Deep 3D human pose estimation: A review
Three-dimensional (3D) human pose estimation involves estimating the articulated 3D joint locations of a human body from an image or video. Due to its widespread applications in a great variety of areas, such as human motion analysis, human–computer interaction, robots, 3D human pose estimation has...
Saved in:
| Published in | Computer vision and image understanding Vol. 210; p. 103225 |
|---|---|
| Main Authors | , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Inc
01.09.2021
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Three-dimensional (3D) human pose estimation involves estimating the articulated 3D joint locations of a human body from an image or video. Due to its widespread applications in a great variety of areas, such as human motion analysis, human–computer interaction, robots, 3D human pose estimation has recently attracted increasing attention in the computer vision community, however, it is a challenging task due to depth ambiguities and the lack of in-the-wild datasets. A large number of approaches, with many based on deep learning, have been developed over the past decade, largely advancing the performance on existing benchmarks. To guide future development, a comprehensive literature review is highly desired in this area. However, existing surveys on 3D human pose estimation mainly focus on traditional methods and a comprehensive review on deep learning based methods remains lacking in the literature. In this paper, we provide a thorough review of existing deep learning based works for 3D pose estimation, summarize the advantages and disadvantages of these methods and provide an in-depth understanding of this area. Furthermore, we also explore the commonly-used benchmark datasets on which we conduct a comprehensive study for comparison and analysis. Our study sheds light on the state of research development in 3D human pose estimation and provides insights that can facilitate the future design of models and algorithms.
•The recent methods for deep 3D pose estimation are categorized and thoroughly analyzed.•Provide an extensive review of related datasets and evaluation metrics.•Compare the pros and cons of the deep 3D models valuated on the datasets and draw a conclusion.•We discuss the potential research orientations of future. |
|---|---|
| AbstractList | Three-dimensional (3D) human pose estimation involves estimating the articulated 3D joint locations of a human body from an image or video. Due to its widespread applications in a great variety of areas, such as human motion analysis, human–computer interaction, robots, 3D human pose estimation has recently attracted increasing attention in the computer vision community, however, it is a challenging task due to depth ambiguities and the lack of in-the-wild datasets. A large number of approaches, with many based on deep learning, have been developed over the past decade, largely advancing the performance on existing benchmarks. To guide future development, a comprehensive literature review is highly desired in this area. However, existing surveys on 3D human pose estimation mainly focus on traditional methods and a comprehensive review on deep learning based methods remains lacking in the literature. In this paper, we provide a thorough review of existing deep learning based works for 3D pose estimation, summarize the advantages and disadvantages of these methods and provide an in-depth understanding of this area. Furthermore, we also explore the commonly-used benchmark datasets on which we conduct a comprehensive study for comparison and analysis. Our study sheds light on the state of research development in 3D human pose estimation and provides insights that can facilitate the future design of models and algorithms.
•The recent methods for deep 3D pose estimation are categorized and thoroughly analyzed.•Provide an extensive review of related datasets and evaluation metrics.•Compare the pros and cons of the deep 3D models valuated on the datasets and draw a conclusion.•We discuss the potential research orientations of future. |
| ArticleNumber | 103225 |
| Author | Zhen, Xiantong Wang, Jinbao Shao, Ling He, Zhenyu Zheng, Feng Tan, Shujie Xu, Shuo |
| Author_xml | – sequence: 1 givenname: Jinbao surname: Wang fullname: Wang, Jinbao organization: Department of Computer Science and Engineering, Southern University of Science and Technology, 518055, China – sequence: 2 givenname: Shujie surname: Tan fullname: Tan, Shujie organization: Department of Computer Science and Engineering, Southern University of Science and Technology, 518055, China – sequence: 3 givenname: Xiantong surname: Zhen fullname: Zhen, Xiantong organization: Inception Institute of Artificial Intelligence, Abu Dhabi, The United Arab Emirates – sequence: 4 givenname: Shuo surname: Xu fullname: Xu, Shuo organization: Department of Electronics and Information Engineering, Anhui University, 230601, China – sequence: 5 givenname: Feng surname: Zheng fullname: Zheng, Feng email: zhengf@sustech.edu.cn organization: Department of Computer Science and Engineering, Southern University of Science and Technology, 518055, China – sequence: 6 givenname: Zhenyu surname: He fullname: He, Zhenyu organization: Harbin Institute of Technology (Shenzhen), China – sequence: 7 givenname: Ling surname: Shao fullname: Shao, Ling organization: Inception Institute of Artificial Intelligence, Abu Dhabi, The United Arab Emirates |
| BookMark | eNp9z0tLw0AQwPFFKthWv4Cn3Dwl7uwjD_FSWl9Q8KLgbdlOJrihTcpuWvHbmxhPHnqaZeC_zG_GJk3bEGPXwBPgkN7WCR7dIRFcQL-QQugzNgVe8FhI_TEZ3lkWS1Digs1CqDkHUAVM2c2KaB_JVfR52Nkm2reBIgqd29nOtc1dtIg8HR19XbLzym4DXf3NOXt_fHhbPsfr16eX5WIdo1Sqi7WmDddFmaYFKL1BhJRA5mWliwKk5RVWwHPkeX8hqgxVDmmJlmRlUdhcyTnLx3_RtyF4qgy67veWzlu3NcDNADa1GcBmAJsR3KfiX7r3vcN_n47ux4h6VA_1JqCjBql0nrAzZetO5T9JzG9r |
| CitedBy_id | crossref_primary_10_29121_ijetmr_v11_i6_2024_1464 crossref_primary_10_1371_journal_pone_0293178 crossref_primary_10_4028_p_9cplm1 crossref_primary_10_1111_epi_17926 crossref_primary_10_3390_s25030667 crossref_primary_10_1109_THMS_2021_3121649 crossref_primary_10_3389_fnbot_2025_1531894 crossref_primary_10_1109_LRA_2024_3478569 crossref_primary_10_3389_fnbot_2023_1148545 crossref_primary_10_24018_ejece_2023_7_6_573 crossref_primary_10_1016_j_displa_2021_102138 crossref_primary_10_1016_j_imavis_2025_105437 crossref_primary_10_1016_j_heliyon_2024_e36589 crossref_primary_10_3390_s23156997 crossref_primary_10_1109_TFUZZ_2022_3177028 crossref_primary_10_1109_TIM_2023_3338658 crossref_primary_10_3390_aerospace10030298 crossref_primary_10_1007_s10489_022_03516_1 crossref_primary_10_32604_cmes_2023_027676 crossref_primary_10_3390_s23218997 crossref_primary_10_3390_s24103123 crossref_primary_10_32604_cmc_2023_035904 crossref_primary_10_3390_s24092947 crossref_primary_10_32604_cmc_2024_058193 crossref_primary_10_1016_j_eswa_2023_122419 crossref_primary_10_1038_s41597_024_04077_3 crossref_primary_10_1109_THMS_2022_3219242 crossref_primary_10_38124_ijisrt_IJISRT24JUN071 crossref_primary_10_1007_s11082_023_06246_x crossref_primary_10_1016_j_artmed_2022_102474 crossref_primary_10_1016_j_media_2022_102484 crossref_primary_10_1109_JSEN_2023_3315849 crossref_primary_10_1016_j_conb_2022_02_002 crossref_primary_10_1016_j_cviu_2024_103999 crossref_primary_10_1109_ACCESS_2023_3323220 crossref_primary_10_1142_S1469026823410092 crossref_primary_10_1109_OJCAS_2022_3231097 crossref_primary_10_1061__ASCE_CP_1943_5487_0001060 crossref_primary_10_1016_j_cub_2024_05_033 crossref_primary_10_1109_JSEN_2024_3523903 crossref_primary_10_1016_j_aej_2024_10_099 crossref_primary_10_29109_gujsc_1384031 crossref_primary_10_1109_TNSRE_2022_3150392 crossref_primary_10_35940_ijitee_B9783_13020124 crossref_primary_10_1016_j_cviu_2025_104297 crossref_primary_10_1007_s41999_024_01082_y crossref_primary_10_1007_s11042_024_20495_2 crossref_primary_10_3390_agriculture14122282 crossref_primary_10_3390_app13042700 crossref_primary_10_1016_j_imavis_2023_104841 crossref_primary_10_1109_ACCESS_2025_3548170 crossref_primary_10_1186_s12984_023_01294_6 crossref_primary_10_1016_j_autcon_2024_105452 crossref_primary_10_1049_ipr2_12400 crossref_primary_10_1177_09544062251314931 crossref_primary_10_1080_0951192X_2024_2372281 crossref_primary_10_1109_TCSVT_2024_3423411 crossref_primary_10_1061_JCEMD4_COENG_13071 crossref_primary_10_12677_AIRR_2023_122017 crossref_primary_10_1145_3709000 crossref_primary_10_1016_j_aei_2023_101875 crossref_primary_10_3233_JPD_223351 crossref_primary_10_1186_s13640_024_00623_6 crossref_primary_10_1016_j_image_2023_117041 crossref_primary_10_1186_s40537_024_00915_8 crossref_primary_10_3390_s22145419 crossref_primary_10_7717_peerj_cs_2574 crossref_primary_10_3390_s21196530 crossref_primary_10_1016_j_gaitpost_2022_07_019 crossref_primary_10_1016_j_inffus_2023_102154 crossref_primary_10_3390_electronics12204273 crossref_primary_10_3389_fcomp_2024_1379925 crossref_primary_10_1016_j_cag_2023_06_024 crossref_primary_10_1109_ACCESS_2024_3397612 crossref_primary_10_1109_TBDATA_2023_3291558 crossref_primary_10_1016_j_aej_2024_10_079 crossref_primary_10_1007_s00138_024_01530_6 crossref_primary_10_3390_bioengineering11020136 crossref_primary_10_3390_jimaging9120275 crossref_primary_10_1145_3691356 crossref_primary_10_1016_j_engappai_2022_105636 crossref_primary_10_1007_s10462_024_11019_3 crossref_primary_10_3390_bioengineering10030369 crossref_primary_10_3390_bioengineering11020141 crossref_primary_10_1016_j_neucom_2024_128743 crossref_primary_10_1016_j_sna_2024_115752 crossref_primary_10_1109_JBHI_2023_3340716 crossref_primary_10_3390_electronics14061078 crossref_primary_10_3390_s22186951 crossref_primary_10_1109_TCE_2024_3363616 crossref_primary_10_3389_fpsyg_2021_705170 crossref_primary_10_1002_mdc3_13692 crossref_primary_10_1117_1_JEI_33_4_043022 crossref_primary_10_1109_ACCESS_2022_3191644 crossref_primary_10_1111_mice_13139 crossref_primary_10_3390_buildings14103174 crossref_primary_10_3233_THC_240639 crossref_primary_10_1016_j_aej_2024_12_097 crossref_primary_10_1002_aisy_202300335 crossref_primary_10_1007_s12283_022_00387_0 crossref_primary_10_3390_s24072037 crossref_primary_10_1007_s10639_023_12365_5 crossref_primary_10_1016_j_aej_2025_02_058 crossref_primary_10_3389_fpsyg_2022_897230 crossref_primary_10_1016_j_autcon_2022_104193 crossref_primary_10_1109_ACCESS_2025_3538332 crossref_primary_10_1109_JSEN_2024_3485226 crossref_primary_10_1016_j_cviu_2023_103830 crossref_primary_10_1007_s11042_023_16225_9 crossref_primary_10_1142_S0218213024400086 crossref_primary_10_1186_s12984_024_01362_5 crossref_primary_10_1038_s41598_024_66165_z crossref_primary_10_5607_en24008 crossref_primary_10_1007_s00371_023_02957_0 crossref_primary_10_1016_j_atech_2024_100486 crossref_primary_10_1016_j_neucom_2025_129413 crossref_primary_10_1038_s44172_024_00272_7 crossref_primary_10_56977_jicce_2023_21_4_337 crossref_primary_10_1007_s13735_023_00294_5 crossref_primary_10_3389_frobt_2022_813843 crossref_primary_10_3389_fspor_2022_994221 crossref_primary_10_3390_app122010591 crossref_primary_10_1109_TIM_2023_3301060 crossref_primary_10_1155_2024_7113084 crossref_primary_10_3390_s22072712 crossref_primary_10_1109_TIP_2024_3490401 crossref_primary_10_1145_3580883 crossref_primary_10_1007_s00530_022_00980_0 crossref_primary_10_1007_s11042_022_13921_w crossref_primary_10_1016_j_gaitpost_2024_06_007 crossref_primary_10_1016_j_jvcir_2025_104409 crossref_primary_10_1155_2022_6858822 crossref_primary_10_1016_j_autcon_2023_105236 crossref_primary_10_1016_j_neucom_2022_05_107 crossref_primary_10_1109_TIM_2025_3548063 crossref_primary_10_1109_ACCESS_2024_3444790 crossref_primary_10_1007_s42979_024_02785_6 crossref_primary_10_1016_j_eswa_2023_121981 crossref_primary_10_1109_TCSVT_2022_3187670 crossref_primary_10_1016_j_cviu_2025_104307 |
| Cites_doi | 10.1109/ICCV.2019.00083 10.1007/978-3-030-01249-6_48 10.1145/3181973 10.1109/CVPR.2019.01115 10.1109/CVPR.2018.00787 10.1109/CVPR.2018.00763 10.1109/CVPR.2017.139 10.1109/CVPR.2015.7298751 10.1109/CVPR.2017.588 10.1109/CVPR.2018.00498 10.1109/ICCV.2017.51 10.1109/ICCV.2019.00785 10.1109/ICCV.2017.427 10.1007/978-3-030-01234-2_8 10.1109/MMUL.2012.24 10.1145/3072959.3073711 10.1016/j.cviu.2016.09.002 10.1109/CVPR.2019.00794 10.1109/CVPR.2018.00230 10.1109/ICCV.2019.00234 10.1109/TPAMI.2017.2782743 10.1109/CVPR.2018.00744 10.1109/CVPR.2019.00351 10.1109/ICCV.2019.00228 10.1109/CVPR.2018.00762 10.1109/CVPR.2019.00354 10.1145/3072959.3073596 10.1109/ICCV.2017.322 10.1007/s11263-009-0273-6 10.1145/2661229.2661273 10.1109/CVPR.2017.138 10.1007/978-3-030-01249-6_46 10.1109/TPAMI.2012.261 10.1145/2816795.2818013 10.1109/CVPR.2016.533 10.1109/CVPR.2016.511 10.1109/CVPR42600.2020.00530 10.1109/CVPR.2018.00539 10.1109/ICCV.2019.00445 10.1109/ICCV.2019.00081 10.1109/ICCV.2017.288 10.1016/j.cviu.2019.102897 10.1007/978-3-030-58536-5_22 10.1109/ICCV.2019.00089 10.1109/TPAMI.2016.2557779 10.1109/CVPR.2018.00229 10.1109/ICCV.2017.467 10.1109/CVPR.2014.471 10.1007/978-3-030-01249-6_5 10.1109/CVPR.2019.00789 10.1109/CVPRW.2018.00232 10.1111/cgf.12184 10.1109/CVPR.2018.00551 10.1109/CVPR.2018.00542 10.1109/CVPR.2018.00868 10.1109/ICCV.2019.00235 10.1007/978-3-030-01225-0_27 10.1109/ICCV.2017.284 10.1109/TPAMI.2019.2892985 10.1162/neco.1997.9.8.1735 10.1109/ICCVW.2017.99 10.1007/s11263-016-0966-6 10.1007/978-3-030-01231-1_33 10.1007/978-3-030-01249-6_37 10.1109/ICCV.2019.00444 10.1109/CVPR.2017.170 10.1109/CVPR.2017.492 10.1109/CVPR.2018.00055 10.3390/s16020208 10.1109/CVPR.2017.280 10.1109/ICCV.2019.00545 10.1109/TPAMI.2013.248 10.1007/s11263-018-1066-6 10.1109/WACV.2019.00162 10.1109/CVPR.2017.134 10.1109/CVPR.2019.00798 10.1109/CVPR.2014.216 10.1109/LRA.2019.2896705 10.1109/CVPR.2016.113 10.1109/ICCV.2019.00237 10.1109/ICCV.2019.00554 10.1109/CVPR.2018.00359 10.1109/ICCV.2015.94 10.1109/CVPR.2019.00586 10.1609/aaai.v30i1.10460 10.1109/CVPR.2017.501 10.1109/LRA.2019.2895266 10.1109/CVPR.2016.537 10.1109/ICCV.2019.00778 10.1109/CVPR.2018.00226 10.1109/CVPR.2019.00381 10.1109/CVPRW.2017.20 10.1109/CVPR.2019.00797 10.1109/CVPR.2018.00880 10.1016/j.cag.2019.09.002 10.1007/978-3-030-01240-3_41 10.1109/ICCV.2019.00243 10.1109/CVPR.2019.01116 10.1109/CVPR.2019.00724 10.1145/2159516.2159523 10.1109/ICCV.2017.425 10.1109/ICCV.2019.00236 10.1109/CVPR.2017.500 10.1007/s10462-019-09724-5 10.1007/978-3-030-66096-3_36 10.1109/CVPR.2017.143 10.1109/CVPR.2019.00606 10.1109/CVPR.2017.603 10.1109/ICCV.2017.589 10.1109/CVPR.2019.01012 |
| ContentType | Journal Article |
| Copyright | 2021 The Author(s) |
| Copyright_xml | – notice: 2021 The Author(s) |
| DBID | 6I. AAFTH AAYXX CITATION |
| DOI | 10.1016/j.cviu.2021.103225 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering Computer Science |
| EISSN | 1090-235X |
| ExternalDocumentID | 10_1016_j_cviu_2021_103225 S1077314221000692 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 6I. 6TJ 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAFTH 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- AATTM AAXKI AAYWO AAYXX ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SST |
| ID | FETCH-LOGICAL-c344t-55eb059d669145bcc16e138df59913a0fcf108c08225c47c4816dcae3fac2a843 |
| IEDL.DBID | .~1 |
| ISSN | 1077-3142 |
| IngestDate | Tue Jul 01 04:32:08 EDT 2025 Thu Apr 24 22:57:02 EDT 2025 Fri Feb 23 02:42:16 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | 68T45 68U10 3D Human Pose Estimation 68-02 Deep Learning |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c344t-55eb059d669145bcc16e138df59913a0fcf108c08225c47c4816dcae3fac2a843 |
| OpenAccessLink | https://www.sciencedirect.com/science/article/pii/S1077314221000692 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_cviu_2021_103225 crossref_primary_10_1016_j_cviu_2021_103225 elsevier_sciencedirect_doi_10_1016_j_cviu_2021_103225 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | September 2021 2021-09-00 |
| PublicationDateYYYYMMDD | 2021-09-01 |
| PublicationDate_xml | – month: 09 year: 2021 text: September 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | Computer vision and image understanding |
| PublicationYear | 2021 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Johnson, Everingham (b51) 2010; 2 Loper, Mahmood, Romero, Pons-Moll, Black (b75) 2015; 34 Sun, X., Shang, J., Liang, S., Wei, Y., 2017. Compositional human pose regression. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2602–2611. Cheng, Yang, Wang, Tan (b23) 2020 Huang, Guibas (b46) 2013; 32 Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J., 2018. End-to-end recovery of human shape and pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7122–7131. Du, Wong, Liu, Han, Gui, Wang, Kankanhalli, Geng (b32) 2016 Omran, Lassner, Pons-Moll, Gehler, Schiele (b96) 2018 Cai, Y., Ge, L., Liu, J., Cai, J., Cham, T.-J., Yuan, J., Thalmann, N.M., 2019. Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2272–2281. Agrawal, Lu, Antol, Mitchell, Zitnick, Parikh, Batra (b1) 2015; 123 Arnab, A., Doersch, C., Zisserman, A., 2019a. Exploiting temporal context for 3D human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3395–3404. Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K., 2017b. Harvesting multiple views for marker-less 3d human pose annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6988–6997. Ci, H., Wang, C., Ma, X., Wang, Y., 2019. Optimizing network structure for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2262–2271. Fabbri, M., Lanzi, F., Calderara, S., Palazzi, A., Vezzani, R., Cucchiara, R., 2018. Learning to detect and track visible and occluded body joints in a virtual world. In: Proceedings of the European Conference on Computer Vision, ECCV. pp. 430–446. Habibie, I., Xu, W., Mehta, D., Pons-Moll, G., Theobalt, C., 2019. In the wild human pose estimation using explicit 2D features and intermediate 3D representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 10905–10914. Zheng, Huang, Lu, Yang (b164) 2019 Tome, Toso, Agapito, Russell (b141) 2018 Novotny, D., Ravi, N., Graham, B., Neverova, N., Vedaldi, A., 2019. C3DPO: Canonical 3D pose networks for non-rigid structure from motion. In: Proceedings of the IEEE International Conference on Computer Vision. Rhodin, H., Robertini, N., Richardt, C., Seidel, H.-P., Theobalt, C., 2015. A versatile scene model with differentiable visibility applied to generative pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 765–773. Yang, Ramanan (b159) 2012; 35 Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P.V., Schiele, B., 2016. Deepcut: Joint subset partition and labeling for multi person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4929–4937. Zanfir, A., Marinoiu, E., Sminchisescu, C., 2018. Monocular 3d pose and shape estimation of multiple people in natural scenes-the importance of multiple scene constraints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2148–2157. Li, C., Lee, G.H., 2019. Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 9887–9895. Choi, Moon, Lee (b25) 2020 Rhodin, H., Constantin, V., Katircioglu, I., Salzmann, M., Fua, P., 2019. Neural scene decomposition for multi-person motion capture. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Newell, Yang, Deng (b89) 2016 Sengupta, Budvytis, Cipolla (b123) 2020 Popov, S., Bauszat, P., Ferrari, V., 2020. CoReNet: Coherent 3D scene reconstruction from a single RGB image. In: ECCV. Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K., 2019b. Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV). pp. 2252–2261. Pavlakos, G., Kolotouros, N., Daniilidis, K., 2019. TexturePose: Supervising Human Mesh Estimation with Texture Consistency. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 803–812. Tompson, J.J., Jain, A., LeCun, Y., Bregler, C., 2014. Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in Neural Information Processing Systems. pp. 1799–1807. Kocabas, Karagoz, Akbas (b58) 2019 Lee, K., Lee, I., Lee, S., 2018. Propagating lstm: 3d pose estimation based on joint interdependency. In: Proceedings of the European Conference on Computer Vision, ECCV. pp. 119–135. Li, Chan (b65) 2014 Song, Xiao (b129) 2015 Rhodin, H., Salzmann, M., Fua, P., 2018. Unsupervised geometry-aware representation for 3d human pose estimation. In: Proceedings of the European Conference on Computer Vision, ECCV. pp. 750–767. Alp Güler, R., Neverova, N., Kokkinos, I., 2018. Densepose: Dense human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7297–7306. Han, X., Wu, Z., Wu, Z., Yu, R., Davis, L.S., 2018. Viton: An image-based virtual try-on network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7543–7552. Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B., 2014a. 2d human pose estimation: New benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3686–3693. Rematas, K., Kemelmacher-Shlizerman, I., Curless, B., Seitz, S., 2018. Soccer on your tabletop. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4738–4747. Grauman, Shakhnarovich, Darrell (b38) 2003 Park, Hwang, Kwak (b97) 2016 Sarafianos, Boteanu, Ionescu, Kakadiaris (b121) 2016; 152 Zecha, D., Einfalt, M., Eggert, C., Lienhart, R., 2018. Kinematic Pose Rectification for Performance Analysis and Retrieval in Sports. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. pp. 1791–1799. Trumble, M., Gilbert, A., Hilton, A., Collomosse, J., 2018. Deep autoencoder for combined human pose estimation and body model upscaling. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 784–800. Elhayek, de Aguiar, Jain, Thompson, Pishchulin, Andriluka, Bregler, Schiele, Theobalt (b33) 2016; 39 Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y., 2018. Integral human pose regression. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 529–545. Xu, J., Zhao, R., Zhu, F., Wang, H., Ouyang, W., 2018b. Attention-aware compositional network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2119–2128. Pons-Moll, Baak, Gall, Leal-Taixe, Mueller, Seidel, Rosenhahn (b106) 2011 Wei, S.-E., Ramakrishna, V., Kanade, T., Sheikh, Y., 2016. Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4724–4732. Liang, J., Lin, M., 2019. Shape-aware human pose and shape reconstruction using multi-view images. In: 2019 IEEE/CVF International Conference on Computer Vision, ICCV. pp. 4351–4361. Zhou, K., Han, X., Jiang, N., Jia, K., Lu, J., 2019. HEMlets pose: Learning part-centric heatmap triplets for accurate 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2344–2353. Martinez, J., Hossain, R., Romero, J., Little, J.J., 2017. A simple yet effective baseline for 3d human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2640–2649. Joo, H., Simon, T., Sheikh, Y., 2018. Total capture: A 3d deformation model for tracking faces, hands, and bodies. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 8320–8329. Arnab, A., Doersch, C., Zisserman, A., 2019b. Exploiting temporal context for 3D human pose estimation in the wild. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 3390–3399. Hassan, M., Choutas, V., Tzionas, D., Black, M.J., 2019. Resolving 3D human pose ambiguities with 3D scene constrains. In: Proceedings IEEE International Conference on Computer Vision, ICCV. Popa, A.-I., Zanfir, M., Sminchisescu, C., 2017. Deep multitask architecture for integrated 2d and 3d human sensing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6289–6298. Sigal, Balan, Black (b126) 2009; 87 Moon, Lee (b87) 2020 Bogo, Kanazawa, Lassner, Gehler, Romero, Black (b15) 2016 Pons-Moll, Pujades, Hu, Black (b107) 2017; 36 Tekin, B., Rozantsev, A., Lepetit, V., Fua, P., 2016. Direct prediction of 3d body poses from motion compensated sequences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 991–1000. Varol, G., Romero, J., Martin, X., Mahmood, N., Black, M.J., Laptev, I., Schmid, C., 2017. Learning from synthetic humans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 109–117. Du, Vasudevan, Johnson-Roberson (b31) 2019; 4 Qiu, H., Wang, C., Wang, J., Wang, N., Zeng, W., 2019. Cross View Fusion for 3D Human Pose Estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 4342–4351. Katircioglu, Tekin, Salzmann, Lepetit, Fua (b55) 2018; 126 Airò Farulla, Pianu, Cempini, Cortese, Russo, Indaco, Nerino, Chimienti, Oddo, Vitiello (b2) 2016; 16 He, K., Gkioxari, G., Dollár, P., Girshick, R., 2017. Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2961–2969. Sigal, Balan, Black (b127) 2010; 87 Siarohin, A., Sangineto, E., Lathuilière, S., Sebe, N., 2018. Deformable gans for pose-based human image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3408–3416. Zhang (b162) 2012; 19 Andriluka, M., Iqbal, U Huang (10.1016/j.cviu.2021.103225_b45) 2017 Katircioglu (10.1016/j.cviu.2021.103225_b55) 2018; 126 Nie (10.1016/j.cviu.2021.103225_b93) 2019 Cheng (10.1016/j.cviu.2021.103225_b23) 2020 10.1016/j.cviu.2021.103225_b140 Luo (10.1016/j.cviu.2021.103225_b76) 2020 10.1016/j.cviu.2021.103225_b142 Kocabas (10.1016/j.cviu.2021.103225_b58) 2019 Sengupta (10.1016/j.cviu.2021.103225_b123) 2020 10.1016/j.cviu.2021.103225_b143 10.1016/j.cviu.2021.103225_b7 10.1016/j.cviu.2021.103225_b146 10.1016/j.cviu.2021.103225_b6 Park (10.1016/j.cviu.2021.103225_b97) 2016 10.1016/j.cviu.2021.103225_b9 10.1016/j.cviu.2021.103225_b8 10.1016/j.cviu.2021.103225_b147 Wei (10.1016/j.cviu.2021.103225_b152) 2020 10.1016/j.cviu.2021.103225_b3 Belagiannis (10.1016/j.cviu.2021.103225_b14) 2014 10.1016/j.cviu.2021.103225_b95 Rhodin (10.1016/j.cviu.2021.103225_b114) 2016 10.1016/j.cviu.2021.103225_b149 10.1016/j.cviu.2021.103225_b5 10.1016/j.cviu.2021.103225_b11 10.1016/j.cviu.2021.103225_b99 10.1016/j.cviu.2021.103225_b12 10.1016/j.cviu.2021.103225_b98 10.1016/j.cviu.2021.103225_b16 10.1016/j.cviu.2021.103225_b13 Chen (10.1016/j.cviu.2021.103225_b19) 2019 10.1016/j.cviu.2021.103225_b18 Kim (10.1016/j.cviu.2021.103225_b56) 2019; 4 Tome (10.1016/j.cviu.2021.103225_b141) 2018 10.1016/j.cviu.2021.103225_b131 Choi (10.1016/j.cviu.2021.103225_b25) 2020 10.1016/j.cviu.2021.103225_b133 10.1016/j.cviu.2021.103225_b132 10.1016/j.cviu.2021.103225_b91 10.1016/j.cviu.2021.103225_b134 Chen (10.1016/j.cviu.2021.103225_b21) 2020; 192 10.1016/j.cviu.2021.103225_b139 10.1016/j.cviu.2021.103225_b138 10.1016/j.cviu.2021.103225_b82 Sigal (10.1016/j.cviu.2021.103225_b126) 2009; 87 10.1016/j.cviu.2021.103225_b88 Ferrari (10.1016/j.cviu.2021.103225_b36) 2009 Noroozi (10.1016/j.cviu.2021.103225_b94) 2018 Sigal (10.1016/j.cviu.2021.103225_b127) 2010; 87 Yang (10.1016/j.cviu.2021.103225_b159) 2012; 35 Nibali (10.1016/j.cviu.2021.103225_b90) 2018 Du (10.1016/j.cviu.2021.103225_b31) 2019; 4 Trumble (10.1016/j.cviu.2021.103225_b144) 2017 10.1016/j.cviu.2021.103225_b122 Zheng (10.1016/j.cviu.2021.103225_b164) 2019 10.1016/j.cviu.2021.103225_b80 Sarafianos (10.1016/j.cviu.2021.103225_b121) 2016; 152 10.1016/j.cviu.2021.103225_b81 10.1016/j.cviu.2021.103225_b125 Xu (10.1016/j.cviu.2021.103225_b155) 2018; 37 Loper (10.1016/j.cviu.2021.103225_b75) 2015; 34 10.1016/j.cviu.2021.103225_b77 Du (10.1016/j.cviu.2021.103225_b32) 2016 Moon (10.1016/j.cviu.2021.103225_b87) 2020 Bogo (10.1016/j.cviu.2021.103225_b15) 2016 10.1016/j.cviu.2021.103225_b79 Luvizon (10.1016/j.cviu.2021.103225_b78) 2019; 85 Simonyan (10.1016/j.cviu.2021.103225_b128) 2014 10.1016/j.cviu.2021.103225_b111 Nie (10.1016/j.cviu.2021.103225_b92) 2017 10.1016/j.cviu.2021.103225_b110 10.1016/j.cviu.2021.103225_b113 10.1016/j.cviu.2021.103225_b70 10.1016/j.cviu.2021.103225_b112 10.1016/j.cviu.2021.103225_b115 Rogez (10.1016/j.cviu.2021.103225_b120) 2019 10.1016/j.cviu.2021.103225_b62 10.1016/j.cviu.2021.103225_b117 10.1016/j.cviu.2021.103225_b63 10.1016/j.cviu.2021.103225_b116 10.1016/j.cviu.2021.103225_b60 10.1016/j.cviu.2021.103225_b119 10.1016/j.cviu.2021.103225_b61 10.1016/j.cviu.2021.103225_b66 10.1016/j.cviu.2021.103225_b67 Song (10.1016/j.cviu.2021.103225_b129) 2015 Choutas (10.1016/j.cviu.2021.103225_b26) 2020 10.1016/j.cviu.2021.103225_b68 10.1016/j.cviu.2021.103225_b69 Sharma (10.1016/j.cviu.2021.103225_b124) 2019 Elhayek (10.1016/j.cviu.2021.103225_b33) 2016; 39 Pons-Moll (10.1016/j.cviu.2021.103225_b107) 2017; 36 Tung (10.1016/j.cviu.2021.103225_b145) 2017 10.1016/j.cviu.2021.103225_b100 Stoll (10.1016/j.cviu.2021.103225_b130) 2011 10.1016/j.cviu.2021.103225_b102 10.1016/j.cviu.2021.103225_b101 Pons-Moll (10.1016/j.cviu.2021.103225_b106) 2011 10.1016/j.cviu.2021.103225_b103 10.1016/j.cviu.2021.103225_b105 10.1016/j.cviu.2021.103225_b108 10.1016/j.cviu.2021.103225_b50 Newell (10.1016/j.cviu.2021.103225_b89) 2016 10.1016/j.cviu.2021.103225_b109 Sutskever (10.1016/j.cviu.2021.103225_b135) 2014 10.1016/j.cviu.2021.103225_b53 10.1016/j.cviu.2021.103225_b54 10.1016/j.cviu.2021.103225_b59 Johnson (10.1016/j.cviu.2021.103225_b51) 2010; 2 10.1016/j.cviu.2021.103225_b57 Loper (10.1016/j.cviu.2021.103225_b74) 2014; 33 Airò Farulla (10.1016/j.cviu.2021.103225_b2) 2016; 16 Joo (10.1016/j.cviu.2021.103225_b52) 2017; 41 Omran (10.1016/j.cviu.2021.103225_b96) 2018 10.1016/j.cviu.2021.103225_b40 Wang (10.1016/j.cviu.2021.103225_b148) 2019 10.1016/j.cviu.2021.103225_b41 10.1016/j.cviu.2021.103225_b42 10.1016/j.cviu.2021.103225_b43 Roetenberg (10.1016/j.cviu.2021.103225_b118) 2009 10.1016/j.cviu.2021.103225_b47 Agrawal (10.1016/j.cviu.2021.103225_b1) 2015; 123 Lin (10.1016/j.cviu.2021.103225_b73) 2020 Mehta (10.1016/j.cviu.2021.103225_b85) 2017; 36 Akhter (10.1016/j.cviu.2021.103225_b4) 2012; 31 10.1016/j.cviu.2021.103225_b160 Zhang (10.1016/j.cviu.2021.103225_b162) 2012; 19 10.1016/j.cviu.2021.103225_b161 10.1016/j.cviu.2021.103225_b163 10.1016/j.cviu.2021.103225_b166 10.1016/j.cviu.2021.103225_b165 10.1016/j.cviu.2021.103225_b168 Ferrari (10.1016/j.cviu.2021.103225_b35) 2008 Zhou (10.1016/j.cviu.2021.103225_b167) 2016 10.1016/j.cviu.2021.103225_b30 Peng (10.1016/j.cviu.2021.103225_b104) 2020 10.1016/j.cviu.2021.103225_b34 Lin (10.1016/j.cviu.2021.103225_b71) 2014 10.1016/j.cviu.2021.103225_b37 Ionescu (10.1016/j.cviu.2021.103225_b48) 2013; 36 Mehta (10.1016/j.cviu.2021.103225_b84) 2018 Moon (10.1016/j.cviu.2021.103225_b86) 2019 Lentzas (10.1016/j.cviu.2021.103225_b64) 2019; 53 10.1016/j.cviu.2021.103225_b39 Tai (10.1016/j.cviu.2021.103225_b136) 2015 Huang (10.1016/j.cviu.2021.103225_b46) 2013; 32 10.1016/j.cviu.2021.103225_b151 10.1016/j.cviu.2021.103225_b150 10.1016/j.cviu.2021.103225_b153 Grauman (10.1016/j.cviu.2021.103225_b38) 2003 Li (10.1016/j.cviu.2021.103225_b65) 2014 10.1016/j.cviu.2021.103225_b154 Anguelov (10.1016/j.cviu.2021.103225_b10) 2005 10.1016/j.cviu.2021.103225_b157 10.1016/j.cviu.2021.103225_b156 10.1016/j.cviu.2021.103225_b158 Iskakov (10.1016/j.cviu.2021.103225_b49) 2019 Mehta (10.1016/j.cviu.2021.103225_b83) 2017 Cao (10.1016/j.cviu.2021.103225_b17) 2018 10.1016/j.cviu.2021.103225_b22 10.1016/j.cviu.2021.103225_b20 10.1016/j.cviu.2021.103225_b27 10.1016/j.cviu.2021.103225_b24 Tan (10.1016/j.cviu.2021.103225_b137) 2018 10.1016/j.cviu.2021.103225_b28 10.1016/j.cviu.2021.103225_b29 Hochreiter (10.1016/j.cviu.2021.103225_b44) 1997; 9 Lin (10.1016/j.cviu.2021.103225_b72) 2014 |
| References_xml | – reference: Li, Z., Wang, X., Wang, F., Jiang, P., 2019b. On boosting single-frame 3D human pose estimation via monocular videos. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2192–2201. – start-page: 951 year: 2011 end-page: 958 ident: b130 article-title: Fast articulated motion tracking using a sums of gaussians body model publication-title: 2011 International Conference on Computer Vision – reference: Cao, Z., Simon, T., Wei, S.-E., Sheikh, Y., 2017. Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7291–7299. – year: 2019 ident: b49 article-title: Learnable triangulation of human pose – volume: 123 start-page: 4 year: 2015 end-page: 31 ident: b1 article-title: VQA: Visual question answering publication-title: Int. J. Comput. Vis. – reference: Tekin, B., Rozantsev, A., Lepetit, V., Fua, P., 2016. Direct prediction of 3d body poses from motion compensated sequences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 991–1000. – reference: Alp Guler, R., Trigeorgis, G., Antonakos, E., Snape, P., Zafeiriou, S., Kokkinos, I., 2017. Densereg: Fully convolutional dense shape regression in-the-wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6799–6808. – volume: 31 start-page: 17 year: 2012 ident: b4 article-title: Bilinear spatiotemporal basis models publication-title: ACM Trans. Graph. – reference: Wang, C., Kong, C., Lucey, S., 2019b. Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 743–752. – reference: Zhou, X., Huang, Q., Sun, X., Xue, X., Wei, Y., 2017. Towards 3d human pose estimation in the wild: a weakly-supervised approach. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 398–407. – reference: Yang, W., Ouyang, W., Wang, X., Ren, J., Li, H., Wang, X., 2018. 3d human pose estimation in the wild by adversarial learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5255–5264. – year: 2020 ident: b104 article-title: Learning graph convolutional network for skeleton-based human action recognition by neural searching – reference: Xu, Y., Zhu, S.-C., Tung, T., 2019. DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 7760–7770. – volume: 36 start-page: 44 year: 2017 ident: b85 article-title: Vnect: Real-time 3d human pose estimation with a single rgb camera publication-title: ACM Trans. Graph. – reference: Green, R., 2003. Spherical harmonic lighting: The gritty details. In: Archives of the Game Developers Conference, vol. 56, p. 4. – reference: Nibali, A., He, Z., Morgan, S., Prendergast, L., 2019. 3D Human pose estimation with 2D marginal heatmaps. In: 2019 IEEE Winter Conference on Applications of Computer Vision, WACV. pp. 1477–1485. – start-page: 740 year: 2014 end-page: 755 ident: b71 article-title: Microsoft coco: Common objects in context publication-title: European Conference on Computer Vision – year: 2018 ident: b137 article-title: Indirect deep structured learning for 3d human body shape and pose prediction – volume: 2 start-page: 5 year: 2010 ident: b51 article-title: Clustered pose and nonlinear appearance models for human pose estimation publication-title: Bmvc – volume: 152 start-page: 1 year: 2016 end-page: 20 ident: b121 article-title: 3d human pose estimation: A review of the literature and analysis of covariates publication-title: Comput. Vis. Image Underst. – reference: Cheng, Y., Yang, B., Wang, B., Yan, W., Tan, R.T., 2019. Occlusion-aware networks for 3D human pose estimation in video. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 723–732. – reference: Hwang, J., Park, S., Kwak, N., 2017. Athlete pose estimation by a global-local network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. pp. 58–65. – start-page: 506 year: 2017 end-page: 516 ident: b83 article-title: Monocular 3d human pose estimation in the wild using improved cnn supervision publication-title: 2017 International Conference on 3D Vision (3DV) – reference: Arnab, A., Doersch, C., Zisserman, A., 2019a. Exploiting temporal context for 3D human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3395–3404. – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: b44 article-title: Long short-term memory publication-title: Neural Comput. – reference: Han, X., Wu, Z., Wu, Z., Yu, R., Davis, L.S., 2018. Viton: An image-based virtual try-on network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7543–7552. – reference: Andriluka, M., Iqbal, U., Insafutdinov, E., Pishchulin, L., Milan, A., Gall, J., Schiele, B., 2018. Posetrack: A benchmark for human pose estimation and tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5167–5176. – volume: 85 start-page: 15 year: 2019 end-page: 22 ident: b78 article-title: Human pose regression by combining indirect part detection and contextual information publication-title: Comput. Graph. – year: 2020 ident: b25 article-title: Pose2mesh: Graph convolutional network for 3D human pose and mesh recovery from a 2D human pose – reference: Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y., 2018. Integral human pose regression. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 529–545. – start-page: 742 year: 2014 end-page: 754 ident: b14 article-title: Multiple human pose estimation with temporally consistent 3D pictorial structures publication-title: European Conference on Computer Vision – reference: Sun, X., Shang, J., Liang, S., Wei, Y., 2017. Compositional human pose regression. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2602–2611. – volume: 87 start-page: 4 year: 2009 end-page: 27 ident: b126 article-title: Humaneva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion publication-title: Int. J. Comput. Vis. – reference: Rhodin, H., Spörri, J., Katircioglu, I., Constantin, V., Meyer, F., Müller, E., Salzmann, M., Fua, P., 2018. Learning monocular 3D human pose estimation from multi-view images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 8437–8446. – reference: Scott, J., Collins, R., Funk, C., Liu, Y., 2017. 4D model-based spatiotemporal alignment of scripted Taiji Quan sequences. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 795–804. – year: 2020 ident: b123 article-title: Synthetic training for accurate 3D human pose and shape estimation in the wild – start-page: 332 year: 2014 end-page: 347 ident: b65 article-title: 3d human pose estimation from monocular images with deep convolutional neural network publication-title: Asian Conference on Computer Vision – year: 2019 ident: b93 article-title: Single-stage multi-person pose machines – start-page: 509 year: 2016 end-page: 526 ident: b114 article-title: General automatic human shape and motion capture using volumetric contour cues publication-title: European Conference on Computer Vision – year: 2009 ident: b118 article-title: Xsens MVN: Full 6dof human motion tracking using miniature inertial sensors – volume: 4 start-page: 1501 year: 2019 end-page: 1508 ident: b31 article-title: Bio-lstm: A biomechanically inspired recurrent neural network for 3-d pedestrian pose and gait prediction publication-title: IEEE Robot. Autom. Lett. – reference: Lin, M., Lin, L., Liang, X., Wang, K., Cheng, H., 2017. Recurrent 3d pose sequence machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 810–819. – reference: Mahmood, N., Ghorbani, N., Troje, N., Pons-Moll, G., Black, M.J., 2019. AMASS: Archive of motion capture as surface shapes. In: 2019 IEEE/CVF International Conference on Computer Vision, ICCV, pp. 5441–5450. – year: 2019 ident: b86 article-title: Camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image – volume: 34 start-page: 248 year: 2015 ident: b75 article-title: SMPL: A skinned multi-person linear model publication-title: ACM Trans. Graph. (TOG) – reference: Rhodin, H., Salzmann, M., Fua, P., 2018. Unsupervised geometry-aware representation for 3d human pose estimation. In: Proceedings of the European Conference on Computer Vision, ECCV. pp. 750–767. – reference: Siarohin, A., Sangineto, E., Lathuilière, S., Sebe, N., 2018. Deformable gans for pose-based human image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3408–3416. – volume: 19 start-page: 4 year: 2012 end-page: 10 ident: b162 article-title: Microsoft kinect sensor and its effect publication-title: IEEE multimedia – reference: Martinez, J., Hossain, R., Romero, J., Little, J.J., 2017. A simple yet effective baseline for 3d human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2640–2649. – year: 2019 ident: b19 article-title: Holistic++ scene understanding: Single-view 3D holistic scene parsing and human pose estimation with human-object interaction and physical commonsense – reference: Tekin, B., Márquez-Neila, P., Salzmann, M., Fua, P., 2017. Learning to fuse 2d and 3d image cues for monocular body pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 3941–3950. – reference: Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B., 2014b. 2D human pose estimation: New Benchmark and state of the art analysis. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition. pp. 3686–3693. – reference: Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M.J., Gehler, P.V., 2017. Unite the people: Closing the loop between 3d and 2d human representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6050–6059. – reference: Pavlakos, G., Kolotouros, N., Daniilidis, K., 2019. TexturePose: Supervising Human Mesh Estimation with Texture Consistency. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 803–812. – start-page: 3 year: 2017 ident: b144 article-title: Total capture: 3D human pose estimation fusing video and inertial sensors. publication-title: BMVC, vol. 2 – year: 2020 ident: b26 article-title: Monocular expressive body regression through body-driven attention – start-page: 474 year: 2018 end-page: 483 ident: b141 article-title: Rethinking pose in 3d: Multi-stage refinement and recovery for markerless motion capture publication-title: 2018 International Conference on 3D Vision (3DV) – reference: Fabbri, M., Lanzi, F., Calderara, S., Palazzi, A., Vezzani, R., Cucchiara, R., 2018. Learning to detect and track visible and occluded body joints in a virtual world. In: Proceedings of the European Conference on Computer Vision, ECCV. pp. 430–446. – reference: Hassan, M., Choutas, V., Tzionas, D., Black, M.J., 2019. Resolving 3D human pose ambiguities with 3D scene constrains. In: Proceedings IEEE International Conference on Computer Vision, ICCV. – start-page: 156 year: 2016 end-page: 169 ident: b97 article-title: 3D human pose estimation using convolutional neural networks with 2D pose information publication-title: European Conference on Computer Vision – year: 2017 ident: b145 article-title: Self-supervised learning of motion capture publication-title: NIPS – reference: Wandt, B., Rosenhahn, B., 2019. RepNet: Weakly supervised training of an adversarial reprojection network for 3D human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7782–7791. – reference: Zhou, K., Han, X., Jiang, N., Jia, K., Lu, J., 2019. HEMlets pose: Learning part-centric heatmap triplets for accurate 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2344–2353. – reference: Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B., 2014a. 2d human pose estimation: New benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3686–3693. – year: 2019 ident: b148 article-title: Not all parts are created equal: 3D pose estimation by modelling bi-directional dependencies of body parts – year: 2018 ident: b17 article-title: Openpose: realtime multi-person 2D pose estimation using part affinity fields – reference: Qiu, H., Wang, C., Wang, J., Wang, N., Zeng, W., 2019. Cross View Fusion for 3D Human Pose Estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 4342–4351. – volume: 192 year: 2020 ident: b21 article-title: Monocular human pose estimation: A survey of deep learning-based methods publication-title: Comput. Vis. Image Underst. – start-page: 120 year: 2018 end-page: 130 ident: b84 article-title: Single-shot multi-person 3d pose estimation from monocular rgb publication-title: 2018 International Conference on 3D Vision (3DV) – year: 2019 ident: b124 article-title: Monocular 3d human pose estimation by generation and ordinal ranking – start-page: 483 year: 2016 end-page: 499 ident: b89 article-title: Stacked hourglass networks for human pose estimation publication-title: European Conference on Computer Vision – reference: Coskun, H., Achilles, F., DiPietro, R., Navab, N., Tombari, F., 2017. Long short-term memory kalman filters: Recurrent neural estimators for pose regularization. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 5524–5532. – start-page: 1 year: 2009 end-page: 8 ident: b36 article-title: Pose search: retrieving people using their pose publication-title: 2009 IEEE Conference on Computer Vision and Pattern Recognition – reference: Belagiannis, V., Amin, S., Andriluka, M., Schiele, B., Navab, N., Ilic, S., 2014a. 3D pictorial structures for multiple human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1669–1676. – start-page: 3467 year: 2017 end-page: 3475 ident: b92 article-title: Monocular 3d human pose estimation by predicting depth on joints publication-title: 2017 IEEE International Conference on Computer Vision (ICCV) – reference: Weng, C.-Y., Curless, B., Kemelmacher-Shlizerman, I., 2019. Photo wake-up: 3d character animation from a single photo. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5908–5917. – volume: 53 start-page: 1975 year: 2019 end-page: 2021 ident: b64 article-title: Non-intrusive human activity recognition and abnormal behavior detection on elderly people: a review publication-title: Artif. Intell. Rev. – reference: Su, C., Li, J., Zhang, S., Xing, J., Gao, W., Tian, Q., 2017. Pose-driven deep convolutional model for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 3960–3969. – volume: 36 start-page: 1325 year: 2013 end-page: 1339 ident: b48 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. – reference: Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M., 2019. 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7753–7762. – reference: Trumble, M., Gilbert, A., Hilton, A., Collomosse, J., 2018. Deep autoencoder for combined human pose estimation and body model upscaling. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 784–800. – reference: Moreno-Noguer, F., 2017. 3d human pose estimation from a single image via distance matrix regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2823–2832. – reference: Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K., 2019b. Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV). pp. 2252–2261. – reference: Jack, D., Maire, F., Shirazi, S., Eriksson, A., 2019. IGE-Net: Inverse Graphics Energy Networks for Human Pose Estimation and Single-View Reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7075–7084. – reference: Rematas, K., Kemelmacher-Shlizerman, I., Curless, B., Seitz, S., 2018. Soccer on your tabletop. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4738–4747. – reference: Li, Y., Huang, C., Loy, C.C., 2019a. Dense intrinsic appearance flow for human pose transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3693–3702. – reference: Popa, A.-I., Zanfir, M., Sminchisescu, C., 2017. Deep multitask architecture for integrated 2d and 3d human sensing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6289–6298. – year: 2020 ident: b23 article-title: 3D Human pose estimation using spatio-temporal networks with explicit occlusion training publication-title: AAAI – reference: Tompson, J.J., Jain, A., LeCun, Y., Bregler, C., 2014. Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in Neural Information Processing Systems. pp. 1799–1807. – volume: 4 start-page: 1940 year: 2019 end-page: 1947 ident: b56 article-title: Pedx: Benchmark dataset for metric 3-D pose estimation of pedestrians in complex urban intersections publication-title: IEEE Robot. Autom. Lett. – reference: Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.N., 2019. Semantic graph convolutional networks for 3D human pose regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3425–3435. – start-page: 421 year: 2017 end-page: 430 ident: b45 article-title: Towards accurate marker-less human shape and pose estimation over time publication-title: 2017 International Conference on 3D Vision (3DV) – reference: He, K., Gkioxari, G., Dollár, P., Girshick, R., 2017. Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2961–2969. – volume: 87 start-page: 4 year: 2010 ident: b127 article-title: Humaneva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion publication-title: Int. J. Comput. Vis. – reference: Cai, Y., Ge, L., Liu, J., Cai, J., Cham, T.-J., Yuan, J., Thalmann, N.M., 2019. Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2272–2281. – volume: 35 start-page: 2878 year: 2012 end-page: 2890 ident: b159 article-title: Articulated human detection with flexible mixtures of parts publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: Joo, H., Simon, T., Sheikh, Y., 2018. Total capture: A 3d deformation model for tracking faces, hands, and bodies. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 8320–8329. – year: 2003 ident: b38 article-title: A bayesian approach to image-based visual hull reconstruction publication-title: 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings. vol. 1 – year: 2005 ident: b10 article-title: SCAPE: shape completion and animation of people publication-title: SIGGRAPH 2005 – reference: Wang, Z., Shin, D., Fowlkes, C.C., 2020. Predicting camera viewpoint improves cross-dataset generalization for 3D human pose estimation. In: ECCV Workshops. – reference: Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K., 2018. Learning to estimate 3D human pose and shape from a single color image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 459–468. – reference: Rogez, G., Weinzaepfel, P., Schmid, C., 2017. LCR-Net: Localization-classification-regression for human pose. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. pp. 1216–1224. – start-page: 561 year: 2016 end-page: 578 ident: b15 article-title: Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image publication-title: European Conference on Computer Vision – reference: Arnab, A., Doersch, C., Zisserman, A., 2019b. Exploiting temporal context for 3D human pose estimation in the wild. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 3390–3399. – reference: Chen, X., Lin, K.-Y., Liu, W., Qian, C., Lin, L., 2019b. Weakly-supervised discovery of geometry-aware representation for 3d human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 10895–10904. – year: 2019 ident: b164 article-title: Pose invariant embedding for deep person re-identification publication-title: IEEE Trans. Image Process. – volume: 16 start-page: 208 year: 2016 ident: b2 article-title: Vision-based pose estimation for robot-mediated hand telerehabilitation publication-title: Sensors – reference: Dong, J., Jiang, W., Huang, Q., Bao, H., Zhou, X., 2019. Fast and robust multi-person 3d pose estimation from multiple views. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7792–7801. – reference: Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P.V., Schiele, B., 2016. Deepcut: Joint subset partition and labeling for multi person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4929–4937. – year: 2020 ident: b87 article-title: I2l-meshnet: Image-to-lixel prediction network for accurate 3D human pose and mesh estimation from a single RGB image publication-title: ECCV – year: 2014 ident: b128 article-title: Very deep convolutional networks for large-scale image recognition – year: 2018 ident: b94 article-title: Survey on emotional body gesture recognition publication-title: IEEE Trans. Affect. Comput. – reference: Wei, S.-E., Ramakrishna, V., Kanade, T., Sheikh, Y., 2016. Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4724–4732. – reference: Habibie, I., Xu, W., Mehta, D., Pons-Moll, G., Theobalt, C., 2019. In the wild human pose estimation using explicit 2D features and intermediate 3D representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 10905–10914. – reference: Marinoiu, E., Zanfir, M., Olaru, V., Sminchisescu, C., 2018. 3d human sensing, action and emotion recognition in robot assisted therapy of children with autism. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2158–2167. – reference: Zecha, D., Einfalt, M., Eggert, C., Lienhart, R., 2018. Kinematic Pose Rectification for Performance Analysis and Retrieval in Sports. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. pp. 1791–1799. – reference: Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K., 2017a. Coarse-to-fine volumetric prediction for single-image 3D human pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7025–7034. – start-page: 20 year: 2016 end-page: 36 ident: b32 article-title: Marker-less 3d human motion capture with monocular image sequence and height-maps publication-title: European Conference on Computer Vision – reference: Lee, K., Lee, I., Lee, S., 2018. Propagating lstm: 3d pose estimation based on joint interdependency. In: Proceedings of the European Conference on Computer Vision, ECCV. pp. 119–135. – volume: 41 start-page: 190 year: 2017 end-page: 204 ident: b52 article-title: Panoptic studio: A massively multiview system for social interaction capture publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 33 start-page: 220 year: 2014 ident: b74 article-title: MoSh: Motion and shape capture from sparse markers publication-title: ACM Trans. Graph. – reference: Li, C., Lee, G.H., 2019. Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 9887–9895. – reference: Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J., 2018. End-to-end recovery of human shape and pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7122–7131. – reference: Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K., 2017b. Harvesting multiple views for marker-less 3d human pose annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6988–6997. – start-page: 1 year: 2008 end-page: 8 ident: b35 article-title: Progressive search space reduction for human pose estimation publication-title: 2008 IEEE Conference on Computer Vision and Pattern Recognition – reference: Zanfir, A., Marinoiu, E., Sminchisescu, C., 2018. Monocular 3d pose and shape estimation of multiple people in natural scenes-the importance of multiple scene constraints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2148–2157. – start-page: 484 year: 2018 end-page: 494 ident: b96 article-title: Neural body fitting: Unifying deep learning and model based human pose and shape estimation publication-title: 2018 International Conference on 3D Vision (3DV) – reference: Xu, J., Zhao, R., Zhu, F., Wang, H., Ouyang, W., 2018b. Attention-aware compositional network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2119–2128. – reference: Fish Tung, H.-Y., Harley, A.W., Seto, W., Fragkiadaki, K., 2017. Adversarial inverse graphics networks: learning 2D-to-3D lifting and image-to-image translation from unpaired supervision. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 4354–4362. – year: 2020 ident: b73 article-title: End-to-end human pose and mesh reconstruction with transformers – reference: Dabral, R., Mundhada, A., Kusupati, U., Afaque, S., Sharma, A., Jain, A., 2018. Learning 3d human pose from structure and motion. In: Proceedings of the European Conference on Computer Vision, ECCV. pp. 668–683. – year: 2014 ident: b135 article-title: Sequence to sequence learning with neural networks publication-title: NIPS – year: 2015 ident: b129 article-title: LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop – reference: Luvizon, D.C., Picard, D., Tabia, H., 2018. 2d/3d pose estimation and action recognition using multitask deep learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5137–5146. – reference: Krizhevsky, A., Sutskever, I., Hinton, G.E., 2012. Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems. pp. 1097–1105. – reference: Alp Güler, R., Neverova, N., Kokkinos, I., 2018. Densepose: Dense human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7297–7306. – year: 2014 ident: b72 article-title: Microsoft COCO: Common objects in context publication-title: ECCV – reference: Popov, S., Bauszat, P., Ferrari, V., 2020. CoReNet: Coherent 3D scene reconstruction from a single RGB image. In: ECCV. – start-page: 1243 year: 2011 end-page: 1250 ident: b106 article-title: Outdoor human motion capture using inverse kinematics and von mises-fisher sampling publication-title: 2011 International Conference on Computer Vision – reference: Novotny, D., Ravi, N., Graham, B., Neverova, N., Vedaldi, A., 2019. C3DPO: Canonical 3D pose networks for non-rigid structure from motion. In: Proceedings of the IEEE International Conference on Computer Vision. – reference: Rhodin, H., Robertini, N., Richardt, C., Seidel, H.-P., Theobalt, C., 2015. A versatile scene model with differentiable visibility applied to generative pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 765–773. – reference: Chen, C.-H., Tyagi, A., Agrawal, A., Drover, D., MV, R., Stojanov, S., Rehg, J.M., 2019a. Unsupervised 3D Pose Estimation with Geometric Self-Supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5714–5724. – reference: von Marcard, T., Henschel, R., Black, M.J., Rosenhahn, B., Pons-Moll, G., 2018. Recovering accurate 3d human pose in the wild using imus and a moving camera. In: Proceedings of the European Conference on Computer Vision, ECCV. pp. 601–617. – reference: Kocabas, M., Athanasiou, N., Black, M.J., 2020. VIBE: Video inference for human body pose and shape estimation. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5252–5262. – year: 2019 ident: b120 article-title: Lcr-net++: Multi-person 2d and 3d pose detection in natural images publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: Tome, D., Russell, C., Agapito, L., 2017. Lifting from the deep: Convolutional 3d pose estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2500–2509. – year: 2018 ident: b90 article-title: Numerical coordinate regression with convolutional neural networks – reference: Pavlakos, G., Zhou, X., Daniilidis, K., 2018. Ordinal depth supervision for 3d human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7307–7316. – reference: Xia, F., Zhu, J., Wang, P., Yuille, A.L., 2016. Pose-guided human parsing by an and/or graph using pose-context features. In: Thirtieth AAAI Conference on Artificial Intelligence. – volume: 32 start-page: 177 year: 2013 end-page: 186 ident: b46 article-title: Consistent shape maps via semidefinite programming publication-title: Comput. Graph. Forum – volume: 36 start-page: 73 year: 2017 ident: b107 article-title: Clothcap: Seamless 4D clothing capture and retargeting publication-title: ACM Trans. Graph. – volume: 39 start-page: 501 year: 2016 end-page: 514 ident: b33 article-title: MARCOnI—ConvNet-Based MARker-less motion capture in outdoor and indoor scenes publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2020 ident: b76 article-title: 3D Human motion estimation via motion compression and refinement – reference: Ci, H., Wang, C., Ma, X., Wang, Y., 2019. Optimizing network structure for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2262–2271. – year: 2020 ident: b152 article-title: Deepsfm: Structure from motion via deep bundle adjustment publication-title: ECCV – reference: Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K., 2019a. Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2252–2261. – reference: Rayat Imtiaz Hossain, M., Little, J.J., 2018. Exploiting temporal information for 3d human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 68–84. – year: 2019 ident: b58 article-title: Self-supervised learning of 3d human pose using multi-view geometry – reference: Zhou, X., Zhu, M., Leonardos, S., Derpanis, K.G., Daniilidis, K., 2016b. Sparseness meets deepness: 3D human pose estimation from monocular video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4966–4975. – volume: 126 start-page: 1326 year: 2018 end-page: 1341 ident: b55 article-title: Learning latent representations of 3d human pose with deep neural networks publication-title: Int. J. Comput. Vis. – start-page: 186 year: 2016 end-page: 201 ident: b167 article-title: Deep kinematic pose regression publication-title: European Conference on Computer Vision – reference: Sun, Y., Ye, Y., Liu, W., Gao, W., Fu, Y., Mei, T., 2019. Human mesh recovery from monocular images via a skeleton-disentangled representation. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV). pp. 5348–5357. – reference: Varol, G., Romero, J., Martin, X., Mahmood, N., Black, M.J., Laptev, I., Schmid, C., 2017. Learning from synthetic humans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 109–117. – reference: Akhter, I., Black, M.J., 2015. Pose-conditioned joint angle limits for 3D human pose reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1446–1455. – reference: Liang, J., Lin, M., 2019. Shape-aware human pose and shape reconstruction using multi-view images. In: 2019 IEEE/CVF International Conference on Computer Vision, ICCV. pp. 4351–4361. – year: 2015 ident: b136 article-title: Improved semantic representations from tree-structured long short-term memory networks – volume: 37 start-page: 27 year: 2018 ident: b155 article-title: Monoperfcap: Human performance capture from monocular video publication-title: ACM Trans. Graph. (ToG) – reference: Rhodin, H., Constantin, V., Katircioglu, I., Salzmann, M., Fua, P., 2019. Neural scene decomposition for multi-person motion capture. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). – ident: 10.1016/j.cviu.2021.103225_b149 doi: 10.1109/ICCV.2019.00083 – ident: 10.1016/j.cviu.2021.103225_b143 doi: 10.1007/978-3-030-01249-6_48 – volume: 37 start-page: 27 issue: 2 year: 2018 ident: 10.1016/j.cviu.2021.103225_b155 article-title: Monoperfcap: Human performance capture from monocular video publication-title: ACM Trans. Graph. (ToG) doi: 10.1145/3181973 – year: 2020 ident: 10.1016/j.cviu.2021.103225_b23 article-title: 3D Human pose estimation using spatio-temporal networks with explicit occlusion training – year: 2020 ident: 10.1016/j.cviu.2021.103225_b25 – start-page: 1 year: 2009 ident: 10.1016/j.cviu.2021.103225_b36 article-title: Pose search: retrieving people using their pose – ident: 10.1016/j.cviu.2021.103225_b20 doi: 10.1109/CVPR.2019.01115 – year: 2009 ident: 10.1016/j.cviu.2021.103225_b118 – ident: 10.1016/j.cviu.2021.103225_b41 doi: 10.1109/CVPR.2018.00787 – ident: 10.1016/j.cviu.2021.103225_b99 doi: 10.1109/CVPR.2018.00763 – year: 2014 ident: 10.1016/j.cviu.2021.103225_b135 article-title: Sequence to sequence learning with neural networks – year: 2020 ident: 10.1016/j.cviu.2021.103225_b26 – ident: 10.1016/j.cviu.2021.103225_b100 doi: 10.1109/CVPR.2017.139 – ident: 10.1016/j.cviu.2021.103225_b3 doi: 10.1109/CVPR.2015.7298751 – ident: 10.1016/j.cviu.2021.103225_b70 doi: 10.1109/CVPR.2017.588 – ident: 10.1016/j.cviu.2021.103225_b112 doi: 10.1109/CVPR.2018.00498 – ident: 10.1016/j.cviu.2021.103225_b166 doi: 10.1109/ICCV.2017.51 – ident: 10.1016/j.cviu.2021.103225_b157 doi: 10.1109/ICCV.2019.00785 – ident: 10.1016/j.cviu.2021.103225_b131 doi: 10.1109/ICCV.2017.427 – ident: 10.1016/j.cviu.2021.103225_b63 doi: 10.1007/978-3-030-01234-2_8 – volume: 19 start-page: 4 issue: 2 year: 2012 ident: 10.1016/j.cviu.2021.103225_b162 article-title: Microsoft kinect sensor and its effect publication-title: IEEE multimedia doi: 10.1109/MMUL.2012.24 – start-page: 20 year: 2016 ident: 10.1016/j.cviu.2021.103225_b32 article-title: Marker-less 3d human motion capture with monocular image sequence and height-maps – start-page: 332 year: 2014 ident: 10.1016/j.cviu.2021.103225_b65 article-title: 3d human pose estimation from monocular images with deep convolutional neural network – volume: 36 start-page: 73 issue: 4 year: 2017 ident: 10.1016/j.cviu.2021.103225_b107 article-title: Clothcap: Seamless 4D clothing capture and retargeting publication-title: ACM Trans. Graph. doi: 10.1145/3072959.3073711 – volume: 152 start-page: 1 year: 2016 ident: 10.1016/j.cviu.2021.103225_b121 article-title: 3d human pose estimation: A review of the literature and analysis of covariates publication-title: Comput. Vis. Image Underst. doi: 10.1016/j.cviu.2016.09.002 – ident: 10.1016/j.cviu.2021.103225_b103 doi: 10.1109/CVPR.2019.00794 – ident: 10.1016/j.cviu.2021.103225_b81 doi: 10.1109/CVPR.2018.00230 – ident: 10.1016/j.cviu.2021.103225_b60 doi: 10.1109/ICCV.2019.00234 – volume: 41 start-page: 190 issue: 1 year: 2017 ident: 10.1016/j.cviu.2021.103225_b52 article-title: Panoptic studio: A massively multiview system for social interaction capture publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2017.2782743 – ident: 10.1016/j.cviu.2021.103225_b54 doi: 10.1109/CVPR.2018.00744 – start-page: 474 year: 2018 ident: 10.1016/j.cviu.2021.103225_b141 article-title: Rethinking pose in 3d: Multi-stage refinement and recovery for markerless motion capture – ident: 10.1016/j.cviu.2021.103225_b11 doi: 10.1109/CVPR.2019.00351 – ident: 10.1016/j.cviu.2021.103225_b68 doi: 10.1109/ICCV.2019.00228 – ident: 10.1016/j.cviu.2021.103225_b5 doi: 10.1109/CVPR.2018.00762 – ident: 10.1016/j.cviu.2021.103225_b163 doi: 10.1109/CVPR.2019.00354 – volume: 36 start-page: 44 issue: 4 year: 2017 ident: 10.1016/j.cviu.2021.103225_b85 article-title: Vnect: Real-time 3d human pose estimation with a single rgb camera publication-title: ACM Trans. Graph. doi: 10.1145/3072959.3073596 – start-page: 951 year: 2011 ident: 10.1016/j.cviu.2021.103225_b130 article-title: Fast articulated motion tracking using a sums of gaussians body model – ident: 10.1016/j.cviu.2021.103225_b43 doi: 10.1109/ICCV.2017.322 – year: 2020 ident: 10.1016/j.cviu.2021.103225_b152 article-title: Deepsfm: Structure from motion via deep bundle adjustment – year: 2005 ident: 10.1016/j.cviu.2021.103225_b10 article-title: SCAPE: shape completion and animation of people – volume: 87 start-page: 4 year: 2009 ident: 10.1016/j.cviu.2021.103225_b126 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 – volume: 33 start-page: 220 issue: 6 year: 2014 ident: 10.1016/j.cviu.2021.103225_b74 article-title: MoSh: Motion and shape capture from sparse markers publication-title: ACM Trans. Graph. doi: 10.1145/2661229.2661273 – year: 2018 ident: 10.1016/j.cviu.2021.103225_b90 – ident: 10.1016/j.cviu.2021.103225_b101 doi: 10.1109/CVPR.2017.138 – ident: 10.1016/j.cviu.2021.103225_b59 doi: 10.1109/ICCV.2019.00234 – ident: 10.1016/j.cviu.2021.103225_b116 doi: 10.1007/978-3-030-01249-6_46 – volume: 35 start-page: 2878 issue: 12 year: 2012 ident: 10.1016/j.cviu.2021.103225_b159 article-title: Articulated human detection with flexible mixtures of parts publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2012.261 – volume: 34 start-page: 248 issue: 6 year: 2015 ident: 10.1016/j.cviu.2021.103225_b75 article-title: SMPL: A skinned multi-person linear model publication-title: ACM Trans. Graph. (TOG) doi: 10.1145/2816795.2818013 – ident: 10.1016/j.cviu.2021.103225_b105 doi: 10.1109/CVPR.2016.533 – ident: 10.1016/j.cviu.2021.103225_b151 doi: 10.1109/CVPR.2016.511 – start-page: 421 year: 2017 ident: 10.1016/j.cviu.2021.103225_b45 article-title: Towards accurate marker-less human shape and pose estimation over time – ident: 10.1016/j.cviu.2021.103225_b57 doi: 10.1109/CVPR42600.2020.00530 – start-page: 561 year: 2016 ident: 10.1016/j.cviu.2021.103225_b15 article-title: Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image – year: 2019 ident: 10.1016/j.cviu.2021.103225_b93 – ident: 10.1016/j.cviu.2021.103225_b77 doi: 10.1109/CVPR.2018.00539 – year: 2015 ident: 10.1016/j.cviu.2021.103225_b129 – ident: 10.1016/j.cviu.2021.103225_b69 doi: 10.1109/ICCV.2019.00445 – ident: 10.1016/j.cviu.2021.103225_b24 doi: 10.1109/ICCV.2019.00081 – ident: 10.1016/j.cviu.2021.103225_b82 doi: 10.1109/ICCV.2017.288 – year: 2019 ident: 10.1016/j.cviu.2021.103225_b58 – volume: 192 year: 2020 ident: 10.1016/j.cviu.2021.103225_b21 article-title: Monocular human pose estimation: A survey of deep learning-based methods publication-title: Comput. Vis. Image Underst. doi: 10.1016/j.cviu.2019.102897 – ident: 10.1016/j.cviu.2021.103225_b109 doi: 10.1007/978-3-030-58536-5_22 – start-page: 483 year: 2016 ident: 10.1016/j.cviu.2021.103225_b89 article-title: Stacked hourglass networks for human pose estimation – year: 2019 ident: 10.1016/j.cviu.2021.103225_b148 – ident: 10.1016/j.cviu.2021.103225_b98 doi: 10.1109/ICCV.2019.00089 – start-page: 742 year: 2014 ident: 10.1016/j.cviu.2021.103225_b14 article-title: Multiple human pose estimation with temporally consistent 3D pictorial structures – year: 2018 ident: 10.1016/j.cviu.2021.103225_b17 – volume: 39 start-page: 501 issue: 3 year: 2016 ident: 10.1016/j.cviu.2021.103225_b33 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 – ident: 10.1016/j.cviu.2021.103225_b160 doi: 10.1109/CVPR.2018.00229 – year: 2018 ident: 10.1016/j.cviu.2021.103225_b137 – ident: 10.1016/j.cviu.2021.103225_b12 doi: 10.1109/CVPR.2019.00351 – ident: 10.1016/j.cviu.2021.103225_b37 doi: 10.1109/ICCV.2017.467 – ident: 10.1016/j.cviu.2021.103225_b8 doi: 10.1109/CVPR.2014.471 – start-page: 1243 year: 2011 ident: 10.1016/j.cviu.2021.103225_b106 article-title: Outdoor human motion capture using inverse kinematics and von mises-fisher sampling – ident: 10.1016/j.cviu.2021.103225_b111 doi: 10.1007/978-3-030-01249-6_5 – ident: 10.1016/j.cviu.2021.103225_b113 doi: 10.1109/CVPR.2019.00789 – start-page: 506 year: 2017 ident: 10.1016/j.cviu.2021.103225_b83 article-title: Monocular 3d human pose estimation in the wild using improved cnn supervision – ident: 10.1016/j.cviu.2021.103225_b161 doi: 10.1109/CVPRW.2018.00232 – volume: 32 start-page: 177 issue: 5 year: 2013 ident: 10.1016/j.cviu.2021.103225_b46 article-title: Consistent shape maps via semidefinite programming publication-title: Comput. Graph. Forum doi: 10.1111/cgf.12184 – ident: 10.1016/j.cviu.2021.103225_b158 doi: 10.1109/CVPR.2018.00551 – ident: 10.1016/j.cviu.2021.103225_b7 doi: 10.1109/CVPR.2018.00542 – ident: 10.1016/j.cviu.2021.103225_b53 doi: 10.1109/CVPR.2018.00868 – start-page: 740 year: 2014 ident: 10.1016/j.cviu.2021.103225_b71 article-title: Microsoft coco: Common objects in context – ident: 10.1016/j.cviu.2021.103225_b27 doi: 10.1109/ICCV.2019.00235 – year: 2015 ident: 10.1016/j.cviu.2021.103225_b136 – ident: 10.1016/j.cviu.2021.103225_b9 doi: 10.1109/CVPR.2014.471 – ident: 10.1016/j.cviu.2021.103225_b34 doi: 10.1007/978-3-030-01225-0_27 – year: 2020 ident: 10.1016/j.cviu.2021.103225_b123 – ident: 10.1016/j.cviu.2021.103225_b132 doi: 10.1109/ICCV.2017.284 – ident: 10.1016/j.cviu.2021.103225_b61 – year: 2019 ident: 10.1016/j.cviu.2021.103225_b120 article-title: Lcr-net++: Multi-person 2d and 3d pose detection in natural images publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2019.2892985 – volume: 9 start-page: 1735 issue: 8 year: 1997 ident: 10.1016/j.cviu.2021.103225_b44 article-title: Long short-term memory publication-title: Neural Comput. doi: 10.1162/neco.1997.9.8.1735 – ident: 10.1016/j.cviu.2021.103225_b122 doi: 10.1109/ICCVW.2017.99 – volume: 123 start-page: 4 year: 2015 ident: 10.1016/j.cviu.2021.103225_b1 article-title: VQA: Visual question answering publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-016-0966-6 – ident: 10.1016/j.cviu.2021.103225_b133 doi: 10.1007/978-3-030-01231-1_33 – ident: 10.1016/j.cviu.2021.103225_b80 doi: 10.1007/978-3-030-01249-6_37 – ident: 10.1016/j.cviu.2021.103225_b110 doi: 10.1109/ICCV.2019.00444 – ident: 10.1016/j.cviu.2021.103225_b88 doi: 10.1109/CVPR.2017.170 – ident: 10.1016/j.cviu.2021.103225_b146 doi: 10.1109/CVPR.2017.492 – ident: 10.1016/j.cviu.2021.103225_b142 – ident: 10.1016/j.cviu.2021.103225_b102 doi: 10.1109/CVPR.2018.00055 – volume: 16 start-page: 208 issue: 2 year: 2016 ident: 10.1016/j.cviu.2021.103225_b2 article-title: Vision-based pose estimation for robot-mediated hand telerehabilitation publication-title: Sensors doi: 10.3390/s16020208 – year: 2020 ident: 10.1016/j.cviu.2021.103225_b87 article-title: I2l-meshnet: Image-to-lixel prediction network for accurate 3D human pose and mesh estimation from a single RGB image – start-page: 120 year: 2018 ident: 10.1016/j.cviu.2021.103225_b84 article-title: Single-shot multi-person 3d pose estimation from monocular rgb – ident: 10.1016/j.cviu.2021.103225_b6 doi: 10.1109/CVPR.2017.280 – start-page: 484 year: 2018 ident: 10.1016/j.cviu.2021.103225_b96 article-title: Neural body fitting: Unifying deep learning and model based human pose and shape estimation – ident: 10.1016/j.cviu.2021.103225_b134 doi: 10.1109/ICCV.2019.00545 – volume: 36 start-page: 1325 issue: 7 year: 2013 ident: 10.1016/j.cviu.2021.103225_b48 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 – volume: 126 start-page: 1326 issue: 12 year: 2018 ident: 10.1016/j.cviu.2021.103225_b55 article-title: Learning latent representations of 3d human pose with deep neural networks publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-018-1066-6 – year: 2014 ident: 10.1016/j.cviu.2021.103225_b72 article-title: Microsoft COCO: Common objects in context – ident: 10.1016/j.cviu.2021.103225_b91 doi: 10.1109/WACV.2019.00162 – ident: 10.1016/j.cviu.2021.103225_b119 doi: 10.1109/CVPR.2017.134 – year: 2019 ident: 10.1016/j.cviu.2021.103225_b124 – year: 2018 ident: 10.1016/j.cviu.2021.103225_b94 article-title: Survey on emotional body gesture recognition publication-title: IEEE Trans. Affect. Comput. – year: 2020 ident: 10.1016/j.cviu.2021.103225_b104 – year: 2020 ident: 10.1016/j.cviu.2021.103225_b76 – ident: 10.1016/j.cviu.2021.103225_b30 doi: 10.1109/CVPR.2019.00798 – ident: 10.1016/j.cviu.2021.103225_b13 doi: 10.1109/CVPR.2014.216 – volume: 4 start-page: 1940 issue: 2 year: 2019 ident: 10.1016/j.cviu.2021.103225_b56 article-title: Pedx: Benchmark dataset for metric 3-D pose estimation of pedestrians in complex urban intersections publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2019.2896705 – ident: 10.1016/j.cviu.2021.103225_b139 doi: 10.1109/CVPR.2016.113 – ident: 10.1016/j.cviu.2021.103225_b42 doi: 10.1109/ICCV.2019.00237 – ident: 10.1016/j.cviu.2021.103225_b79 doi: 10.1109/ICCV.2019.00554 – ident: 10.1016/j.cviu.2021.103225_b125 doi: 10.1109/CVPR.2018.00359 – ident: 10.1016/j.cviu.2021.103225_b115 doi: 10.1109/ICCV.2015.94 – ident: 10.1016/j.cviu.2021.103225_b22 doi: 10.1109/CVPR.2019.00586 – ident: 10.1016/j.cviu.2021.103225_b154 doi: 10.1609/aaai.v30i1.10460 – ident: 10.1016/j.cviu.2021.103225_b108 doi: 10.1109/CVPR.2017.501 – year: 2014 ident: 10.1016/j.cviu.2021.103225_b128 – volume: 4 start-page: 1501 issue: 2 year: 2019 ident: 10.1016/j.cviu.2021.103225_b31 article-title: Bio-lstm: A biomechanically inspired recurrent neural network for 3-d pedestrian pose and gait prediction publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2019.2895266 – ident: 10.1016/j.cviu.2021.103225_b168 doi: 10.1109/CVPR.2016.537 – ident: 10.1016/j.cviu.2021.103225_b95 doi: 10.1109/ICCV.2019.00778 – year: 2019 ident: 10.1016/j.cviu.2021.103225_b164 article-title: Pose invariant embedding for deep person re-identification publication-title: IEEE Trans. Image Process. – ident: 10.1016/j.cviu.2021.103225_b156 doi: 10.1109/CVPR.2018.00226 – ident: 10.1016/j.cviu.2021.103225_b66 doi: 10.1109/CVPR.2019.00381 – ident: 10.1016/j.cviu.2021.103225_b47 doi: 10.1109/CVPRW.2017.20 – ident: 10.1016/j.cviu.2021.103225_b147 doi: 10.1109/CVPR.2019.00797 – start-page: 3 year: 2017 ident: 10.1016/j.cviu.2021.103225_b144 article-title: Total capture: 3D human pose estimation fusing video and inertial sensors. – ident: 10.1016/j.cviu.2021.103225_b117 doi: 10.1109/CVPR.2018.00880 – volume: 85 start-page: 15 year: 2019 ident: 10.1016/j.cviu.2021.103225_b78 article-title: Human pose regression by combining indirect part detection and contextual information publication-title: Comput. Graph. doi: 10.1016/j.cag.2019.09.002 – ident: 10.1016/j.cviu.2021.103225_b29 doi: 10.1007/978-3-030-01240-3_41 – ident: 10.1016/j.cviu.2021.103225_b165 doi: 10.1109/ICCV.2019.00243 – start-page: 156 year: 2016 ident: 10.1016/j.cviu.2021.103225_b97 article-title: 3D human pose estimation using convolutional neural networks with 2D pose information – year: 2019 ident: 10.1016/j.cviu.2021.103225_b19 – ident: 10.1016/j.cviu.2021.103225_b40 doi: 10.1109/CVPR.2019.01116 – year: 2019 ident: 10.1016/j.cviu.2021.103225_b86 – start-page: 1 year: 2008 ident: 10.1016/j.cviu.2021.103225_b35 article-title: Progressive search space reduction for human pose estimation – ident: 10.1016/j.cviu.2021.103225_b50 doi: 10.1109/CVPR.2019.00724 – start-page: 186 year: 2016 ident: 10.1016/j.cviu.2021.103225_b167 article-title: Deep kinematic pose regression – volume: 31 start-page: 17 issue: 2 year: 2012 ident: 10.1016/j.cviu.2021.103225_b4 article-title: Bilinear spatiotemporal basis models publication-title: ACM Trans. Graph. doi: 10.1145/2159516.2159523 – ident: 10.1016/j.cviu.2021.103225_b138 doi: 10.1109/ICCV.2017.425 – ident: 10.1016/j.cviu.2021.103225_b16 doi: 10.1109/ICCV.2019.00236 – ident: 10.1016/j.cviu.2021.103225_b62 doi: 10.1109/CVPR.2017.500 – volume: 53 start-page: 1975 year: 2019 ident: 10.1016/j.cviu.2021.103225_b64 article-title: Non-intrusive human activity recognition and abnormal behavior detection on elderly people: a review publication-title: Artif. Intell. Rev. doi: 10.1007/s10462-019-09724-5 – ident: 10.1016/j.cviu.2021.103225_b150 doi: 10.1007/978-3-030-66096-3_36 – volume: 2 start-page: 5 issue: 4 year: 2010 ident: 10.1016/j.cviu.2021.103225_b51 article-title: Clustered pose and nonlinear appearance models for human pose estimation publication-title: Bmvc – start-page: 3467 year: 2017 ident: 10.1016/j.cviu.2021.103225_b92 article-title: Monocular 3d human pose estimation by predicting depth on joints – ident: 10.1016/j.cviu.2021.103225_b39 – ident: 10.1016/j.cviu.2021.103225_b18 doi: 10.1109/CVPR.2017.143 – ident: 10.1016/j.cviu.2021.103225_b153 doi: 10.1109/CVPR.2019.00606 – ident: 10.1016/j.cviu.2021.103225_b140 doi: 10.1109/CVPR.2017.603 – year: 2017 ident: 10.1016/j.cviu.2021.103225_b145 article-title: Self-supervised learning of motion capture – volume: 87 start-page: 4 issue: 1–2 year: 2010 ident: 10.1016/j.cviu.2021.103225_b127 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: 2020 ident: 10.1016/j.cviu.2021.103225_b73 – year: 2019 ident: 10.1016/j.cviu.2021.103225_b49 – ident: 10.1016/j.cviu.2021.103225_b28 doi: 10.1109/ICCV.2017.589 – start-page: 509 year: 2016 ident: 10.1016/j.cviu.2021.103225_b114 article-title: General automatic human shape and motion capture using volumetric contour cues – ident: 10.1016/j.cviu.2021.103225_b67 doi: 10.1109/CVPR.2019.01012 – year: 2003 ident: 10.1016/j.cviu.2021.103225_b38 article-title: A bayesian approach to image-based visual hull reconstruction |
| SSID | ssj0011491 |
| Score | 2.6792161 |
| Snippet | Three-dimensional (3D) human pose estimation involves estimating the articulated 3D joint locations of a human body from an image or video. Due to its... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 103225 |
| SubjectTerms | 3D Human Pose Estimation Deep Learning |
| Title | Deep 3D human pose estimation: A review |
| URI | https://dx.doi.org/10.1016/j.cviu.2021.103225 |
| Volume | 210 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEA6lXvTgoyrWR8lB8CCxzeaxWW-ltVTFXrTQ25LNZqEi7WJbj_52M7vZUkF68LhDZlmGycyX7Mx8CF0nMolSoyxhSqWER9SSSIaaZEoHxlInLFgUXkZyOOZPEzGpoV7VCwNllT72lzG9iNZe0vbWbOfTafvVHVxCBlcYcEUtI4jDnIfg5Xff6zIPB_cL1jxYTGC1b5wpa7zM13TlzogBhd7zAOiy_0pOGwlncIj2PVLE3fJjjlDNzhrowKNG7PfkwokqYoZK1kB7G1MGj9FN39ocsz4u-PhwPl9YDLM1yqbFe9zFZf_KCRoPHt56Q-L5EYhhnC-JEDZx6CiVMqJcJMZQaSlTaSYc6GO6k5mMdpSBme7C8NBwRWVqtGWZNoFWnJ2i-mw-s2cI06CThS6bh1Iqrl0UixL4r821YO79gWkiWhkmNn54OHBYfMRVldh7DMaMwZhxacwmul3r5OXojK2rRWXv-JcDxC62b9E7_6feBdqFp7Jc7BLVl58re-XwxTJpFQ7UQjvdx-fh6Adp48sA |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb8IwDLYQHLYd9mCbxp45TNphqiDNo-luCIbKeFwGEreqTVOJaQI0YL9_CUkRkyYOu7p1VVnJZzux_QE8pjwNMymUR4TIPBpi5YU8SLxcJL5UWAs3LAqDIY_G9G3CJiVoFb0wpqzSYb_F9A1aO0ndWbO-mE7r7zpxCYg5wjBH1DzUOFwx06lYGSrNbi8abi8TdBKAbemhOZKjvuudsWVe8nu61mmij037uW8Ys__yTzs-p3MKxy5YRE37P2dQUrMqnLjAEbltudSigpuhkFXhaGfQ4Dk8tZVaINJGG0o-tJgvFTLjNWzf4gtqItvCcgHjzuuoFXmOIsGThNKVx5hKdYCUcR5iylIpMVeYiCxnOu4jSSOXOW4Iaca6M0kDSQXmmUwUyRPpJ4KSSyjP5jN1BQj7jTzQDj3gXNBEA1mYmqttmjCiv-_LGuDCMLF088MNjcVnXBSKfcTGmLExZmyNWYPnrc7CTs_Y-zYr7B3_WgOxhvc9etf_1HuAg2g06Mf97rB3A4fmia0eu4Xy6mut7nS4sUrv3XL6AX0kzbE |
| 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=Deep+3D+human+pose+estimation%3A+A+review&rft.jtitle=Computer+vision+and+image+understanding&rft.au=Wang%2C+Jinbao&rft.au=Tan%2C+Shujie&rft.au=Zhen%2C+Xiantong&rft.au=Xu%2C+Shuo&rft.date=2021-09-01&rft.issn=1077-3142&rft.volume=210&rft.spage=103225&rft_id=info:doi/10.1016%2Fj.cviu.2021.103225&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_cviu_2021_103225 |
| 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 |