – volume: 87 start-page: 4 year: 2010 end-page: 27 ident: bib0115 article-title: Humaneva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion publication-title: Int. J. Comput. Vis. – volume: 115 start-page: 290 year: 2011 end-page: 299 ident: bib0030 article-title: 3D Human pose recovery from image by efficient visual feature selection publication-title: Comput. Vision Image Understanding – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: bib0078 article-title: Deep learning publication-title: Nature – start-page: 470 year: 2012 end-page: 481 ident: bib0026 article-title: Generative 2D and 3D human pose estimation with vote distributions publication-title: Advances in Visual Computing – year: 2015 ident: bib0015 article-title: 3D Pictorial structures revisited: multiple human pose estimation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: ). – start-page: 1873 year: 2009 end-page: 1880 ident: bib0144 article-title: Modeling 3D human poses from uncalibrated monocular images publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Miami Beach, FL – start-page: 3342 year: 2013 end-page: 3349 ident: bib0050 article-title: Articulated pose estimation using discriminative armlet classifiers publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Portland, Oregon – start-page: 434 year: 2008 end-page: 445 ident: bib0091 article-title: Relevant feature selection for human pose estimation and localization in cluttered images publication-title: Proc. 10th European Conference on Computer Vision – year: 2016 ident: bib0132 article-title: Direct prediction of 3D body poses from motion compensated sequences publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV – start-page: 951 year: 2011 end-page: 958 ident: bib0126 article-title: Fast articulated motion tracking using a sums of gaussians body model publication-title: Proc. IEEE International Conference on Computer Vision. Barcelona, Spain – start-page: 12.1 year: 2010 end-page: 12.11 ident: bib0072 article-title: Clustered pose and nonlinear appearance models for human pose estimation publication-title: Proc. British Machine Vision Conference. Aberystwyth, Wales – start-page: 3810 year: 2015 end-page: 3818 ident: bib0041 article-title: Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA – volume: 7 start-page: 197 year: 2014 end-page: 387 ident: bib0037 article-title: Deep learning: methods and applications publication-title: Found. Trends Signal Process. – volume: 61 start-page: 55 year: 2005 end-page: 79 ident: bib0045 article-title: Pictorial structures for object recognition publication-title: Int. J. Comput. Vis. – volume: 35 start-page: 2821 year: 2013 end-page: 2840 ident: bib0112 article-title: Efficient human pose estimation from single depth images publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: arXiv preprint. – reference: SAE International. CAESAR: Civilian American and European Surface Anthropometry Resource database. Available online at: – start-page: 1385 year: 2011 end-page: 1392 ident: bib0148 article-title: Articulated pose estimation with flexible mixtures-of-parts publication-title: Proc. 24th IEEE Conference on Computer Vision and Pattern Recognition. Colorado Springs, CO – start-page: 9 year: 2009 end-page: 15 ident: bib0053 article-title: Discriminative 3D human pose estimation from monocular images via topological preserving hierarchical affinity clustering publication-title: Proc. IEEE 12th International Conference on Computer Vision. Kyoto – start-page: 90 year: 1997 end-page: 102 ident: bib0005 article-title: Human motion analysis: a review publication-title: Proc. IEEE Nonrigid and Articulated Motion Workshop. San Juan, Puerto Rico – start-page: 1888 year: 2013 end-page: 1895 ident: bib0097 article-title: Monocular image 3D human pose estimation under self-occlusion publication-title: Proc. IEEE International Conference on Computer Vision. Sydney, Australia – volume: 56 start-page: 116 year: 2013 end-page: 124 ident: bib0113 article-title: Real-time human pose recognition in parts from single depth images publication-title: Commun. ACM – start-page: 1097 year: 2012 end-page: 1105 ident: bib0077 article-title: Imagenet classification with deep convolutional neural networks publication-title: Proc. Advances in Neural Information Processing Systems. Lake Tahoe, NV – start-page: 742 year: 2014 end-page: 754 ident: bib0016 article-title: Multiple human pose estimation with temporally consistent 3D pictorial structures publication-title: Proc. 13th European Conference on Computer Vision, ChaLearn Looking at People Workshop. Zurich, Switzerland – start-page: 51.1 year: 2010 end-page: 51.10 ident: bib0109 article-title: Localized fusion of shape and appearance features for 3D human pose estimation publication-title: Proc. British Machine Vision Conference. Aberystwyth, Wales – start-page: 2214 year: 2009 end-page: 2221 ident: bib0059 article-title: Multi-view 3D human pose estimation combining single-frame recovery, temporal integration and model adaptation publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Miami Beach, FL – volume: 2 start-page: 5 year: 2012 ident: bib0125 article-title: Continuous body and hand gesture recognition for natural human-computer interaction publication-title: ACM Trans. Interact. Intell. Syst. – volume: 46 start-page: 3223 year: 2013 end-page: 3237 ident: bib0110 article-title: Discriminative fusion of shape and appearance features for human pose estimation publication-title: Pattern Recognit. – volume: 14 start-page: 229 year: 2003 end-page: 236 ident: bib0013 article-title: On the improvement of anthropometry and pose estimation from a single uncalibrated image publication-title: Mach. Vis. Appl. – year: 2016 ident: bib0074 article-title: Show me your body: gender classification from still images publication-title: Proc. 23rd IEEE International Conference on Image Processing. Phoenix, AZ – volume: 87 start-page: 1 year: 2010 end-page: 3 ident: bib0118 article-title: Guest editorial: State of the art in image-and video-based human pose and motion estimation publication-title: Int. J. Comput. Vis. – volume: 108 start-page: 52 year: 2007 end-page: 73 ident: bib0043 article-title: Vision-based hand pose estimation: a review publication-title: Comput. Vision Image Understanding – year: 2011 ident: bib0087 article-title: Visual Analysis of Humans: Looking at People – start-page: 3570 year: 2012 end-page: 3577 ident: bib0146 article-title: Parsing clothing in fashion photographs publication-title: Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition – start-page: 332 year: 2014 end-page: 347 ident: bib0079 article-title: 3D human pose estimation from monocular images with deep convolutional neural network publication-title: Proc. 12th Asian Conference on Computer Vision. Singapore – volume: 335 year: 2009 ident: bib0020 article-title: Real-time 3D body pose estimation publication-title: Multi-Camera Netw. – start-page: 1674 year: 2010 end-page: 1677 ident: bib0070 article-title: 3D human pose reconstruction using millions of exemplars publication-title: Proc. 20th IEEE International Conference on Pattern Recognition. Istanbul, Turkey – start-page: 1701 year: 2014 end-page: 1708 ident: bib0129 article-title: DeepFace: closing the gap to human-level performance in face verification publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH – volume: 22 start-page: 4286 year: 2013 end-page: 4300 ident: bib0111 article-title: A Gaussian process guided particle filter for tracking 3D human pose in video publication-title: IEEE Trans. Image Process. – start-page: 1 year: 2008 end-page: 8 ident: bib0138 article-title: Sparse probabilistic regression for activity-independent human pose inference publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK – volume: 132 start-page: 75 year: 2015 end-page: 86 ident: bib0088 article-title: Efficient tracking of human poses using a manifold hierarchy publication-title: Comput. Vision Image Understanding – reference: Wang, C., Wang, Y., Lin, Z., Yuille, A. L., Gao, W., 2014b. Source code for Robust estimation of 3D human poses from a single image. Available online at: – start-page: 623 year: 2010 end-page: 630 ident: bib0009 article-title: Monocular 3D pose estimation and tracking by detection publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, CA – start-page: 2553 year: 2013 end-page: 2561 ident: bib0128 article-title: Deep Neural Networks for Object Detection publication-title: Proc. Advances in Neural Information Processing Systems. Lake Tahoe, NV – volume: 17 start-page: 1676 year: 2011 end-page: 1689 ident: bib0031 article-title: Learning a 3D human pose distance metric from geometric pose descriptor publication-title: IEEE Trans. Visual Comput. Graphics – start-page: 1129 year: 2006 end-page: 1136 ident: bib0100 article-title: Learning to parse images of articulated bodies publication-title: Proc. Advances in Neural Information Processing Systems. Vancouver, Canada – start-page: 609 year: 2012 end-page: 623 ident: bib0032 article-title: Describing clothing by semantic attributes publication-title: Proc. 12th European Conference on Computer Vision – volume: 110 start-page: 164 year: 2015 end-page: 177 ident: bib0081 article-title: 3D Human motion tracking by exemplar-based conditional particle filter publication-title: Signal Process. – start-page: 1 year: 2008 end-page: 8 ident: bib0090 article-title: Discriminative learning of visual words for 3D human pose estimation publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK – start-page: 1799 year: 2014 end-page: 1807 ident: bib0135 article-title: Joint training of a convolutional network and a graphical model for human pose estimation publication-title: Proc. Advances in Neural Information Processing Systems. Montreal, Canada – volume: 31 start-page: 223 year: 2013 end-page: 230 ident: bib0134 article-title: Canonical locality preserving latent variable model for discriminative pose inference publication-title: Image Vision Comput. – year: 2016 ident: bib0131 article-title: Structured prediction of 3D human pose with deep neural networks publication-title: Proc. 27th British Machine Vision Conference. York, UK – year: 2016 ident: bib0166 article-title: Human pose estimation from video and publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: 73 start-page: 82 year: 1999 end-page: 98 ident: bib0049 article-title: The visual analysis of human movement: A survey publication-title: Comput. Vision Image Understanding – volume: 22 start-page: 995 year: 2011 end-page: 1008 ident: bib0063 article-title: A recognition-based motion capture baseline on the HumanEva II test data publication-title: Mach. Vis. Appl. – year: 2013 ident: bib0007 article-title: Multi-view pictorial structures for 3D human pose estimation publication-title: Proc. 24 – volume: 40 start-page: 13 year: 2010 end-page: 24 ident: bib0069 article-title: Advances in view-invariant human motion analysis: a review publication-title: IEEE Trans. Syst. Man Cybern. Part C – year: 2016 ident: bib0158 article-title: Sparseness meets deepness: 3D human pose estimation from monocular video publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV – volume: 98 start-page: 15 year: 2012 end-page: 48 ident: bib0119 article-title: Loose-limbed people: estimating 3D human pose and motion using non-parametric belief propagation publication-title: Int. J. Comput. Vis. – start-page: 467 year: 2010 end-page: 480 ident: bib0140 article-title: Deterministic 3D human pose estimation using rigid structure publication-title: Proc. 11th European Conference on Computer Vision – start-page: 361 year: 2014 end-page: 365 ident: bib0137 article-title: Viewpoint-dependent 3D human body posing for sports legacy recovery from images and video publication-title: Proc. 22nd IEEE European Signal Processing Conference. Lisbon, Portugal – start-page: 1 year: 2016 ident: bib0042 article-title: MARCOnI - ConvNet-based MARker-less motion capture in outdoor and indoor scenes publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: , arXiv preprint. – reference: Boteanu, B., Sarafianos, N., Ionescu, B., Kakadiaris, I., (2016). Synpose 300 dataset and ground truth. Available online at: – start-page: 1321 year: 2011 end-page: 1328 ident: bib0036 article-title: Tracking 3D human pose with large root node uncertainty publication-title: Proc. 24th IEEE Conference on Computer Vision and Pattern Recognition. Colorado Springs, CO – start-page: 669 year: 2000 end-page: 676 ident: bib0012 article-title: Estimating anthropometry and pose from a single image publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head Island, SC – volume: 96 start-page: 103 year: 2012 end-page: 124 ident: bib0060 article-title: Multi-view 3D human pose estimation in complex environment publication-title: Int. J. Comput. Vis. – year: 2015 ident: bib0155 publication-title: Source code for 3D shape reconstruction from 2D landmarks: a convex formulation. – volume: 116 start-page: 330 year: 2012 end-page: 346 ident: bib0035 article-title: Estimating pose of articulated objects using low-level motion publication-title: Comput. Vision Image Understanding – start-page: 1194 year: 2012 end-page: 1201 ident: bib0103 article-title: A database for fine grained activity detection of cooking activities publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Providence, Rhode Island – start-page: 484 year: 2009 end-page: 491 ident: bib0108 article-title: Context-based appearance descriptor for 3D human pose estimation from monocular images publication-title: Proc. IEEE Digital Image Computing: Techniques and Applications. Melbourne, VIC – start-page: 1746 year: 2009 end-page: 1753 ident: bib0048 article-title: Motion capture using joint skeleton tracking and surface estimation publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Miami Beach, FL – start-page: 573 year: 2012 end-page: 586 ident: bib0099 article-title: Reconstructing 3D human pose from 2D image landmarks publication-title: Proc. 12th European Conference on Computer Vision – volume: 67 start-page: 251 year: 2006 end-page: 276 ident: bib0104 article-title: Combining generative and discriminative models in a framework for articulated pose estimation publication-title: Int. J. Comput. Vis. – start-page: 2361 year: 2014 end-page: 2368 ident: bib0143 article-title: Robust estimation of 3D human poses from a single image publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH – volume: 8 start-page: 3 year: 2007 end-page: 23 ident: bib0021 article-title: Generative or discriminative? Getting the best of both worlds publication-title: Bayesian Stat. – start-page: 132 year: 2008 end-page: 143 ident: bib0040 article-title: Gaussian process latent variable models for human pose estimation publication-title: Machine Learning for Multimodal Interaction – year: 2016 ident: bib0163 article-title: Sparse Representation for publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – start-page: 5659 year: 2015 end-page: 5670 ident: bib0062 article-title: Multimodal deep autoencoder for human pose recovery publication-title: IEEE Trans. Image Process. – volume: 36 start-page: 1325 year: 2014 end-page: 1339 ident: bib0067 article-title: Human3.6m: large scale datasets and predictive methods for 3D human sensing in natural environments publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 188 year: 2013 end-page: 206 ident: bib0056 article-title: Full-body human motion capture from monocular depth images publication-title: Time-of-Flight and Depth Imaging. Sensors, Algorithms, and Applications – start-page: 48 year: 2009 end-page: 60 ident: bib0065 article-title: Estimating human pose from occluded images publication-title: Proc. Ninth Asian Conference on Computer Vision – Volume Part I – start-page: 418 year: 2015 end-page: 431 ident: bib0096 article-title: Game experience when controlling a weak avatar in full-body enaction publication-title: Proc. Intelligent Virtual Agents – start-page: 3618 year: 2013 end-page: 3625 ident: bib0028 article-title: 3D pictorial structures for multiple view articulated pose estimation publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Portland, Oregon – reference: Carnegie Mellon University Graphics Lab. MoCap: motion capture database. (available online at – volume: 3 start-page: 313 year: 2011 end-page: 332 ident: bib0085 article-title: Human body pose interpretation and classification for social human-robot interaction publication-title: Int. J. Soc. Rob. – volume: 35 start-page: 1798 year: 2013 end-page: 1828 ident: bib0018 article-title: Representation learning: a review and new perspectives publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1249 year: 2011 end-page: 1256 ident: bib0082 article-title: Markerless motion capture of interacting characters using multi-view image segmentation publication-title: Proc. 24th IEEE Conference on Computer Vision and Pattern Recognition. Colorado Springs, CO – reference: Jiang, H., Grauman, K., 2016. Seeing invisible poses: Estimating 3D body pose from egocentric video. – year: 2016 ident: bib0157 publication-title: Source code for Sparseness meets deepness: 3D human pose estimation from monocular video. – volume: 42 start-page: 2907 year: 2009 end-page: 2921 ident: bib0101 article-title: Action-specific motion prior for efficient bayesian 3D human body tracking publication-title: Pattern Recognit. – start-page: 642 year: 2006 end-page: 655 ident: bib0027 article-title: POSECUT: simultaneous segmentation and 3D pose estimation of humans using dynamic graph-cuts publication-title: Proc. 9th European Conference on Computer Vision. Graz, Austria – start-page: 149 year: 2013 end-page: 187 ident: bib0152 article-title: A survey on human motion analysis from depth data publication-title: Time-of-Flight and Depth Imaging. Sensors, Algorithms, and Applications – start-page: 2848 year: 2015 end-page: 2856 ident: bib0080 article-title: Maximum-margin structured learning with deep networks for 3D human pose estimation publication-title: Proc. IEEE International Conference on Computer Vision. Santiago, Chile – volume: 87 start-page: 28 year: 2010 end-page: 52 ident: bib0024 article-title: Twin gaussian processes for structured prediction publication-title: Int. J. Comput. Vis. – start-page: II year: 2004 end-page: 882 ident: bib0003 article-title: 3D human pose from silhouettes by relevance vector regression publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Vol. 2. Washington, DC – start-page: 253 year: 2014 end-page: 264 ident: bib0008 article-title: Test-time adaptation for 3D human pose estimation publication-title: Pattern Recognition – start-page: 394 year: 2015 end-page: 397 ident: bib0122 article-title: Lie algebra-based kinematic prior for 3D human pose tracking publication-title: Proc. International Conference on Machine Vision Applications. Tokyo Japan – volume: 22 start-page: 1453 year: 2000 end-page: 1459 ident: bib0073 article-title: Model-based estimation of 3D human motion publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1089 year: 2009 end-page: 1096 ident: bib0133 article-title: The TUM kitchen data set of everyday manipulation activities for motion tracking and action recognition publication-title: Proc. IEEE 12th International Conference on Computer Vision Workshops. Kyoto – year: 2016 ident: bib0151 article-title: A dual-source approach for 3D pose estimation from a single image publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV – volume: 38(8) start-page: 1505 year: 2016 end-page: 1516 ident: bib0167 article-title: Reconstruction of human motion from monocular image sequences publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – start-page: 647 year: 2010 end-page: 654 ident: bib0106 article-title: Combining discriminative and generative methods for 3D deformable surface and articulated pose reconstruction publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, CA – year: 2013 ident: bib0075 article-title: Multiview body part recognition with random forests publication-title: Proc. 24th British Machine Vision Conference. Bristol, United Kingdom – start-page: 1048 year: 2013 end-page: 1054 ident: bib0044 article-title: Athlete pose estimation from monocular TV sports footage publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition Workshops. Portland, Oregon – start-page: 2345 year: 2014 end-page: 2352 ident: bib0094 article-title: Posebits for monocular human pose estimation publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH – reference: Bo, L., Sminchisescu, C., (2010b). Source code for Twin gaussian processes for structured prediction. Available online at: – start-page: 1 year: 2015 end-page: 8 ident: bib0141 article-title: 3D human motion capture from monocular image sequences publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition Workshops – start-page: 1 year: 2011 end-page: 6 ident: bib0052 article-title: Monocular 3D human pose estimation by classification publication-title: Proc. IEEE International Conference on Multimedia and Expo. Barcelona, Spain – reference: Valmadre, J., Lucey, S., (2010b). Source code for Deterministic 3D human pose estimation using rigid structure. Available online at: – volume: 30 start-page: 493 year: 2008 end-page: 506 ident: bib0054 article-title: Constraint integration for efficient multiview pose estimation with self-occlusions publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 9 year: 2010 end-page: 14 ident: bib0089 article-title: Human pose estimation with implicit shape models publication-title: Proc. 1st ACM International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams – start-page: 362 year: 2014 end-page: 370 ident: bib0114 article-title: Human pose estimation publication-title: Compu. Vision – start-page: 3522 year: 2012 end-page: 3529 ident: bib0147 article-title: Recognizing proxemics in personal photos publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Providence, Rhode Island – start-page: 3537 year: 2015 end-page: 3546 ident: bib0159 article-title: The stitched puppet: A graphical model of 3D human shape and pose publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Boston, Massachusetts – volume: 43 start-page: 1347 year: 2013 end-page: 1356 ident: bib0011 article-title: Tensor body: real-time reconstruction of the human body and avatar synthesis from RGB-D publication-title: IEEE Trans. Cybern. – start-page: 1243 year: 2011 end-page: 1250 ident: bib0165 article-title: Outdoor Human Motion Capture using Inverse Kinematics and von publication-title: Proc. IEEE International Conference on Computer Vision – start-page: 1289 year: 2013 end-page: 1296 ident: bib0084 article-title: Pictorial human spaces: how well do humans perceive a 3D articulated pose? publication-title: Proc. IEEE International Conference on Computer Vision. Sydney, Australia – start-page: 387 year: 2013 end-page: 396 ident: bib0153 article-title: Bodyavatar: creating freeform 3D avatars using first-person body gestures publication-title: Proc. 26th annual ACM symposium on user interface software and technology – start-page: 3634 year: 2013 end-page: 3641 ident: bib0120 article-title: A joint model for 2D and 3D pose estimation from a single image publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Portland, Oregon – start-page: 4447 year: 2015 end-page: 4455 ident: bib0156 article-title: 3D shape estimation from 2D landmarks: a convex relaxation approach publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA – year: 2016 ident: bib0033 article-title: Synthesizing training images for boosting human 3D pose estimation publication-title: arXiv preprint arXiv:1604.02703 – volume: 6 start-page: 538 year: 2012 end-page: 552 ident: bib0061 article-title: Human pose estimation and activity recognition from multi-view videos: comparative explorations of recent developments publication-title: IEEE J. Sel. Top. Signal Process. – start-page: 157 year: 2011 end-page: 167 ident: bib0038 article-title: 3D body pose estimation using an adaptive person model for articulated ICP publication-title: Intelligent Robotics and Applications – start-page: 1359 year: 2011 end-page: 1367 ident: bib0149 article-title: Learning probabilistic non-linear latent variable models for tracking complex activities publication-title: Proc. Advances in Neural Information Processing Systems. Granada, Spain – start-page: 631 year: 2010 end-page: 638 ident: bib0130 article-title: Dynamical binary latent variable models for 3D human pose tracking publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA – start-page: 674 year: 2012 end-page: 687 ident: bib0145 article-title: No bias left behind: covariate shift adaptation for discriminative 3D pose estimation publication-title: Proc. 12th European Conference on Computer Vision – volume: 18 start-page: 1527 year: 2006 end-page: 1554 ident: bib0057 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Comput. – reference: Blender Foundation, (2002). Blender open source 3D creation suite. Available online at – start-page: I year: 2004 end-page: 421–I–428 ident: bib0116 article-title: Tracking loose-limbed people publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Vol. 1. Washington, DC – start-page: 1669 year: 2014 end-page: 1676 ident: bib0014 article-title: 3D pictorial structures for multiple human pose estimation publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH – start-page: 1806 year: 2011 end-page: 1819 ident: bib0019 article-title: Multiple object tracking using k-shortest paths optimization publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1 year: 2008 end-page: 8 ident: bib0047 article-title: Progressive search space reduction for human pose estimation publication-title: Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition – start-page: 3546 year: 2012 end-page: 3553 ident: bib0160 article-title: From pictorial structures to deformable structures publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Providence, Rhode Island – start-page: 185 year: 2006 end-page: 195 ident: bib0117 article-title: Predicting 3D people from 2D pictures publication-title: Articulated Motion and Deformable Objects – volume: 28 start-page: 44 year: 2006 end-page: 58 ident: bib0004 article-title: Recovering 3D human pose from monocular images publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 113 start-page: 163 year: 2015 end-page: 175 ident: bib0161 article-title: Metric regression forests for correspondence estimation publication-title: Int. J. Comput. Vision – start-page: 2220 year: 2011 end-page: 2227 ident: bib0066 article-title: Latent structured models for human pose estimation publication-title: Proc. 13th IEEE International Conference on Computer Vision. Barcelona, Spain – volume: 104 start-page: 90 year: 2006 end-page: 126 ident: bib0086 article-title: A survey of advances in vision-based human motion capture and analysis publication-title: Comput. Vision Image Understanding – reference: Rogez, G., Schmid, C., 2016. Mocap-guided data augmentation for 3D pose estimation in the wild. – reference: Ramakrishna, V., Kanade, T., Sheikh, Y., 2012b. Source code for Reconstructing 3D human pose from 2D image landmarks. Available online at: – start-page: 247 year: 2011 end-page: 248 ident: bib0127 article-title: Faast: the flexible action and articulated skeleton toolkit publication-title: IEEE Conference on Virtual Reality, Singapore – volume: 313 start-page: 504 year: 2006 end-page: 507 ident: bib0058 article-title: Reducing the dimensionality of data with neural networks publication-title: Science – start-page: 260 year: 2012 end-page: 272 ident: bib0010 article-title: Human context: modeling human-human interactions for monocular 3D pose estimation publication-title: Articulated Motion and Deformable Objects – start-page: 588 year: 2013 end-page: 595 ident: bib0093 article-title: Poselet conditioned pictorial structures publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Portland, Oregon – year: 2013 ident: bib0162 article-title: Metric regression forests for human pose estimation publication-title: Proc. 24 – year: 2002 ident: bib0123 publication-title: Estimation Algorithms for Ambiguous Visual Models. Three-Dimensional Human Modeling and Motion Reconstruction in Monocular Video Sequences – start-page: 1446 year: 2015 end-page: 1455 ident: bib0006 article-title: Pose-conditioned joint angle limits for 3D human pose reconstruction publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Boston, Massachusetts – volume: 87 start-page: 53 year: 2010 end-page: 74 ident: bib0092 article-title: A study on smoothing for particle-filtered 3D human body tracking publication-title: Int. J. Comput. Vis. – year: 2014 ident: bib0076 article-title: Depth sweep regression forests for estimating 3D human pose from images publication-title: Proc. British Machine Vision Conference. Nottingham, United Kingdom – start-page: 140 year: 2015 end-page: 147 ident: bib0107 article-title: 3D pictorial structures for human pose estimation with supervoxels publication-title: Proc. IEEE Winter Conference on Applications of Computer Vision. Waikoloa, HI – start-page: 1736 year: 2014 end-page: 1744 ident: bib0034 article-title: Articulated pose estimation by a graphical model with image dependent pairwise relations publication-title: Proc. Advances in Neural Information Processing Systems. Montreal, Canada – year: 2016 ident: bib0150 publication-title: Source code for a dual-source approach for 3D pose estimation from a single image. – reference: Huang, J.-B., Yang, M.-H., (2009b). Source code for Estimating human pose from occluded images. Available online at: – start-page: 1653 year: 2016 end-page: 1660 ident: bib0029 article-title: Personalizing human video pose estimation publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV – start-page: 1264 year: 2011 end-page: 1269 ident: bib0002 article-title: Umpm benchmark: a multi-person dataset with synchronized video and motion capture data for evaluation of articulated human motion and interaction publication-title: Proc. IEEE International Conference on Computer Vision Workshops, Barcelona Spain – start-page: 1961 year: 2011 end-page: 1968 ident: bib0055 article-title: From 3D scene geometry to human workspace publication-title: Proc. 24th IEEE Conference on Computer Vision and Pattern Recognition. Colorado Springs, CO – volume: 108 start-page: 4 year: 2007 end-page: 18 ident: bib0095 article-title: Vision-based human motion analysis: an overview publication-title: Comput. Vision Image Understanding – start-page: 1 year: 2015 end-page: 14 ident: bib0154 article-title: Ergonomics-inspired reshaping and exploration of collections of models publication-title: IEEE Trans. Visual Comput. Graphics – volume: 99 start-page: 190 year: 2012 end-page: 214 ident: bib0039 article-title: 2D Articulated human pose estimation and retrieval in (almost) unconstrained still images publication-title: Int. J. Comput. Vis. – reference: . – start-page: 185 year: 2008 end-page: 211 ident: bib0124 article-title: 3D human motion analysis in monocular video: techniques and challenges publication-title: Human Motion – volume: 83 start-page: 121 year: 2009 end-page: 134 ident: bib0068 article-title: Learning generative models for multi-activity body pose estimation publication-title: Int. J. Comput. Vis. – volume: 32 start-page: 1627 year: 2010 end-page: 1645 ident: bib0046 article-title: Object detection with discriminatively trained part-based models publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 2673 year: 2012 end-page: 2680 ident: bib0121 article-title: Single image 3D human pose estimation from noisy observations publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Providence, Rhode Island – volume: 2 start-page: 1 year: 2009 end-page: 127 ident: bib0017 article-title: Learning deep architectures for AI publication-title: Found. Trends Mach. Learn. – start-page: 1653 year: 2014 end-page: 1660 ident: bib0136 article-title: DeepPose: Human pose estimation via deep neural networks publication-title: Proc. IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH – start-page: 674 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0145 article-title: No bias left behind: covariate shift adaptation for discriminative 3D pose estimation – start-page: 434 year: 2008 ident: 10.1016/j.cviu.2016.09.002_bib0091 article-title: Relevant feature selection for human pose estimation and localization in cluttered images – start-page: 1653 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0136 article-title: DeepPose: Human pose estimation via deep neural networks – start-page: 188 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0056 article-title: Full-body human motion capture from monocular depth images – volume: 83 start-page: 121 issue: 2 year: 2009 ident: 10.1016/j.cviu.2016.09.002_bib0068 article-title: Learning generative models for multi-activity body pose estimation publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-008-0158-0 – start-page: 1089 year: 2009 ident: 10.1016/j.cviu.2016.09.002_bib0133 article-title: The TUM kitchen data set of everyday manipulation activities for motion tracking and action recognition – volume: 22 start-page: 995 issue: 6 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0063 article-title: A recognition-based motion capture baseline on the HumanEva II test data publication-title: Mach. Vis. Appl. doi: 10.1007/s00138-011-0344-x – volume: 42 start-page: 2907 issue: 11 year: 2009 ident: 10.1016/j.cviu.2016.09.002_bib0101 article-title: Action-specific motion prior for efficient bayesian 3D human body tracking publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2009.02.012 – volume: 28 start-page: 44 issue: 1 year: 2006 ident: 10.1016/j.cviu.2016.09.002_bib0004 article-title: Recovering 3D human pose from monocular images publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2006.21 – start-page: 149 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0152 article-title: A survey on human motion analysis from depth data – start-page: 1961 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0055 article-title: From 3D scene geometry to human workspace – start-page: 1674 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0070 article-title: 3D human pose reconstruction using millions of exemplars – start-page: 2361 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0143 article-title: Robust estimation of 3D human poses from a single image – volume: 31 start-page: 223 issue: 3 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0134 article-title: Canonical locality preserving latent variable model for discriminative pose inference publication-title: Image Vision Comput. doi: 10.1016/j.imavis.2012.06.009 – start-page: 1446 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0006 article-title: Pose-conditioned joint angle limits for 3D human pose reconstruction – start-page: 1321 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0036 article-title: Tracking 3D human pose with large root node uncertainty – start-page: 1 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0052 article-title: Monocular 3D human pose estimation by classification – start-page: 588 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0093 article-title: Poselet conditioned pictorial structures – start-page: 247 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0127 article-title: Faast: the flexible action and articulated skeleton toolkit – year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0074 article-title: Show me your body: gender classification from still images – start-page: 361 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0137 article-title: Viewpoint-dependent 3D human body posing for sports legacy recovery from images and video – start-page: 2345 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0094 article-title: Posebits for monocular human pose estimation – start-page: 157 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0038 article-title: 3D body pose estimation using an adaptive person model for articulated ICP – volume: 99 start-page: 190 issue: 2 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0039 article-title: 2D Articulated human pose estimation and retrieval in (almost) unconstrained still images publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-012-0524-9 – volume: 6 start-page: 538 issue: 5 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0061 article-title: Human pose estimation and activity recognition from multi-view videos: comparative explorations of recent developments publication-title: IEEE J. Sel. Top. Signal Process. doi: 10.1109/JSTSP.2012.2196975 – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0078 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – start-page: 631 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0130 article-title: Dynamical binary latent variable models for 3D human pose tracking – volume: 22 start-page: 1453 issue: 12 year: 2000 ident: 10.1016/j.cviu.2016.09.002_bib0073 article-title: Model-based estimation of 3D human motion publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/34.895978 – volume: 132 start-page: 75 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0088 article-title: Efficient tracking of human poses using a manifold hierarchy publication-title: Comput. Vision Image Understanding doi: 10.1016/j.cviu.2014.10.005 – start-page: 3634 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0120 article-title: A joint model for 2D and 3D pose estimation from a single image – volume: 115 start-page: 290 issue: 3 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0030 article-title: 3D Human pose recovery from image by efficient visual feature selection publication-title: Comput. Vision Image Understanding doi: 10.1016/j.cviu.2010.11.007 – start-page: 1669 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0014 article-title: 3D pictorial structures for multiple human pose estimation – start-page: 1129 year: 2006 ident: 10.1016/j.cviu.2016.09.002_bib0100 article-title: Learning to parse images of articulated bodies – year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0157 publication-title: Source code for Sparseness meets deepness: 3D human pose estimation from monocular video. – start-page: 484 year: 2009 ident: 10.1016/j.cviu.2016.09.002_bib0108 article-title: Context-based appearance descriptor for 3D human pose estimation from monocular images – start-page: 253 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0008 article-title: Test-time adaptation for 3D human pose estimation – year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0162 article-title: Metric regression forests for human pose estimation – start-page: 1243 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0165 article-title: Outdoor Human Motion Capture using Inverse Kinematics and von Mises-Fisher Sampling, Barcelona, Spain – start-page: 1 year: 2008 ident: 10.1016/j.cviu.2016.09.002_bib0090 article-title: Discriminative learning of visual words for 3D human pose estimation – ident: 10.1016/j.cviu.2016.09.002_bib0105 – start-page: 5659 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0062 article-title: Multimodal deep autoencoder for human pose recovery publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2015.2487860 – start-page: 1048 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0044 article-title: Athlete pose estimation from monocular TV sports footage – start-page: 185 year: 2008 ident: 10.1016/j.cviu.2016.09.002_bib0124 article-title: 3D human motion analysis in monocular video: techniques and challenges – start-page: 48 year: 2009 ident: 10.1016/j.cviu.2016.09.002_bib0065 article-title: Estimating human pose from occluded images – year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0076 article-title: Depth sweep regression forests for estimating 3D human pose from images – start-page: 1289 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0084 article-title: Pictorial human spaces: how well do humans perceive a 3D articulated pose? – start-page: 140 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0107 article-title: 3D pictorial structures for human pose estimation with supervoxels – year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0151 article-title: A dual-source approach for 3D pose estimation from a single image – year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0158 article-title: Sparseness meets deepness: 3D human pose estimation from monocular video – ident: 10.1016/j.cviu.2016.09.002_bib0023 – start-page: 90 year: 1997 ident: 10.1016/j.cviu.2016.09.002_bib0005 article-title: Human motion analysis: a review – ident: 10.1016/j.cviu.2016.09.002_bib0083 – volume: 87 start-page: 53 issue: 1–2 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0092 article-title: A study on smoothing for particle-filtered 3D human body tracking publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-009-0205-5 – volume: 35 start-page: 2821 issue: 12 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0112 article-title: Efficient human pose estimation from single depth images publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2012.241 – volume: 96 start-page: 103 issue: 1 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0060 article-title: Multi-view 3D human pose estimation in complex environment publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-011-0451-1 – volume: 36 start-page: 1325 issue: 7 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0067 article-title: Human3.6m: large scale datasets and predictive methods for 3D human sensing in natural environments publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2013.248 – start-page: 51.1 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0109 article-title: Localized fusion of shape and appearance features for 3D human pose estimation – start-page: 1264 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0002 article-title: Umpm benchmark: a multi-person dataset with synchronized video and motion capture data for evaluation of articulated human motion and interaction – year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0087 – ident: 10.1016/j.cviu.2016.09.002_bib0098 doi: 10.1007/978-3-642-33765-9_41 – start-page: 1194 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0103 article-title: A database for fine grained activity detection of cooking activities – start-page: 3810 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0041 article-title: Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras – start-page: 418 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0096 article-title: Game experience when controlling a weak avatar in full-body enaction – start-page: 1 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0154 article-title: Ergonomics-inspired reshaping and exploration of collections of models publication-title: IEEE Trans. Visual Comput. Graphics – volume: 17 start-page: 1676 issue: 11 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0031 article-title: Learning a 3D human pose distance metric from geometric pose descriptor publication-title: IEEE Trans. Visual Comput. Graphics doi: 10.1109/TVCG.2010.272 – start-page: 12.1 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0072 article-title: Clustered pose and nonlinear appearance models for human pose estimation – year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0150 publication-title: Source code for a dual-source approach for 3D pose estimation from a single image. – start-page: 1 year: 2008 ident: 10.1016/j.cviu.2016.09.002_bib0047 article-title: Progressive search space reduction for human pose estimation – start-page: 2220 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0066 article-title: Latent structured models for human pose estimation – start-page: 573 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0099 article-title: Reconstructing 3D human pose from 2D image landmarks – start-page: 3342 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0050 article-title: Articulated pose estimation using discriminative armlet classifiers – start-page: I year: 2004 ident: 10.1016/j.cviu.2016.09.002_bib0116 article-title: Tracking loose-limbed people – volume: 43 start-page: 1347 issue: 5 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0011 article-title: Tensor body: real-time reconstruction of the human body and avatar synthesis from RGB-D publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2013.2276430 – year: 2002 ident: 10.1016/j.cviu.2016.09.002_bib0123 – volume: 61 start-page: 55 issue: 1 year: 2005 ident: 10.1016/j.cviu.2016.09.002_bib0045 article-title: Pictorial structures for object recognition publication-title: Int. J. Comput. Vis. doi: 10.1023/B:VISI.0000042934.15159.49 – start-page: 1 year: 2008 ident: 10.1016/j.cviu.2016.09.002_bib0138 article-title: Sparse probabilistic regression for activity-independent human pose inference – start-page: 1 issue: 99 year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0042 article-title: MARCOnI - ConvNet-based MARker-less motion capture in outdoor and indoor scenes publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2016.2557779 – start-page: 742 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0016 article-title: Multiple human pose estimation with temporally consistent 3D pictorial structures – volume: 40 start-page: 13 issue: 1 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0069 article-title: Advances in view-invariant human motion analysis: a review publication-title: IEEE Trans. Syst. Man Cybern. Part C doi: 10.1109/TSMCC.2009.2027608 – start-page: 332 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0079 article-title: 3D human pose estimation from monocular images with deep convolutional neural network – start-page: 1359 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0149 article-title: Learning probabilistic non-linear latent variable models for tracking complex activities – start-page: 260 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0010 article-title: Human context: modeling human-human interactions for monocular 3D pose estimation – start-page: 2553 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0128 article-title: Deep Neural Networks for Object Detection – volume: 87 start-page: 28 issue: 1–2 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0024 article-title: Twin gaussian processes for structured prediction publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-008-0204-y – volume: 73 start-page: 82 issue: 1 year: 1999 ident: 10.1016/j.cviu.2016.09.002_bib0049 article-title: The visual analysis of human movement: A survey publication-title: Comput. Vision Image Understanding doi: 10.1006/cviu.1998.0716 – start-page: 1888 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0097 article-title: Monocular image 3D human pose estimation under self-occlusion – start-page: 609 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0032 article-title: Describing clothing by semantic attributes – start-page: 3522 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0147 article-title: Recognizing proxemics in personal photos – start-page: 642 year: 2006 ident: 10.1016/j.cviu.2016.09.002_bib0027 article-title: POSECUT: simultaneous segmentation and 3D pose estimation of humans using dynamic graph-cuts – ident: 10.1016/j.cviu.2016.09.002_bib0064 doi: 10.1007/978-3-642-12307-8_5 – start-page: 1806 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0019 article-title: Multiple object tracking using k-shortest paths optimization publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2011.21 – year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0033 article-title: Synthesizing training images for boosting human 3D pose estimation publication-title: arXiv preprint arXiv:1604.02703 – start-page: II year: 2004 ident: 10.1016/j.cviu.2016.09.002_bib0003 article-title: 3D human pose from silhouettes by relevance vector regression – year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0075 article-title: Multiview body part recognition with random forests – start-page: 3570 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0146 article-title: Parsing clothing in fashion photographs – start-page: 3618 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0028 article-title: 3D pictorial structures for multiple view articulated pose estimation – start-page: 1701 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0129 article-title: DeepFace: closing the gap to human-level performance in face verification – volume: 335 issue: 2 year: 2009 ident: 10.1016/j.cviu.2016.09.002_bib0020 article-title: Real-time 3D body pose estimation publication-title: Multi-Camera Netw. doi: 10.1016/B978-0-12-374633-7.00016-1 – volume: 67 start-page: 251 issue: 3 year: 2006 ident: 10.1016/j.cviu.2016.09.002_bib0104 article-title: Combining generative and discriminative models in a framework for articulated pose estimation publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-006-5165-4 – ident: 10.1016/j.cviu.2016.09.002_bib0001 – start-page: 2214 year: 2009 ident: 10.1016/j.cviu.2016.09.002_bib0059 article-title: Multi-view 3D human pose estimation combining single-frame recovery, temporal integration and model adaptation – volume: 110 start-page: 164 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0081 article-title: 3D Human motion tracking by exemplar-based conditional particle filter publication-title: Signal Process. doi: 10.1016/j.sigpro.2014.08.028 – year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0007 article-title: Multi-view pictorial structures for 3D human pose estimation – year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0131 article-title: Structured prediction of 3D human pose with deep neural networks – volume: 2 start-page: 1 issue: 1 year: 2009 ident: 10.1016/j.cviu.2016.09.002_bib0017 article-title: Learning deep architectures for AI publication-title: Found. Trends Mach. Learn. doi: 10.1561/2200000006 – start-page: 1097 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0077 article-title: Imagenet classification with deep convolutional neural networks – start-page: 1746 year: 2009 ident: 10.1016/j.cviu.2016.09.002_bib0048 article-title: Motion capture using joint skeleton tracking and surface estimation – start-page: 951 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0126 article-title: Fast articulated motion tracking using a sums of gaussians body model – start-page: 4447 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0156 article-title: 3D shape estimation from 2D landmarks: a convex relaxation approach – start-page: 470 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0026 article-title: Generative 2D and 3D human pose estimation with vote distributions – volume: 46 start-page: 3223 issue: 12 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0110 article-title: Discriminative fusion of shape and appearance features for human pose estimation publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2013.05.019 – start-page: 185 year: 2006 ident: 10.1016/j.cviu.2016.09.002_bib0117 article-title: Predicting 3D people from 2D pictures – volume: 98 start-page: 15 issue: 1 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0119 article-title: Loose-limbed people: estimating 3D human pose and motion using non-parametric belief propagation publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-011-0493-4 – start-page: 1736 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0034 article-title: Articulated pose estimation by a graphical model with image dependent pairwise relations – volume: 108 start-page: 52 issue: 1 year: 2007 ident: 10.1016/j.cviu.2016.09.002_bib0043 article-title: Vision-based hand pose estimation: a review publication-title: Comput. Vision Image Understanding doi: 10.1016/j.cviu.2006.10.012 – year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0163 article-title: Sparse Representation for 3D shape estimation: A convex relaxation approach – start-page: 623 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0009 article-title: Monocular 3D pose estimation and tracking by detection – start-page: 362 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0114 article-title: Human pose estimation publication-title: Compu. Vision doi: 10.1007/978-0-387-31439-6_584 – volume: 3 start-page: 313 issue: 3 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0085 article-title: Human body pose interpretation and classification for social human-robot interaction publication-title: Int. J. Soc. Rob. doi: 10.1007/s12369-011-0099-6 – start-page: 394 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0122 article-title: Lie algebra-based kinematic prior for 3D human pose tracking – start-page: 467 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0140 article-title: Deterministic 3D human pose estimation using rigid structure – volume: 116 start-page: 330 issue: 3 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0035 article-title: Estimating pose of articulated objects using low-level motion publication-title: Comput. Vision Image Understanding doi: 10.1016/j.cviu.2011.08.007 – ident: 10.1016/j.cviu.2016.09.002_bib0142 doi: 10.1109/CVPR.2014.303 – year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0132 article-title: Direct prediction of 3D body poses from motion compensated sequences – volume: 2 start-page: 5 issue: 1 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0125 article-title: Continuous body and hand gesture recognition for natural human-computer interaction publication-title: ACM Trans. Interact. Intell. Syst. doi: 10.1145/2133366.2133371 – volume: 7 start-page: 197 issue: 3–4 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0037 article-title: Deep learning: methods and applications publication-title: Found. Trends Signal Process. doi: 10.1561/2000000039 – start-page: 387 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0153 article-title: Bodyavatar: creating freeform 3D avatars using first-person body gestures – start-page: 1 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0141 article-title: 3D human motion capture from monocular image sequences – volume: 30 start-page: 493 issue: 3 year: 2008 ident: 10.1016/j.cviu.2016.09.002_bib0054 article-title: Constraint integration for efficient multiview pose estimation with self-occlusions publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2007.1173 – volume: 38(8) start-page: 1505 year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0167 article-title: 3D Reconstruction of human motion from monocular image sequences – start-page: 9 year: 2009 ident: 10.1016/j.cviu.2016.09.002_bib0053 article-title: Discriminative 3D human pose estimation from monocular images via topological preserving hierarchical affinity clustering – start-page: 663 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0164 article-title: Multisensor-fusion for 3D full-body human motion capture – start-page: 1385 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0148 article-title: Articulated pose estimation with flexible mixtures-of-parts – volume: 32 start-page: 1627 issue: 9 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0046 article-title: Object detection with discriminatively trained part-based models publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2009.167 – volume: 104 start-page: 90 issue: 2 year: 2006 ident: 10.1016/j.cviu.2016.09.002_bib0086 article-title: A survey of advances in vision-based human motion capture and analysis publication-title: Comput. Vision Image Understanding doi: 10.1016/j.cviu.2006.08.002 – start-page: 3546 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0160 article-title: From pictorial structures to deformable structures – ident: 10.1016/j.cviu.2016.09.002_bib0071 doi: 10.1109/CVPR.2017.373 – start-page: 2673 year: 2012 ident: 10.1016/j.cviu.2016.09.002_bib0121 article-title: Single image 3D human pose estimation from noisy observations – ident: 10.1016/j.cviu.2016.09.002_bib0022 – volume: 14 start-page: 229 issue: 4 year: 2003 ident: 10.1016/j.cviu.2016.09.002_bib0013 article-title: On the improvement of anthropometry and pose estimation from a single uncalibrated image publication-title: Mach. Vis. Appl. doi: 10.1007/s00138-002-0088-8 – ident: 10.1016/j.cviu.2016.09.002_bib0102 – volume: 313 start-page: 504 issue: 5786 year: 2006 ident: 10.1016/j.cviu.2016.09.002_bib0058 article-title: Reducing the dimensionality of data with neural networks publication-title: Science doi: 10.1126/science.1127647 – volume: 22 start-page: 4286 issue: 11 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0111 article-title: A Gaussian process guided particle filter for tracking 3D human pose in video publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2013.2271850 – volume: 87 start-page: 1 issue: 1 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0118 article-title: Guest editorial: State of the art in image-and video-based human pose and motion estimation publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-009-0293-2 – start-page: 1249 year: 2011 ident: 10.1016/j.cviu.2016.09.002_bib0082 article-title: Markerless motion capture of interacting characters using multi-view image segmentation – ident: 10.1016/j.cviu.2016.09.002_bib0139 doi: 10.1007/978-3-642-15558-1_34 – start-page: 3537 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0159 article-title: The stitched puppet: A graphical model of 3D human shape and pose – issue: 99 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0015 article-title: 3D Pictorial structures revisited: multiple human pose estimation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1873 year: 2009 ident: 10.1016/j.cviu.2016.09.002_bib0144 article-title: Modeling 3D human poses from uncalibrated monocular images – start-page: 641 year: 2003 ident: 10.1016/j.cviu.2016.09.002_bib0051 article-title: Inferring 3D structure with a statistical image-based shape model – start-page: 9 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0089 article-title: Human pose estimation with implicit shape models – year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0155 publication-title: Source code for 3D shape reconstruction from 2D landmarks: a convex formulation. – start-page: 132 year: 2008 ident: 10.1016/j.cviu.2016.09.002_bib0040 article-title: Gaussian process latent variable models for human pose estimation – start-page: 669 year: 2000 ident: 10.1016/j.cviu.2016.09.002_bib0012 article-title: Estimating anthropometry and pose from a single image – start-page: 2848 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0080 article-title: Maximum-margin structured learning with deep networks for 3D human pose estimation – volume: 56 start-page: 116 issue: 1 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0113 article-title: Real-time human pose recognition in parts from single depth images publication-title: Commun. ACM doi: 10.1145/2398356.2398381 – volume: 18 start-page: 1527 issue: 7 year: 2006 ident: 10.1016/j.cviu.2016.09.002_bib0057 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Comput. doi: 10.1162/neco.2006.18.7.1527 – volume: 113 start-page: 163 issue: 3 year: 2015 ident: 10.1016/j.cviu.2016.09.002_bib0161 article-title: Metric regression forests for correspondence estimation publication-title: Int. J. Comput. Vision doi: 10.1007/s11263-015-0818-9 – volume: 108 start-page: 4 issue: 1 year: 2007 ident: 10.1016/j.cviu.2016.09.002_bib0095 article-title: Vision-based human motion analysis: an overview publication-title: Comput. Vision Image Understanding doi: 10.1016/j.cviu.2006.10.016 – volume: 8 start-page: 3 year: 2007 ident: 10.1016/j.cviu.2016.09.002_bib0021 article-title: Generative or discriminative? Getting the best of both worlds publication-title: Bayesian Stat. – start-page: 1653 year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0029 article-title: Personalizing human video pose estimation – volume: 87 start-page: 4 issue: 1–2 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0115 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 – year: 2016 ident: 10.1016/j.cviu.2016.09.002_bib0166 article-title: Human pose estimation from video and IMUs – start-page: 1799 year: 2014 ident: 10.1016/j.cviu.2016.09.002_bib0135 article-title: Joint training of a convolutional network and a graphical model for human pose estimation – volume: 35 start-page: 1798 issue: 8 year: 2013 ident: 10.1016/j.cviu.2016.09.002_bib0018 article-title: Representation learning: a review and new perspectives publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2013.50 – start-page: 647 year: 2010 ident: 10.1016/j.cviu.2016.09.002_bib0106 article-title: Combining discriminative and generative methods for 3D deformable surface and articulated pose reconstruction – ident: 10.1016/j.cviu.2016.09.002_bib0025
SSID	ssj0011491
Score	2.6247802
Snippet	•Review of the recent literature in 3D human pose estimation from RGB images and videos.•Release of a challenging, publicly available, 3D pose estimation...
SourceID	crossref elsevier
SourceType	Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	3D Human pose estimation Anthropometry Articulated tracking Human motion analysis
Title	3D Human pose estimation: A review of the literature and analysis of covariates
URI	https://dx.doi.org/10.1016/j.cviu.2016.09.002
Volume	152
WOSCitedRecordID	wos000387630900001&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1090-235X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0011491 issn: 1077-3142 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELaWLQc48ChUtDzkA7dVVuvYebi3iBZRkBYkirS3yHYStO02We1L_Tv8U2Zi51GoKkDiEkVOnFieL_bMZOYbQt6GE6EzqX1PSF97QknpKWO05_uR5rGAHZ6puthENJ3Gs5n8Mhj8aHJhdouoLOPra7n8r6KGNhA2ps7-hbjbh0IDnIPQ4Qhih-MfCZ6fOM_8EkPRkUTjqo3gSHqpKqhxLlpSZUfa2jGUmGoHZjRqon39tSkCMbI56fbXwxXG_Wz7WTKt30atVAEAtLF80_klGNJV55ivAGHltoZY9T3r4RQLCJhbLnxSl8ilsLLECGcVFlxaj5Jx33fBQpfE1zrUmqSaGzGfYJCi69SSbo1z1yYnns-D2Y2F23LfuqWX9fbwOr_u993BOiouxmY332JUX1hT3E78bi9sIxS_4ihwEKCvIq2dvEf2_CiQ8ZDsJWens4_tryowMZkNbLWjdplZNojw1zfdrv30NJrzJ-SRM0VoYiH0lAzycp88dmYJdYv-GpoaoTdt--Rhj8byGfnMT2gNOYqQox3kjmlCLeBoVVAAHO0ARwEptAEcXu4A95x8e396_u6D5wp1eIaH4cYLskiqTEmlGCvERBecGR7B9gDKYy4izUzBFTcxGMuZBntZIukhC3JpMlBnteIHZFgCsl4QKgvkoDMmFDIXUgvFRc59eCRo3gLeckhYM4GpcSz2WExlkTbhihcpTnqKk55OZAqTfkhGbZ-l5XC58-6gkUvqtFCrXaYAozv6Hf1jv5fkQfdpvCLDzWqbvyb3zW4zX6_eOLT9BNUjrI4
linkProvider	Elsevier
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=3D+Human+pose+estimation%3A+A+review+of+the+literature+and+analysis+of+covariates&rft.jtitle=Computer+vision+and+image+understanding&rft.au=Sarafianos%2C+Nikolaos&rft.au=Boteanu%2C+Bogdan&rft.au=Ionescu%2C+Bogdan&rft.au=Kakadiaris%2C+Ioannis+A.&rft.date=2016-11-01&rft.pub=Elsevier+Inc&rft.issn=1077-3142&rft.eissn=1090-235X&rft.volume=152&rft.spage=1&rft.epage=20&rft_id=info:doi/10.1016%2Fj.cviu.2016.09.002&rft.externalDocID=S1077314216301369
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-3142&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-3142&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-3142&client=summon