{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T16:26:58Z","timestamp":1775752018349,"version":"3.50.1"},"reference-count":263,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,11,19]],"date-time":"2022-11-19T00:00:00Z","timestamp":1668816000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,19]],"date-time":"2022-11-19T00:00:00Z","timestamp":1668816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1007\/s13735-022-00261-6","type":"journal-article","created":{"date-parts":[[2022,11,19]],"date-time":"2022-11-19T14:02:45Z","timestamp":1668866565000},"page":"489-521","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Human pose estimation using deep learning: review, methodologies, progress and future research directions"],"prefix":"10.1007","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6167-9884","authenticated-orcid":false,"given":"Pranjal","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddhartha","family":"Chauhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lalit Kumar","family":"Awasthi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,19]]},"reference":[{"key":"261_CR1","unstructured":"Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1110\u20131118"},{"key":"261_CR2","doi-asserted-by":"crossref","unstructured":"Li M, Chen S, Chen X, Zhang Y, Wang Y, Tian Q (2019) Actional-structural graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3595\u20133603","DOI":"10.1109\/CVPR.2019.00371"},{"key":"261_CR3","doi-asserted-by":"crossref","unstructured":"Yan A, Wang Y, Li Z, Qiao Y (2019) Pa3d: pose-action 3d machine for video recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7922\u20137931","DOI":"10.1109\/CVPR.2019.00811"},{"key":"261_CR4","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.patcog.2019.03.010","volume":"92","author":"L Huang","year":"2019","unstructured":"Huang L, Huang Y, Ouyang W, Wang L (2019) Part-aligned pose-guided recurrent network for action recognition. Pattern Recogn 92:165\u2013176","journal-title":"Pattern Recogn"},{"key":"261_CR5","doi-asserted-by":"crossref","unstructured":"Luvizon DC, 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\u20135146","DOI":"10.1109\/CVPR.2018.00539"},{"key":"261_CR6","doi-asserted-by":"crossref","unstructured":"Choi H, Moon G, Lee KM (2020) Pose2mesh: graph convolutional network for 3d human pose and mesh recovery from a 2d human pose. In: European conference on computer vision. Springer, pp 769\u2013787","DOI":"10.1007\/978-3-030-58571-6_45"},{"key":"261_CR7","doi-asserted-by":"crossref","unstructured":"Kundu JN, Rakesh M, Jampani V, Venkatesh RM, Venkatesh Babu R (2020) Appearance consensus driven self-supervised human mesh recovery. In: European conference on computer vision. Springer, pp 794\u2013812","DOI":"10.1007\/978-3-030-58452-8_46"},{"key":"261_CR8","doi-asserted-by":"crossref","unstructured":"Samet N, Akbas E (2021) Hprnet: hierarchical point regression for whole-body human pose estimation. arXiv preprint arXiv:2106.04269","DOI":"10.1016\/j.imavis.2021.104285"},{"key":"261_CR9","doi-asserted-by":"crossref","unstructured":"Kanazawa A, Black MJ, Jacobs DW, 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\u20137131","DOI":"10.1109\/CVPR.2018.00744"},{"key":"261_CR10","unstructured":"Cimen G, Maurhofer C, Sumner B, Guay M (2018) Ar poser: automatically augmenting mobile pictures with digital avatars imitating poses. In: 12th international conference on computer graphics, visualization, computer vision and image processing"},{"key":"261_CR11","doi-asserted-by":"crossref","unstructured":"Elhayek A, Kovalenko O, Murthy P, Malik J, Stricker D (2018) Fully automatic multi-person human motion capture for vr applications. In: International conference on virtual reality and augmented reality. Springer, pp 28\u201347","DOI":"10.1007\/978-3-030-01790-3_3"},{"key":"261_CR12","doi-asserted-by":"crossref","unstructured":"Tzimiropoulos G (2015) Project-out cascaded regression with an application to face alignment. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3659\u20133667","DOI":"10.1109\/CVPR.2015.7298989"},{"key":"261_CR13","doi-asserted-by":"crossref","unstructured":"Terven JR, C\u00f3rdova-Esparza DM (2021) Kinz an azure kinect toolkit for python and matlab. Sci Comput Program 102702","DOI":"10.1016\/j.scico.2021.102702"},{"issue":"12","key":"261_CR14","doi-asserted-by":"publisher","first-page":"5756","DOI":"10.3390\/app11125756","volume":"11","author":"M T\u00f6lgyessy","year":"2021","unstructured":"T\u00f6lgyessy M, Dekan M, Chovanec L (2021) Skeleton tracking accuracy and precision evaluation of kinect v1, kinect v2, and the azure kinect. Appl Sci 11(12):5756","journal-title":"Appl Sci"},{"key":"261_CR15","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.patrec.2021.03.028","volume":"147","author":"L Kumarapu","year":"2021","unstructured":"Kumarapu L, Mukherjee P (2021) Animepose: multi-person 3d pose estimation and animation. Pattern Recogn Lett 147:16\u201324","journal-title":"Pattern Recogn Lett"},{"key":"261_CR16","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"261_CR17","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28:91\u201399","journal-title":"Adv Neural Inf Process Syst"},{"key":"261_CR18","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097\u20131105","journal-title":"Adv Neural Inf Process Syst"},{"key":"261_CR19","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer vision - ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Lawrence ZC (2014) Microsoft coco: common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision - ECCV 2014. Springer, Cham, pp 740\u2013755"},{"issue":"1","key":"261_CR20","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TPAMI.2017.2782743","volume":"41","author":"H Joo","year":"2017","unstructured":"Joo H, Simon T, Li X, Liu H, Tan L, Gui L, Banerjee S, Godisart T, Nabbe B, Matthews I et al (2017) Panoptic studio: a massively multiview system for social interaction capture. IEEE Trans Pattern Anal Mach Intell 41(1):190\u2013204","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"261_CR21","doi-asserted-by":"crossref","unstructured":"Mehta D, Rhodin H, Casas D, Fua P, Sotnychenko O, Xu W, Theobalt C (2017) Monocular 3d human pose estimation in the wild using improved cnn supervision. In: 2017 international conference on 3D vision (3DV). IEEE, pp 506\u2013516","DOI":"10.1109\/3DV.2017.00064"},{"issue":"6","key":"261_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper M, Mahmood N, Romero J, Pons-Moll G, Black MJ (2015) Smpl: a skinned multi-person linear model. ACM transactions on graphics (TOG) 34(6):1\u201316","journal-title":"ACM transactions on graphics (TOG)"},{"key":"261_CR23","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905), volume\u00a01. IEEE, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"261_CR24","doi-asserted-by":"crossref","unstructured":"Bourdev L, Malik J (2009) Poselets: body part detectors trained using 3d human pose annotations. In: 2009 IEEE 12th international conference on computer vision, pp 1365\u20131372","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"261_CR25","doi-asserted-by":"crossref","unstructured":"Bourdev L, Maji S, Brox T, Malik J (2010) Detecting people using mutually consistent poselet activations. In: European conference on computer vision. Springer, pp 168\u2013181","DOI":"10.1007\/978-3-642-15567-3_13"},{"key":"261_CR26","doi-asserted-by":"crossref","unstructured":"Song L, Yu G, Yuan J, Liu Z (2021) Human pose estimation and its application to action recognition: a survey. J Vis Commun Image Represent, 103055","DOI":"10.1016\/j.jvcir.2021.103055"},{"issue":"1","key":"261_CR27","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1023\/B:VISI.0000042934.15159.49","volume":"61","author":"PF Felzenszwalb","year":"2005","unstructured":"Felzenszwalb PF, Huttenlocher DP (2005) Pictorial structures for object recognition. Int J Comput Vis 61(1):55\u201379","journal-title":"Int J Comput Vis"},{"key":"261_CR28","first-page":"1385","volume":"2011","author":"Y Yang","year":"2011","unstructured":"Yang Y, Ramanan D (2011) Articulated pose estimation with flexible mixtures-of-parts. CVPR 2011:1385\u20131392","journal-title":"CVPR"},{"key":"261_CR29","doi-asserted-by":"crossref","unstructured":"Wang C, Wang Y, Yuille AL (2013) An approach to pose-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 915\u2013922","DOI":"10.1109\/CVPR.2013.123"},{"key":"261_CR30","doi-asserted-by":"crossref","unstructured":"Li D, Chen X, Zhang Z, Huang K (2018) Pose guided deep model for pedestrian attribute recognition in surveillance scenarios. In: 2018 IEEE international conference on multimedia and expo (ICME). IEEE, pp 1\u20136","DOI":"10.1109\/ICME.2018.8486604"},{"key":"261_CR31","doi-asserted-by":"crossref","unstructured":"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\u20134732","DOI":"10.1109\/CVPR.2016.511"},{"key":"261_CR32","doi-asserted-by":"crossref","unstructured":"Xiao B, Wu H, Wei Y (2018) Simple baselines for human pose estimation and tracking. In: Proceedings of the European conference on computer vision (ECCV), pp 466\u2013481","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"261_CR33","doi-asserted-by":"crossref","unstructured":"Sun K, Xiao B, Liu D, Wang J (2019) Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5693\u20135703","DOI":"10.1109\/CVPR.2019.00584"},{"key":"261_CR34","doi-asserted-by":"crossref","unstructured":"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\u20137299","DOI":"10.1109\/CVPR.2017.143"},{"key":"261_CR35","unstructured":"Newell A, Huang Z, Deng J (2016) Associative embedding: end-to-end learning for joint detection and grouping. arXiv preprint arXiv:1611.05424"},{"key":"261_CR36","doi-asserted-by":"crossref","unstructured":"Cheng B, Xiao B, Wang J, Shi H, Huang TS, Zhang L (2020) Higherhrnet: scale-aware representation learning for bottom-up human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5386\u20135395","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"261_CR37","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.jvcir.2015.06.013","volume":"32","author":"Z Liu","year":"2015","unstructured":"Liu Z, Zhu J, Jiajun B, Chen C (2015) A survey of human pose estimation: the body parts parsing based methods. J Vis Commun Image Represent 32:10\u201319","journal-title":"J Vis Commun Image Represent"},{"issue":"12","key":"261_CR38","doi-asserted-by":"publisher","first-page":"1966","DOI":"10.3390\/s16121966","volume":"16","author":"W Gong","year":"2016","unstructured":"Gong W, Zhang X, Gonz\u00e0lez J, Sobral A, Bouwmans T, Changhe T, Zahzah E (2016) Human pose estimation from monocular images: a comprehensive survey. Sensors 16(12):1966","journal-title":"Sensors"},{"key":"261_CR39","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: European conference on computer vision. Springer, pp 483\u2013499","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"261_CR40","doi-asserted-by":"crossref","unstructured":"Fang H-S, Xie S, Tai Y-W, Lu C (2017) Rmpe: regional multi-person pose estimation. In: Proceedings of the IEEE international conference on computer vision, pp 2334\u20132343","DOI":"10.1109\/ICCV.2017.256"},{"key":"261_CR41","doi-asserted-by":"crossref","unstructured":"Jin S, Xu L, Xu J, Wang C, Liu W, Qian C, Ouyang W, Luo P (2020) Whole-body human pose estimation in the wild. In: European conference on computer vision. Springer, pp 196\u2013214","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"261_CR42","doi-asserted-by":"crossref","unstructured":"Liu W, Chen J, Li C, Qian C, Chu X, Hu X (2018) A cascaded inception of inception network with attention modulated feature fusion for human pose estimation. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12334"},{"key":"261_CR43","doi-asserted-by":"crossref","unstructured":"Duan H, Lin K-Y, Jin S, Liu W, Qian C, Ouyang W (2019) Trb: a novel triplet representation for understanding 2d human body. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9479\u20139488","DOI":"10.1109\/ICCV.2019.00957"},{"key":"261_CR44","doi-asserted-by":"crossref","unstructured":"Kreiss S, Bertoni L, Alahi A (2019) Pifpaf: composite fields for human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11977\u201311986","DOI":"10.1109\/CVPR.2019.01225"},{"key":"261_CR45","doi-asserted-by":"crossref","unstructured":"Jin S, Liu W, Xie E, Wang W, Qian C, Ouyang W, Luo P (2020) Differentiable hierarchical graph grouping for multi-person pose estimation. In: European conference on computer vision. Springer, pp 718\u2013734","DOI":"10.1007\/978-3-030-58571-6_42"},{"key":"261_CR46","doi-asserted-by":"crossref","unstructured":"Jin S, Liu W, Ouyang W, Qian C (2019) Multi-person articulated tracking with spatial and temporal embeddings. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5664\u20135673","DOI":"10.1109\/CVPR.2019.00581"},{"issue":"3","key":"261_CR47","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1080\/10798587.2015.1095419","volume":"22","author":"H-B Zhang","year":"2016","unstructured":"Zhang H-B, Lei Q, Zhong B-N, Du J-X, Peng J (2016) A survey on human pose estimation. Intell Autom Soft Comput 22(3):483\u2013489","journal-title":"Intell Autom Soft Comput"},{"key":"261_CR48","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.neucom.2015.09.116","volume":"187","author":"Y Guo","year":"2016","unstructured":"Guo Y, Liu Y, Oerlemans A, Lao S, Wu S, Lew MS (2016) Deep learning for visual understanding: a review. Neurocomputing 187:27\u201348","journal-title":"Neurocomputing"},{"issue":"6","key":"261_CR49","doi-asserted-by":"publisher","first-page":"663","DOI":"10.26599\/TST.2018.9010100","volume":"24","author":"Q Dang","year":"2019","unstructured":"Dang Q, Yin J, Wang B, Zheng W (2019) Deep learning based 2d human pose estimation: a survey. Tsinghua Sci Technol 24(6):663\u2013676","journal-title":"Tsinghua Sci Technol"},{"key":"261_CR50","doi-asserted-by":"crossref","unstructured":"Wang P, Li W, Ogunbona P, Wan J (2018) and Sergio Escalera. A survey, Rgb-d-based human motion recognition with deep learning","DOI":"10.1016\/j.cviu.2018.04.007"},{"key":"261_CR51","doi-asserted-by":"publisher","first-page":"133330","DOI":"10.1109\/ACCESS.2020.3010248","volume":"8","author":"TL Munea","year":"2020","unstructured":"Munea TL, Jembre YZ, Weldegebriel HT, Chen L, Huang C, Yang C (2020) The progress of human pose estimation: a survey and taxonomy of models applied in 2d human pose estimation. IEEE Access 8:133330\u2013133348","journal-title":"IEEE Access"},{"key":"261_CR52","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102897","volume":"192","author":"Y Chen","year":"2020","unstructured":"Chen Y, Tian Y, He M (2020) Monocular human pose estimation: a survey of deep learning-based methods. Comput Vis Image Underst 192:102897","journal-title":"Comput Vis Image Underst"},{"key":"261_CR53","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"261_CR54","doi-asserted-by":"crossref","unstructured":"Papandreou G, Zhu T, Kanazawa N, Toshev A, Tompson J, Bregler C, Murphy K (2017) Towards accurate multi-person pose estimation in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4903\u20134911","DOI":"10.1109\/CVPR.2017.395"},{"key":"261_CR55","doi-asserted-by":"crossref","unstructured":"Luo Z, Wang Z, Huang Y, Wang L, Tan T, Zhou E (2021) Rethinking the heatmap regression for bottom-up human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13264\u201313273","DOI":"10.1109\/CVPR46437.2021.01306"},{"key":"261_CR56","doi-asserted-by":"crossref","unstructured":"Johnson S, Everingham M (2010) Clustered pose and nonlinear appearance models for human pose estimation. In: bmvc, vol\u00a02, p\u00a05. Citeseer","DOI":"10.5244\/C.24.12"},{"key":"261_CR57","doi-asserted-by":"crossref","unstructured":"Tang W, Wu Y (2019) Does learning specific features for related parts help human pose estimation? In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1107\u20131116","DOI":"10.1109\/CVPR.2019.00120"},{"key":"261_CR58","doi-asserted-by":"crossref","unstructured":"Sapp B, Taskar B (2013) Modec: multimodal decomposable models for human pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3674\u20133681","DOI":"10.1109\/CVPR.2013.471"},{"key":"261_CR59","doi-asserted-by":"crossref","unstructured":"Andriluka M, Pishchulin L, Gehler P, Schiele B (2014) 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\u20133693","DOI":"10.1109\/CVPR.2014.471"},{"key":"261_CR60","doi-asserted-by":"crossref","unstructured":"Nie X, Feng J, Xing J, Yan S (2018) Pose partition networks for multi-person pose estimation. In: Proceedings of the European conference on computer vision (eccv), pp 684\u2013699","DOI":"10.1007\/978-3-030-01228-1_42"},{"key":"261_CR61","doi-asserted-by":"crossref","unstructured":"Li J, Wang C, Zhu H, Mao Y, Fang H-S, Lu C (2019) Crowdpose: efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10863\u201310872","DOI":"10.1109\/CVPR.2019.01112"},{"key":"261_CR62","doi-asserted-by":"crossref","unstructured":"Tian C, Yu R, Zhao X, Xia W, Wang H, Yang Y (2021) Posedet: fast multi-person pose estimation using pose embedding. In: 2021 16th IEEE international conference on automatic face and gesture recognition (FG 2021). IEEE, pp 1\u20138","DOI":"10.1109\/FG52635.2021.9667045"},{"key":"261_CR63","doi-asserted-by":"crossref","unstructured":"Geng Z, Sun K, Xiao B, Zhang Z, Wang J (2021) Bottom-up human pose estimation via disentangled keypoint regression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14676\u201314686","DOI":"10.1109\/CVPR46437.2021.01444"},{"key":"261_CR64","doi-asserted-by":"crossref","unstructured":"Zhang W, Zhu M, Derpanis KG (2013) From actemes to action: a strongly-supervised representation for detailed action understanding. In: Proceedings of the IEEE international conference on computer vision, pp 2248\u20132255","DOI":"10.1109\/ICCV.2013.280"},{"key":"261_CR65","unstructured":"Artacho B, Savakis A (2021) Omnipose: a multi-scale framework for multi-person pose estimation. arXiv preprint arXiv:2103.10180"},{"key":"261_CR66","unstructured":"Yang D, Wang Y, Dantcheva A, Garattoni L, Francesca G, Bremond F (2021) Unik: a unified framework for real-world skeleton-based action recognition. arXiv preprint arXiv:2107.08580"},{"key":"261_CR67","doi-asserted-by":"crossref","unstructured":"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\u20135176","DOI":"10.1109\/CVPR.2018.00542"},{"key":"261_CR68","doi-asserted-by":"crossref","unstructured":"Liu Z, Feng R, Chen H, Wu S, Gao Y, Gao Y, Wang X (2022) Temporal feature alignment and mutual information maximization for video-based human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11006\u201311016","DOI":"10.1109\/CVPR52688.2022.01073"},{"key":"261_CR69","doi-asserted-by":"crossref","unstructured":"Kreiss S, Bertoni L, Alahi A (2021) Openpifpaf: composite fields for semantic keypoint detection and spatio-temporal association. IEEE Trans Intell Transport Syst","DOI":"10.1109\/TITS.2021.3124981"},{"issue":"7","key":"261_CR70","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2013","unstructured":"Ionescu C, Papava D, Olaru V, Sminchisescu C (2013) Human 3.6m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans Pattern Anal Mach Intell 36(7):1325\u20131339","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"261_CR71","doi-asserted-by":"crossref","unstructured":"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\u2013545","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"261_CR72","doi-asserted-by":"crossref","unstructured":"S\u00e1r\u00e1ndi I, Linder T, Arras KO, Leibe B (2020) Metric-scale truncation-robust heatmaps for 3d human pose estimation. In: 2020 15th IEEE international conference on automatic face and gesture recognition (FG 2020). IEEE, pp 407\u2013414","DOI":"10.1109\/FG47880.2020.00108"},{"key":"261_CR73","doi-asserted-by":"crossref","unstructured":"Li S, Ke L, Pratama K, Tai Y-W, Tang C-K, Cheng K-T (2020) Cascaded deep monocular 3d human pose estimation with evolutionary training data. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6173\u20136183","DOI":"10.1109\/CVPR42600.2020.00621"},{"key":"261_CR74","doi-asserted-by":"crossref","unstructured":"Zhao L, Peng X, Tian Y, Kapadia M, Metaxas DN (2019) Semantic graph convolutional networks for 3d human pose regression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3425\u20133435","DOI":"10.1109\/CVPR.2019.00354"},{"key":"261_CR75","doi-asserted-by":"crossref","unstructured":"Arnab A, Doersch C, Zisserman A (2019) Exploiting temporal context for 3d human pose estimation in the wild. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3395\u20133404","DOI":"10.1109\/CVPR.2019.00351"},{"key":"261_CR76","doi-asserted-by":"crossref","unstructured":"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\u20135264","DOI":"10.1109\/CVPR.2018.00551"},{"key":"261_CR77","doi-asserted-by":"crossref","unstructured":"Joo H, Liu H, Tan L, Gui L, Nabbe B, Matthews I, Kanade T, Nobuhara S, Sheikh Y (2015) Panoptic studio: a massively multiview system for social motion capture. In: Proceedings of the IEEE international conference on computer vision, pp 3334\u20133342","DOI":"10.1109\/ICCV.2015.381"},{"key":"261_CR78","doi-asserted-by":"crossref","unstructured":"Tu H, Wang C, Zeng W (2020) Voxelpose: towards multi-camera 3d human pose estimation in wild environment. In: Computer vision\u2014ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16. Springer, pp 197\u2013212","DOI":"10.1007\/978-3-030-58452-8_12"},{"key":"261_CR79","doi-asserted-by":"crossref","unstructured":"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). IEEE, pp 1477\u20131485","DOI":"10.1109\/WACV.2019.00162"},{"key":"261_CR80","doi-asserted-by":"crossref","unstructured":"Mehta D, Sotnychenko O, Mueller F, Xu W, Sridhar S, Pons-Moll G, Theobalt C (2018) Single-shot multi-person 3d pose estimation from monocular rgb. In: 2018 international conference on 3D vision (3DV). IEEE, pp 120\u2013130","DOI":"10.1109\/3DV.2018.00024"},{"key":"261_CR81","doi-asserted-by":"crossref","unstructured":"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\/CVF international conference on computer vision, pp 2344\u20132353","DOI":"10.1109\/ICCV.2019.00243"},{"key":"261_CR82","doi-asserted-by":"crossref","unstructured":"Trumble M, Gilbert A, Malleson C, Hilton A, Collomosse J (2017) Total capture: 3d human pose estimation fusing video and inertial sensors. In: Proceedings of 28th British machine vision conference, pp 1\u201313. University of Surrey","DOI":"10.5244\/C.31.14"},{"issue":"4","key":"261_CR83","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459786","volume":"40","author":"X Yi","year":"2021","unstructured":"Yi X, Zhou Y, Feng X (2021) Transpose: real-time 3d human translation and pose estimation with six inertial sensors. ACM Trans Gr 40(4):1\u201313","journal-title":"ACM Trans Gr"},{"issue":"3","key":"261_CR84","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1007\/s11263-020-01398-9","volume":"129","author":"Z Zhang","year":"2021","unstructured":"Zhang Z, Wang C, Qiu W, Qin W, Zeng W (2021) Adafuse: adaptive multiview fusion for accurate human pose estimation in the wild. Int J Comput Vis 129(3):703\u2013718","journal-title":"Int J Comput Vis"},{"key":"261_CR85","doi-asserted-by":"crossref","unstructured":"Varol G, Romero J, Martin X, Mahmood N, Black MJ, Laptev I, Schmid C (2017) Learning from synthetic humans. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 109\u2013117","DOI":"10.1109\/CVPR.2017.492"},{"key":"261_CR86","unstructured":"Leinen F, Cozzolino V, Sch\u00f6n T (2021) Volnet: estimating human body part volumes from a single rgb image. arXiv preprint arXiv:2107.02259"},{"key":"261_CR87","doi-asserted-by":"crossref","unstructured":"Lassner C, Romero J, Kiefel M, Bogo F, Black MJ, Gehler Peter\u00a0V (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\u20136059","DOI":"10.1109\/CVPR.2017.500"},{"key":"261_CR88","doi-asserted-by":"crossref","unstructured":"Sengupta A, Budvytis I, Cipolla R (2021) Hierarchical kinematic probability distributions for 3d human shape and pose estimation from images in the wild. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 11219\u201311229","DOI":"10.1109\/ICCV48922.2021.01103"},{"key":"261_CR89","doi-asserted-by":"crossref","unstructured":"Zeng W, Ouyang W, Luo P, Liu W, Wang X (2020) 3d human mesh regression with dense correspondence. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7054\u20137063","DOI":"10.1109\/CVPR42600.2020.00708"},{"key":"261_CR90","doi-asserted-by":"crossref","unstructured":"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\u2013446","DOI":"10.1007\/978-3-030-01225-0_27"},{"key":"261_CR91","doi-asserted-by":"crossref","unstructured":"Cheng Y, Wang B, Yang B, Tan RT (2021) Monocular 3d multi-person pose estimation by integrating top-down and bottom-up networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7649\u20137659","DOI":"10.1109\/CVPR46437.2021.00756"},{"key":"261_CR92","doi-asserted-by":"crossref","unstructured":"Meinhardt T, Kirillov A, Leal-Taixe L, Feichtenhofer C (2022) Trackformer: multi-object tracking with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8844\u20138854","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"261_CR93","doi-asserted-by":"crossref","unstructured":"von Marcard T, Henschel R, Black MJ, 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\u2013617","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"261_CR94","doi-asserted-by":"crossref","unstructured":"Zeng A, Ju X, Yang L, Gao R, Zhu X, Dai B, Xu Q (2022) Deciwatch: a simple baseline for 10x efficient 2d and 3d pose estimation. arXiv preprint arXiv:2203.08713","DOI":"10.1007\/978-3-031-20065-6_35"},{"key":"261_CR95","doi-asserted-by":"crossref","unstructured":"Xu J, Yu Z, Ni B, Yang J, Yang X, Zhang W (2020) Deep kinematics analysis for monocular 3d human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 899\u2013908","DOI":"10.1109\/CVPR42600.2020.00098"},{"key":"261_CR96","doi-asserted-by":"crossref","unstructured":"Mahmood N, G, Troje NF, Pons-Moll G, Black MJ (2019) Amass: archive of motion capture as surface shapes. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 5442\u20135451","DOI":"10.1109\/ICCV.2019.00554"},{"key":"261_CR97","doi-asserted-by":"crossref","unstructured":"Bouazizi A, Holzbock A, Kressel U, Dietmayer K, Belagiannis V (2022) Motionmixer: mlp-based 3d human body pose forecasting. arXiv preprint arXiv:2207.00499","DOI":"10.24963\/ijcai.2022\/111"},{"key":"261_CR98","doi-asserted-by":"crossref","unstructured":"Hong F, Zhang M, Pan L, Cai Z, Yang L, Liu Z (2022) Avatarclip: zero-shot text-driven generation and animation of 3d avatars. arXiv preprint arXiv:2205.08535","DOI":"10.1145\/3528223.3530094"},{"key":"261_CR99","doi-asserted-by":"crossref","unstructured":"Cao Z, Gao H, Mangalam K, Cai Q-Z, Vo M, Malik J (2020) Long-term human motion prediction with scene context. In: European conference on computer vision. Springer, pp 387\u2013404","DOI":"10.1007\/978-3-030-58452-8_23"},{"key":"261_CR100","unstructured":"Mohamed A, Chen H, Wang Z, Claudel C (2021) Skeleton-graph: long-term 3d motion prediction from 2d observations using deep spatio-temporal graph cnns. arXiv preprint arXiv:2109.10257"},{"key":"261_CR101","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2016.09.002","volume":"152","author":"N Sarafianos","year":"2016","unstructured":"Sarafianos N, Boteanu B, Ionescu B, Kakadiaris IA (2016) 3d human pose estimation: a review of the literature and analysis of covariates. Comput Vis Image Underst 152:1\u201320","journal-title":"Comput Vis Image Underst"},{"key":"261_CR102","doi-asserted-by":"crossref","unstructured":"Moon G, Chang JY, Lee KM (2019) Camera distance-aware top-down approach for 3d multi-person pose estimation from a single rgb image. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10133\u201310142","DOI":"10.1109\/ICCV.2019.01023"},{"key":"261_CR103","doi-asserted-by":"crossref","unstructured":"Lin K, Wang L, Liu Z (2021) End-to-end human pose and mesh reconstruction with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1954\u20131963","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"261_CR104","unstructured":"Zheng C, Wu W, Yang T, Zhu S, Chen C, Liu R, Shen J, Kehtarnavaz N, Shah M (2020) Deep learning-based human pose estimation: a survey. arXiv preprint arXiv:2012.13392"},{"key":"261_CR105","doi-asserted-by":"crossref","unstructured":"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\u20132509","DOI":"10.1109\/CVPR.2017.603"},{"key":"261_CR106","doi-asserted-by":"crossref","unstructured":"Sidenbladh H, De\u00a0la Torre F, Black MJ (2000) A framework for modeling the appearance of 3d articulated figures. In: Proceedings fourth IEEE international conference on automatic face and gesture recognition (Cat. No. PR00580). IEEE, pp 368\u2013375","DOI":"10.1109\/AFGR.2000.840661"},{"key":"261_CR107","doi-asserted-by":"crossref","unstructured":"Anguelov D, Srinivasan P, Koller D, Thrun S, Rodgers J, Davis J (2005) Scape: shape completion and animation of people. In: ACM SIGGRAPH 2005 papers, pp 408\u2013416","DOI":"10.1145\/1073204.1073207"},{"key":"261_CR108","doi-asserted-by":"crossref","unstructured":"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\u20138329","DOI":"10.1109\/CVPR.2018.00868"},{"key":"261_CR109","doi-asserted-by":"crossref","unstructured":"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\u20136808","DOI":"10.1109\/CVPR.2017.280"},{"issue":"1","key":"261_CR110","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1006\/cviu.1995.1004","volume":"61","author":"TF Cootes","year":"1995","unstructured":"Cootes TF, Taylor CJ, Cooper DH, Graham J (1995) Active shape models-their training and application. Comput Vis Image Underst 61(1):38\u201359","journal-title":"Comput Vis Image Underst"},{"key":"261_CR111","unstructured":"Ju SX, Black MJ, Yacoob Y (1996) Cardboard people: a parameterized model of articulated image motion. In: Proceedings of the second international conference on automatic face and gesture recognition. IEEE, pp 38\u201344"},{"key":"261_CR112","doi-asserted-by":"crossref","unstructured":"Zuffi S, Freifeld O, Black MJ (2012) From pictorial structures to deformable structures. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 3546\u20133553","DOI":"10.1109\/CVPR.2012.6248098"},{"issue":"4","key":"261_CR113","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta D, Sridhar S, Sotnychenko O, Rhodin H, Shafiei M, Seidel HP, Xu W, Casas D, Theobalt C (2017) Vnect: real-time 3d human pose estimation with a single rgb camera. ACM Trans Gr 36(4):1\u201314","journal-title":"ACM Trans Gr"},{"key":"261_CR114","doi-asserted-by":"crossref","unstructured":"Dantone M, Gall J, Leistner C, Van Gool L (2013) Human pose estimation using body parts dependent joint regressors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3041\u20133048","DOI":"10.1109\/CVPR.2013.391"},{"key":"261_CR115","unstructured":"Chen X, Yuille A (2014) Articulated pose estimation by a graphical model with image dependent pairwise relations. arXiv preprint arXiv:1407.3399"},{"key":"261_CR116","doi-asserted-by":"crossref","unstructured":"Gkioxari G, Hariharan B, Girshick R, Malik J (2014) Using k-poselets for detecting people and localizing their keypoints. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3582\u20133589","DOI":"10.1109\/CVPR.2014.458"},{"key":"261_CR117","doi-asserted-by":"crossref","unstructured":"Cai Y, Wang Z, Luo Z, Yin B, Du A, Wang H, Zhang X, Zhou X, Zhou E, Sun J (2020) Learning delicate local representations for multi-person pose estimation. In: European conference on computer vision. Springer, pp 455\u2013472","DOI":"10.1007\/978-3-030-58580-8_27"},{"issue":"1","key":"261_CR118","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","volume":"43","author":"Z Cao","year":"2019","unstructured":"Cao Z, Simon T, Wei SE, Sheikh Y (2019) Openpose: realtime multi-person 2d pose estimation using part affinity fields. IEEE Trans Pattern Anal Mach Intell 43(1):172\u2013186","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"261_CR119","doi-asserted-by":"crossref","unstructured":"Chen Y, Wang Z, Peng Y, Zhang Z, Yu G, Sun J (2018) Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7103\u20137112","DOI":"10.1109\/CVPR.2018.00742"},{"key":"261_CR120","unstructured":"Li W, Wang Z, Yin B, Peng Q, Du Y, Xiao T, Yu G, Lu H, Wei Y, Sun J (2019) Rethinking on multi-stage networks for human pose estimation. arXiv preprint arXiv:1901.00148"},{"key":"261_CR121","unstructured":"Tian Z, Chen H, Shen C (2019) Directpose: direct end-to-end multi-person pose estimation. arXiv preprint arXiv:1911.07451"},{"key":"261_CR122","doi-asserted-by":"crossref","unstructured":"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\u20132611","DOI":"10.1109\/ICCV.2017.284"},{"key":"261_CR123","doi-asserted-by":"crossref","unstructured":"Huang J, Zhu Z, Guo F, Huang G (2020) The devil is in the details: delving into unbiased data processing for human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5700\u20135709","DOI":"10.1109\/CVPR42600.2020.00574"},{"key":"261_CR124","doi-asserted-by":"crossref","unstructured":"Carreira J, Agrawal P, Fragkiadaki K, Malik J (2016) Human pose estimation with iterative error feedback. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4733\u20134742","DOI":"10.1109\/CVPR.2016.512"},{"key":"261_CR125","doi-asserted-by":"crossref","unstructured":"Nie X, Feng J, Zhang J, Yan S (2019) Single-stage multi-person pose machines. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6951\u20136960","DOI":"10.1109\/ICCV.2019.00705"},{"key":"261_CR126","doi-asserted-by":"crossref","unstructured":"Toshev A, Szegedy C (2014) Deeppose: human pose estimation via deep neural networks\u2019. CVPR (Columbus, Ohio), pp 1653\u20131660","DOI":"10.1109\/CVPR.2014.214"},{"key":"261_CR127","first-page":"1799","volume":"27","author":"JJ Tompson","year":"2014","unstructured":"Tompson JJ, Arjun J, Yann L, Christoph B (2014) Joint training of a convolutional network and a graphical model for human pose estimation. Adv Neural Inf Process Syst 27:1799\u20131807","journal-title":"Adv Neural Inf Process Syst"},{"key":"261_CR128","doi-asserted-by":"crossref","unstructured":"Andriluka M, Roth S, Schiele B (2009) Pictorial structures revisited: people detection and articulated pose estimation. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 1014\u20131021","DOI":"10.1109\/CVPR.2009.5206754"},{"key":"261_CR129","doi-asserted-by":"crossref","unstructured":"Toshev A, Szegedy C (2014) Deeppose: human pose estimation via deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1653\u20131660","DOI":"10.1109\/CVPR.2014.214"},{"key":"261_CR130","doi-asserted-by":"crossref","unstructured":"Su K, Yu D, Xu Z, Geng X, Wang C (2019) Multi-person pose estimation with enhanced channel-wise and spatial information. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5674\u20135682","DOI":"10.1109\/CVPR.2019.00582"},{"key":"261_CR131","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"261_CR132","doi-asserted-by":"crossref","unstructured":"Sun M, Kohli P, Shotton J (2012) Conditional regression forests for human pose estimation. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 3394\u20133401","DOI":"10.1109\/CVPR.2012.6248079"},{"key":"261_CR133","doi-asserted-by":"crossref","unstructured":"Pishchulin L, Andriluka M, Gehler P, Schiele B (2013) Poselet conditioned pictorial structures. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 588\u2013595","DOI":"10.1109\/CVPR.2013.82"},{"key":"261_CR134","doi-asserted-by":"crossref","unstructured":"Tang W, Yu P, Wu Y (2018) Deeply learned compositional models for human pose estimation. In: Proceedings of the European conference on computer vision (ECCV), pp 190\u2013206","DOI":"10.1007\/978-3-030-01219-9_12"},{"key":"261_CR135","unstructured":"Zhou X, Wang D, Kr\u00e4henb\u00fchl P (2019) Objects as points. arXiv preprint arXiv:1904.07850"},{"key":"261_CR136","doi-asserted-by":"publisher","first-page":"11354","DOI":"10.1609\/aaai.v34i07.6797","volume":"34","author":"J Li","year":"2020","unstructured":"Li J, Wen S, Wang Z (2020) Simple pose: rethinking and improving a bottom-up approach for multi-person pose estimation. Proceedings of the AAAI conference on artificial intelligence 34:11354\u201311361","journal-title":"Proceedings of the AAAI conference on artificial intelligence"},{"key":"261_CR137","doi-asserted-by":"crossref","unstructured":"Wei F, Sun X, Li H, Wang J, Lin S (2020) Point-set anchors for object detection, instance segmentation and pose estimation. In: European conference on computer vision. Springer, pp 527\u2013544","DOI":"10.1007\/978-3-030-58607-2_31"},{"key":"261_CR138","doi-asserted-by":"crossref","unstructured":"Pishchulin L, Insafutdinov E, Tang S, Andres B, Andriluka M, Gehler PV, 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\u20134937","DOI":"10.1109\/CVPR.2016.533"},{"key":"261_CR139","doi-asserted-by":"crossref","unstructured":"Kocabas M, Karagoz S, Akbas E (2018) Multiposenet: fast multi-person pose estimation using pose residual network. In: Proceedings of the European conference on computer vision (ECCV), pp 417\u2013433","DOI":"10.1007\/978-3-030-01252-6_26"},{"key":"261_CR140","doi-asserted-by":"crossref","unstructured":"Papandreou G, Zhu T, Chen L-C, Gidaris S, Tompson J, Murphy K (2018) Personlab: Person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. In: Proceedings of the European conference on computer vision (ECCV), pp 269\u2013286","DOI":"10.1007\/978-3-030-01264-9_17"},{"issue":"1","key":"261_CR141","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TIP.2018.2865666","volume":"28","author":"Y Luo","year":"2018","unstructured":"Luo Y, Xu Z, Liu P, Du Y, Guo J-M (2018) Multi-person pose estimation via multi-layer fractal network and joints kinship pattern. IEEE Trans Image Process 28(1):142\u2013155","journal-title":"IEEE Trans Image Process"},{"key":"261_CR142","doi-asserted-by":"crossref","unstructured":"Insafutdinov E, Pishchulin L, Andres B, Andriluka M, Schiele B (2016) Deepercut: a deeper, stronger, and faster multi-person pose estimation model. In: European conference on computer vision. Springer, pp 34\u201350","DOI":"10.1007\/978-3-319-46466-4_3"},{"key":"261_CR143","doi-asserted-by":"crossref","unstructured":"Martinez J, Hossain R, Romero J, Little JJ (2017) A simple yet effective baseline for 3d human pose estimation. In: Proceedings of the IEEE international conference on computer vision, pp 2640\u20132649","DOI":"10.1109\/ICCV.2017.288"},{"issue":"1","key":"261_CR144","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/0262-8856(83)90003-3","volume":"1","author":"D Hogg","year":"1983","unstructured":"Hogg D (1983) Model-based vision: a program to see a walking person. Image Vis Comput 1(1):5\u201320","journal-title":"Image Vis Comput"},{"key":"261_CR145","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1109\/TPAMI.1980.6447699","volume":"6","author":"J O\u2019rourke","year":"1980","unstructured":"O\u2019rourke J, Badler NI (1980) Model-based image analysis of human motion using constraint propagation. IEEE Trans Pattern Anal Mach Intell 6:522\u2013536","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"261_CR146","doi-asserted-by":"crossref","unstructured":"Chen C-H, Ramanan D (2017) 3d human pose estimation= 2d pose estimation+ matching. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7035\u20137043","DOI":"10.1109\/CVPR.2017.610"},{"key":"261_CR147","doi-asserted-by":"crossref","unstructured":"Tekin B, Katircioglu I, Salzmann M, Lepetit V, Fua P (2016) Structured prediction of 3d human pose with deep neural networks. arXiv preprint arXiv:1605.05180","DOI":"10.5244\/C.30.130"},{"key":"261_CR148","doi-asserted-by":"crossref","unstructured":"Pavlakos G, Zhou X, Derpanis KG, Daniilidis K (2017) 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\u20137034","DOI":"10.1109\/CVPR.2017.139"},{"key":"261_CR149","doi-asserted-by":"crossref","unstructured":"Wang J, Sun K, Cheng T, Jiang B, Deng C, Zhao Y, Liu D, Mu Y, Tan M, Wang X et\u00a0al. (2020) Deep high-resolution representation learning for visual recognition. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"261_CR150","doi-asserted-by":"crossref","unstructured":"Alp G\u00fcler 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\u20137306","DOI":"10.1109\/CVPR.2018.00762"},{"key":"261_CR151","doi-asserted-by":"crossref","unstructured":"Jiang W, Kolotouros N, Pavlakos G, Zhou X, Daniilidis K (2020) Coherent reconstruction of multiple humans from a single image. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5579\u20135588","DOI":"10.1109\/CVPR42600.2020.00562"},{"key":"261_CR152","doi-asserted-by":"crossref","unstructured":"Andriluka M, Roth S, Schiele B (2010) Monocular 3d pose estimation and tracking by detection. In: 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, pp 623\u2013630","DOI":"10.1109\/CVPR.2010.5540156"},{"key":"261_CR153","doi-asserted-by":"crossref","unstructured":"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\u20132832","DOI":"10.1109\/CVPR.2017.170"},{"issue":"10","key":"261_CR154","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1109\/TPAMI.2015.2509986","volume":"38","author":"V Belagiannis","year":"2015","unstructured":"Belagiannis V, Amin S, Andriluka M, Schiele B, Navab N, Ilic S (2015) 3d pictorial structures revisited: multiple human pose estimation. IEEE Trans Pattern Anal Mach Intell 38(10):1929\u20131942","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"261_CR155","doi-asserted-by":"publisher","first-page":"15573","DOI":"10.1007\/s11042-017-5133-8","volume":"77","author":"S Ershadi-Nasab","year":"2018","unstructured":"Ershadi-Nasab S, Noury E, Kasaei S, Sanaei E (2018) Multiple human 3d pose estimation from multiview images. Multimed Tools Appl 77(12):15573\u201315601","journal-title":"Multimed Tools Appl"},{"key":"261_CR156","doi-asserted-by":"crossref","unstructured":"Tome D, Toso M, Agapito L, Russell C (2018) Rethinking pose in 3d: multi-stage refinement and recovery for markerless motion capture. In: 2018 international conference on 3D vision (3DV). IEEE, pp 474\u2013483","DOI":"10.1109\/3DV.2018.00061"},{"key":"261_CR157","doi-asserted-by":"crossref","unstructured":"Zhang Y, An L, Yu T, Li X, Li K, Liu Y (2020) 4d association graph for realtime multi-person motion capture using multiple video cameras. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1324\u20131333","DOI":"10.1109\/CVPR42600.2020.00140"},{"key":"261_CR158","doi-asserted-by":"crossref","unstructured":"Chen L, Ai H, Chen R, Zhuang Z, Liu S (2020) Cross-view tracking for multi-human 3d pose estimation at over 100 fps. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3279\u20133288","DOI":"10.1109\/CVPR42600.2020.00334"},{"key":"261_CR159","doi-asserted-by":"crossref","unstructured":"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\u2013135","DOI":"10.1007\/978-3-030-01234-2_8"},{"key":"261_CR160","doi-asserted-by":"crossref","unstructured":"Hossain MRI, Little JJ (2018) Exploiting temporal information for 3d human pose estimation. In: Proceedings of the European conference on computer vision (ECCV), pp 68\u201384","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"261_CR161","doi-asserted-by":"crossref","unstructured":"Nie BX, Wei P, Zhu S-C (2017) Monocular 3d human pose estimation by predicting depth on joints. In: 2017 IEEE international conference on computer vision (ICCV). IEEE, pp 3467\u20133475","DOI":"10.1109\/ICCV.2017.373"},{"key":"261_CR162","doi-asserted-by":"crossref","unstructured":"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\u20137316","DOI":"10.1109\/CVPR.2018.00763"},{"key":"261_CR163","doi-asserted-by":"crossref","unstructured":"Yasin H, Iqbal U, Kruger B, Weber A, Gall J (2016) A dual-source approach for 3d pose estimation from a single image. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4948\u20134956","DOI":"10.1109\/CVPR.2016.535"},{"key":"261_CR164","doi-asserted-by":"crossref","unstructured":"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\u2013683","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"261_CR165","doi-asserted-by":"crossref","unstructured":"Tekin B, M\u00e1rquez-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\u20133950","DOI":"10.1109\/ICCV.2017.425"},{"key":"261_CR166","unstructured":"S\u00e1r\u00e1ndi I, Linder T, Arras KO, Leibe B (2018)Synthetic occlusion augmentation with volumetric heatmaps for the 2018 eccv posetrack challenge on 3d human pose estimation. arXiv preprint arXiv:1809.04987"},{"issue":"5","key":"261_CR167","first-page":"1146","volume":"42","author":"G Rogez","year":"2019","unstructured":"Rogez G, Weinzaepfel P, Schmid C (2019) Lcr-net++: multi-person 2d and 3d pose detection in natural images. IEEE Trans Pattern Anal Mach Intell 42(5):1146\u20131161","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"261_CR168","doi-asserted-by":"crossref","unstructured":"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\u20132157","DOI":"10.1109\/CVPR.2018.00229"},{"key":"261_CR169","unstructured":"Mehta D, Sotnychenko O, Mueller F, Xu W, Elgharib M, Fua P, Seidel H-P, Rhodin H, Pons-Moll G, Theobalt C (2019) Xnect: real-time multi-person 3d human pose estimation with a single rgb camera. arXiv preprint arXiv:1907.00837"},{"key":"261_CR170","doi-asserted-by":"crossref","unstructured":"Remelli E, Han S, Honari S, Fua P, Wang R (2020) Lightweight multi-view 3d pose estimation through camera-disentangled representation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6040\u20136049","DOI":"10.1109\/CVPR42600.2020.00608"},{"key":"261_CR171","doi-asserted-by":"crossref","unstructured":"Qiu H, Wang C, Wang J, Wang N, Zeng W (2019) Cross view fusion for 3d human pose estimation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4342\u20134351","DOI":"10.1109\/ICCV.2019.00444"},{"key":"261_CR172","unstructured":"Andrew AM (2001) Multiple view geometry in computer vision. Kybernetes"},{"key":"261_CR173","doi-asserted-by":"crossref","unstructured":"Iskakov K, Burkov E, Lempitsky V, Malkov Y (2019) Learnable triangulation of human pose. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7718\u20137727","DOI":"10.1109\/ICCV.2019.00781"},{"key":"261_CR174","doi-asserted-by":"crossref","unstructured":"Chen H, Guo P, Li P, Lee GH, Chirikjian G (2020) Multi-person 3d pose estimation in crowded scenes based on multi-view geometry. In: European conference on computer vision. Springer, pp 541\u2013557","DOI":"10.1007\/978-3-030-58580-8_32"},{"key":"261_CR175","doi-asserted-by":"crossref","unstructured":"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\/CVF conference on computer vision and pattern recognition, pp 7792\u20137801","DOI":"10.1109\/CVPR.2019.00798"},{"key":"261_CR176","doi-asserted-by":"crossref","unstructured":"Huang C, Jiang S, Li Y, Zhang Z, Traish J, Deng C, Ferguson S, Xu RY (2020) End-to-end dynamic matching network for multi-view multi-person 3d pose estimation. In: European conference on computer vision. Springer, pp 477\u2013493","DOI":"10.1007\/978-3-030-58604-1_29"},{"issue":"1","key":"261_CR177","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-020-01120-2","volume":"32","author":"A Kadkhodamohammadi","year":"2021","unstructured":"Kadkhodamohammadi A, Padoy N (2021) A generalizable approach for multi-view 3d human pose regression. Mach Vis Appl 32(1):1\u201314","journal-title":"Mach Vis Appl"},{"key":"261_CR178","unstructured":"Svens\u00e9n M, Bishop CM (2007) Pattern recognition and machine learning"},{"key":"261_CR179","doi-asserted-by":"crossref","unstructured":"Belagiannis V, Amin S, Andriluka M, Schiele B, Navab N, Ilic S (2014) 3d pictorial structures for multiple human pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1669\u20131676","DOI":"10.1109\/CVPR.2014.216"},{"key":"261_CR180","doi-asserted-by":"crossref","unstructured":"Zhong Z, Zheng L, Zheng Z, Li S, Yang Y (2018) Camera style adaptation for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5157\u20135166","DOI":"10.1109\/CVPR.2018.00541"},{"key":"261_CR181","doi-asserted-by":"crossref","unstructured":"Li S, Chan AB (2014) 3d human pose estimation from monocular images with deep convolutional neural network. In: Asian conference on computer vision. Springer, pp 332\u2013347","DOI":"10.1007\/978-3-319-16808-1_23"},{"key":"261_CR182","doi-asserted-by":"crossref","unstructured":"Li S, Zhang W, Chan AB (2015) Maximum-margin structured learning with deep networks for 3d human pose estimation. In: Proceedings of the IEEE international conference on computer vision, pp 2848\u20132856","DOI":"10.1109\/ICCV.2015.326"},{"key":"261_CR183","doi-asserted-by":"crossref","unstructured":"Rogez G, Weinzaepfel P, Schmid C (2017) Lcr-net: localization-classification-regression for human pose. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3433\u20133441","DOI":"10.1109\/CVPR.2017.134"},{"key":"261_CR184","unstructured":"Luo C, Chu X, Yuille A (2018) Orinet: a fully convolutional network for 3d human pose estimation. arXiv preprint arXiv:1811.04989"},{"key":"261_CR185","doi-asserted-by":"crossref","unstructured":"Fang HS, Xu Y, Wang W, Liu X, Zhu SC (2018) Learning pose grammar to encode human body configuration for 3d pose estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, volume\u00a032","DOI":"10.1609\/aaai.v32i1.12270"},{"issue":"4","key":"261_CR186","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1145\/3386569.3392410","volume":"39","author":"D Mehta","year":"2020","unstructured":"Mehta D, Sotnychenko O, Mueller F, Xu W, Elgharib M, Fua P, Seidel HP, Rhodin H, Pons-Moll G, Theobalt C (2020) Xnect: real-time multi-person 3d motion capture with a single rgb camera. ACM Trans Gr 39(4):82\u201391","journal-title":"ACM Trans Gr"},{"key":"261_CR187","doi-asserted-by":"crossref","unstructured":"Rhodin H, Sp\u00f6rri J, Katircioglu I, Constantin V, Meyer F, M\u00fcller 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\u20138446","DOI":"10.1109\/CVPR.2018.00880"},{"key":"261_CR188","doi-asserted-by":"crossref","unstructured":"Wandt B, Rosenhahn B (2019) Repnet: weakly supervised training of an adversarial reprojection network for 3d human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7782\u20137791","DOI":"10.1109\/CVPR.2019.00797"},{"key":"261_CR189","doi-asserted-by":"crossref","unstructured":"Wang C, Kong C, Lucey S (2019) Distill knowledge from nrsfm for weakly supervised 3d pose learning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 743\u2013752","DOI":"10.1109\/ICCV.2019.00083"},{"key":"261_CR190","doi-asserted-by":"crossref","unstructured":"Kundu JN, Seth S, Jampani V, Rakesh M, Venkatesh BR, Chakraborty A (2020) Self-supervised 3d human pose estimation via part guided novel image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6152\u20136162","DOI":"10.1109\/CVPR42600.2020.00619"},{"key":"261_CR191","doi-asserted-by":"crossref","unstructured":"Zanfir A, Bazavan EG, Xu H, Freeman WT, Sukthankar RSC (2020) Weakly supervised 3d human pose and shape reconstruction with normalizing flows. In: European conference on computer vision. Springer, pp 465\u2013481","DOI":"10.1007\/978-3-030-58539-6_28"},{"key":"261_CR192","doi-asserted-by":"crossref","unstructured":"Chen Z, Liu X, Sheng B, Li P (2020) Garnet: graph attention residual networks based on adversarial learning for 3d human pose estimation. In: Computer graphics international conference. Springer, pp 276\u2013287","DOI":"10.1007\/978-3-030-61864-3_24"},{"key":"261_CR193","unstructured":"Habekost J, Shiratori T, Ye Y, Komura T, Shi M, Aberman K, Aristidou A, Lischinski D, Cohen-Or D, Chen B et\u00a0al. (2020) Learning 3d global human motion estimation from unpaired, disjoint datasets. In: BMVC"},{"key":"261_CR194","unstructured":"Xiaohan Nie B, Xiong C, Zhu S-C (2015) Joint action recognition and pose estimation from video. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1293\u20131301"},{"issue":"3","key":"261_CR195","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1109\/TCYB.2017.2756840","volume":"48","author":"C Cao","year":"2017","unstructured":"Cao C, Zhang Y, Zhang C, Hanqing L (2017) Body joint guided 3-d deep convolutional descriptors for action recognition. IEEE Trans Cybern 48(3):1095\u20131108","journal-title":"IEEE Trans Cybern"},{"key":"261_CR196","doi-asserted-by":"crossref","unstructured":"Liu J, Shahroudy A, Xu D, Wang G (2016) Spatio-temporal lstm with trust gates for 3d human action recognition. In: European conference on computer vision. Springer, pp 816\u2013833","DOI":"10.1007\/978-3-319-46487-9_50"},{"issue":"5","key":"261_CR197","first-page":"1045","volume":"40","author":"J Liu","year":"2017","unstructured":"Liu J, Shahroudy A, Xu D, Wang G (2017) Deep multimodal feature analysis for action recognition in rgb+ d videos. IEEE Trans Pattern Anal Mach Intell 40(5):1045\u20131058","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"261_CR198","unstructured":"Baradel F, Wolf C, Mille J (2017) Pose-conditioned spatio-temporal attention for human action recognition. arXiv preprint arXiv:1703.10106"},{"key":"261_CR199","doi-asserted-by":"crossref","unstructured":"Raaj Y, Idrees H, Hidalgo G, Sheikh Y (2019) Efficient online multi-person 2d pose tracking with recurrent spatio-temporal affinity fields. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4620\u20134628","DOI":"10.1109\/CVPR.2019.00475"},{"key":"261_CR200","doi-asserted-by":"crossref","unstructured":"Girdhar R, Gkioxari G, Torresani L, Paluri M, Tran D (2018) Detect-and-track: efficient pose estimation in videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 350\u2013359","DOI":"10.1109\/CVPR.2018.00044"},{"key":"261_CR201","doi-asserted-by":"crossref","unstructured":"Ramachandran A, Karuppiah A (2020) A survey on recent advances in wearable fall detection systems. BioMed Res Int","DOI":"10.1155\/2020\/2167160"},{"key":"261_CR202","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.medengphy.2016.10.014","volume":"39","author":"SS Khan","year":"2017","unstructured":"Khan SS, Hoey J (2017) Review of fall detection techniques: a data availability perspective. Med Eng Phys 39:12\u201322","journal-title":"Med Eng Phys"},{"issue":"6","key":"261_CR203","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/JBHI.2014.2304357","volume":"18","author":"X Ma","year":"2014","unstructured":"Ma X, Wang H, Xue B, Zhou M, Ji B, Li Y (2014) Depth-based human fall detection via shape features and improved extreme learning machine. IEEE J Biomed Health Inform 18(6):1915\u20131922","journal-title":"IEEE J Biomed Health Inform"},{"key":"261_CR204","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.jbiomech.2019.03.007","volume":"88","author":"EE Geertsema","year":"2019","unstructured":"Geertsema EE, Visser GH, Viergever MA, Kalitzin SN (2019) Automated remote fall detection using impact features from video and audio. J Biomech 88:25\u201332","journal-title":"J Biomech"},{"issue":"4","key":"261_CR205","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1007\/s11554-012-0246-9","volume":"9","author":"G Mastorakis","year":"2014","unstructured":"Mastorakis G, Makris D (2014) Fall detection system using kinect\u2019s infrared sensor. J Real Time Image Proc 9(4):635\u2013646","journal-title":"J Real Time Image Proc"},{"key":"261_CR206","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.jvcir.2017.08.008","volume":"49","author":"A Yajai","year":"2017","unstructured":"Yajai A, Rasmequan S (2017) Adaptive directional bounding box from rgb-d information for improving fall detection. J Vis Commun Image Represent 49:257\u2013273","journal-title":"J Vis Commun Image Represent"},{"key":"261_CR207","doi-asserted-by":"crossref","unstructured":"Ciabattoni L, Foresi G, Monteri\u00f9 A, Proietti Pagnotta D, Tomaiuolo L (2018) Fall detection system by using ambient intelligence and mobile robots. In: 2018 zooming innovation in consumer technologies conference (ZINC). IEEE, pp 130\u2013131","DOI":"10.1109\/ZINC.2018.8448970"},{"key":"261_CR208","doi-asserted-by":"crossref","unstructured":"N\u00fa\u00f1ez-Marcos A, Azkune G, Arganda-Carreras I (2017) Vision-based fall detection with convolutional neural networks. Wirel Commun Mobile Comput","DOI":"10.1155\/2017\/9474806"},{"key":"261_CR209","doi-asserted-by":"publisher","first-page":"17556","DOI":"10.1109\/ACCESS.2019.2962778","volume":"8","author":"Q Han","year":"2020","unstructured":"Han Q, Zhao H, Min W, Cui H, Zhou X, Zuo K, Liu R (2020) A two-stream approach to fall detection with mobilevgg. IEEE Access 8:17556\u201317566","journal-title":"IEEE Access"},{"issue":"1","key":"261_CR210","first-page":"314","volume":"23","author":"L Na","year":"2018","unstructured":"Na L, Yidan W, Feng L, Song J (2018) Deep learning for fall detection: three-dimensional cnn combined with lstm on video kinematic data. IEEE J Biomed Health Inform 23(1):314\u2013323","journal-title":"IEEE J Biomed Health Inform"},{"key":"261_CR211","doi-asserted-by":"crossref","unstructured":"Sajjan S, Moore M, Pan M, Nagaraja G, Lee J, Zeng A, Song S (2020) Clear grasp: 3d shape estimation of transparent objects for manipulation. In: 2020 IEEE international conference on robotics and automation (ICRA). IEEE, pp 3634\u20133642","DOI":"10.1109\/ICRA40945.2020.9197518"},{"issue":"4","key":"261_CR212","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/s10055-019-00419-4","volume":"24","author":"F Escalona","year":"2020","unstructured":"Escalona F, Martinez-Martin E, Cruz E, Cazorla M, Gomez-Donoso F (2020) Eva: evaluating at-home rehabilitation exercises using augmented reality and low-cost sensors. Virtual Real 24(4):567\u2013581","journal-title":"Virtual Real"},{"issue":"3","key":"261_CR213","doi-asserted-by":"publisher","DOI":"10.1002\/itl2.261","volume":"4","author":"D Shi","year":"2021","unstructured":"Shi D, Jiang X (2021) Sport training action correction by using convolutional neural network. Internet Technol Lett 4(3):e261","journal-title":"Internet Technol Lett"},{"key":"261_CR214","doi-asserted-by":"crossref","unstructured":"Wang J, Qiu K, Peng H, Fu J, Zhu J (2019) Ai coach: deep human pose estimation and analysis for personalized athletic training assistance. In: Proceedings of the 27th ACM international conference on multimedia, pp 374\u2013382","DOI":"10.1145\/3343031.3350609"},{"key":"261_CR215","doi-asserted-by":"crossref","unstructured":"Insafutdinov E, Andriluka M, Pishchulin L, Tang S, Levinkov E, Andres B, Schiele B (2017) Arttrack: articulated multi-person tracking in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6457\u20136465","DOI":"10.1109\/CVPR.2017.142"},{"key":"261_CR216","unstructured":"Jin S, Ma X, Han Z, Wu Y, Yang W, Liu W, Qian C, Ouyang W (2017) Towards multi-person pose tracking: bottom-up and top-down methods. In: ICCV posetrack workshop 2:7"},{"key":"261_CR217","unstructured":"Xiu Y, Li J, Wang H, Fang Y, Lu C (2018) Pose flow: efficient online pose tracking. arXiv preprint arXiv:1802.00977"},{"key":"261_CR218","unstructured":"Doering A, Iqbal U, Gall J (2018) Joint flow: temporal flow fields for multi person tracking. arXiv preprint arXiv:1805.04596"},{"key":"261_CR219","doi-asserted-by":"crossref","unstructured":"Li J, Xu C, Chen Z, Bian S, Yang L, Lu C (2021) Hybrik: a hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3383\u20133393","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"261_CR220","doi-asserted-by":"crossref","unstructured":"Lin K, Wang L, Liu Z (2021) Mesh graphormer. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 12939\u201312948","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"261_CR221","doi-asserted-by":"crossref","unstructured":"Yuan Y, Iqbal U, Molchanov P, Kitani K, Kautz J (2022) Glamr: global occlusion-aware human mesh recovery with dynamic cameras. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11038\u201311049","DOI":"10.1109\/CVPR52688.2022.01076"},{"key":"261_CR222","doi-asserted-by":"crossref","unstructured":"Kundu JN, Seth S, Ym P, Jampani V, Chakraborty A, Babu RV (2022) Uncertainty-aware adaptation for self-supervised 3d human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 20448\u201320459","DOI":"10.1109\/CVPR52688.2022.01980"},{"key":"261_CR223","doi-asserted-by":"crossref","unstructured":"Khirodkar R, Tripathi S, Kitani K (2022) Occluded human mesh recovery. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1715\u20131725","DOI":"10.1109\/CVPR52688.2022.00176"},{"key":"261_CR224","doi-asserted-by":"crossref","unstructured":"Li Z, Wang X, Wang F, Jiang P (2019) On boosting single-frame 3d human pose estimation via monocular videos. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2192\u20132201","DOI":"10.1109\/ICCV.2019.00228"},{"key":"261_CR225","doi-asserted-by":"crossref","unstructured":"Khurana T, Dave A, Ramanan D (2021) Detecting invisible people. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3174\u20133184","DOI":"10.1109\/ICCV48922.2021.00316"},{"key":"261_CR226","doi-asserted-by":"crossref","unstructured":"Jiang T, Camgoz NC, Bowden R (2021) Skeletor: skeletal transformers for robust body-pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3394\u20133402","DOI":"10.1109\/CVPRW53098.2021.00378"},{"key":"261_CR227","doi-asserted-by":"crossref","unstructured":"Choi H, Moon G, Chang JY, Lee KM (2021) Beyond static features for temporally consistent 3d human pose and shape from a video. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1964\u20131973","DOI":"10.1109\/CVPR46437.2021.00200"},{"key":"261_CR228","doi-asserted-by":"crossref","unstructured":"Jiao J, Cao Y, Song Y, Lau R (2018) Look deeper into depth: monocular depth estimation with semantic booster and attention-driven loss. In: Proceedings of the European conference on computer vision (ECCV), pp 53\u201369","DOI":"10.1007\/978-3-030-01267-0_4"},{"key":"261_CR229","doi-asserted-by":"crossref","unstructured":"Long X, Lin C, Liu L, Li W, Theobalt C, Yang R, Wang W (2021) Adaptive surface normal constraint for depth estimation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 12849\u201312858","DOI":"10.1109\/ICCV48922.2021.01261"},{"key":"261_CR230","doi-asserted-by":"crossref","unstructured":"Park J, Joo K, Hu Z, Liu C-K, Kweon IS (2020) Non-local spatial propagation network for depth completion. In: European conference on computer vision. Springer, pp 120\u2013136","DOI":"10.1007\/978-3-030-58601-0_8"},{"key":"261_CR231","doi-asserted-by":"crossref","unstructured":"Xiong X, Xiong H, Xian K, Zhao C, Cao Z, Li X (2020) Sparse-to-dense depth completion revisited: sampling strategy and graph construction. In: European conference on computer vision. Springer, pp 682\u2013699","DOI":"10.1007\/978-3-030-58589-1_41"},{"key":"261_CR232","doi-asserted-by":"crossref","unstructured":"Qu C, Liu W, Taylor CJ (2021) Bayesian deep basis fitting for depth completion with uncertainty. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 16147\u201316157","DOI":"10.1109\/ICCV48922.2021.01584"},{"key":"261_CR233","doi-asserted-by":"crossref","unstructured":"Reddy ND, Guigues L, Pishchulin L, Eledath J, Narasimhan SG (2021) Tessetrack: end-to-end learnable multi-person articulated 3d pose tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15190\u201315200","DOI":"10.1109\/CVPR46437.2021.01494"},{"key":"261_CR234","doi-asserted-by":"crossref","unstructured":"Wu S, Jin S, Liu W, Bai L, Qian C, Liu D, Ouyang W (2021) Graph-based 3d multi-person pose estimation using multi-view images. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 11148\u201311157","DOI":"10.1109\/ICCV48922.2021.01096"},{"key":"261_CR235","doi-asserted-by":"crossref","unstructured":"Zhang Y, Wang C, Wang X, Liu W, Zeng W (2022) Voxeltrack: multi-person 3d human pose estimation and tracking in the wild. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2022.3163709"},{"issue":"3","key":"261_CR236","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1109\/TBME.2018.2854632","volume":"66","author":"WR Johnson","year":"2018","unstructured":"Johnson WR, Alderson J, Lloyd D, Mian A (2018) Predicting athlete ground reaction forces and moments from spatio-temporal driven cnn models. IEEE Trans Biomed Eng 66(3):689\u2013694","journal-title":"IEEE Trans Biomed Eng"},{"key":"261_CR237","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.12752","volume":"10","author":"RS Alcantara","year":"2022","unstructured":"Alcantara RS, Edwards WB, Millet GY, Grabowski AM (2022) Predicting continuous ground reaction forces from accelerometers during uphill and downhill running: a recurrent neural network solution. PeerJ 10:e12752","journal-title":"PeerJ"},{"issue":"3","key":"261_CR238","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1016\/j.gaitpost.2008.09.003","volume":"29","author":"JL McGinley","year":"2009","unstructured":"McGinley JL, Baker R, Wolfe R, Morris ME (2009) The reliability of three-dimensional kinematic gait measurements: a systematic review. Gait Posture 29(3):360\u2013369","journal-title":"Gait Posture"},{"issue":"1","key":"261_CR239","first-page":"300","volume":"39","author":"C Morris","year":"2021","unstructured":"Morris C, Mundt M, Goldacre M, Weber J, Mian A, Alderson J (2021) Predicting 3d ground reaction force from 2d video via neural networks in sidestepping tasks. ISBS Proc Arch 39(1):300","journal-title":"ISBS Proc Arch"},{"key":"261_CR240","unstructured":"Yu H, Xu Y, Zhang J, Zhao W, Guan Z, Tao D (2021) Ap-10k: a benchmark for animal pose estimation in the wild. arXiv preprint arXiv:2108.12617"},{"key":"261_CR241","doi-asserted-by":"crossref","unstructured":"Mathis A, Biasi T, Schneider S, Yuksekgonul M, Rogers B, Bethge M, Mathis MW (2021) Pretraining boosts out-of-domain robustness for pose estimation. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1859\u20131868","DOI":"10.1109\/WACV48630.2021.00190"},{"key":"261_CR242","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.47994","volume":"8","author":"JM Graving","year":"2019","unstructured":"Graving JM, Chae D, Naik H, Li L, Koger B, Costelloe BR, Couzin ID (2019) Deepposekit, a software toolkit for fast and robust animal pose estimation using deep learning. Elife 8:e47994","journal-title":"Elife"},{"key":"261_CR243","doi-asserted-by":"publisher","DOI":"10.3389\/fnbeh.2020.581154","volume":"14","author":"R Labuguen","year":"2021","unstructured":"Labuguen R, Matsumoto J, Negrete SB, Nishimaru H, Nishijo H, Takada M, Go Y, Inoue KI, Shibata T (2021) Macaquepose: a novel \u201cin the wild\u2019\u2019 macaque monkey pose dataset for markerless motion capture. Front Behav Neurosci 14:581154","journal-title":"Front Behav Neurosci"},{"issue":"1","key":"261_CR244","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1038\/s41592-018-0234-5","volume":"16","author":"TD Pereira","year":"2019","unstructured":"Pereira TD, Aldarondo DE, Willmore L, Kislin M, Wang SS, Murthy M, Shaevitz JW (2019) Fast animal pose estimation using deep neural networks. Nat Methods 16(1):117\u2013125","journal-title":"Nat Methods"},{"key":"261_CR245","doi-asserted-by":"crossref","unstructured":"Li S, Li J, Tang H, Qian R, Lin W(2019) Atrw: a benchmark for amur tiger re-identification in the wild. arXiv preprint arXiv:1906.05586","DOI":"10.1145\/3394171.3413569"},{"key":"261_CR246","unstructured":"Hendrycks D, Dietterich T (2019) Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261"},{"key":"261_CR247","unstructured":"Michaelis C, Mitzkus B, Geirhos R, Rusak E, Bringmann O, Ecker AS, Bethge M, Brendel W (2019) Benchmarking robustness in object detection: autonomous driving when winter is coming. arXiv preprint arXiv:1907.07484"},{"key":"261_CR248","doi-asserted-by":"crossref","unstructured":"Kamann C, Rother C (2020) Benchmarking the robustness of semantic segmentation models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8828\u20138838","DOI":"10.1109\/CVPR42600.2020.00885"},{"key":"261_CR249","doi-asserted-by":"crossref","unstructured":"Liu W, Mei T (2022) Recent advances of monocular 2d and 3d human pose estimation: a deep learning perspective. ACM Comput Surv","DOI":"10.1145\/3524497"},{"key":"261_CR250","doi-asserted-by":"crossref","unstructured":"Wang J, Jin S, Liu W, Liu W, Qian C, Luo P (2021) When human pose estimation meets robustness: adversarial algorithms and benchmarks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11855\u201311864","DOI":"10.1109\/CVPR46437.2021.01168"},{"key":"261_CR251","unstructured":"Zheng C, Wu W, Yang T, Zhu S, Chen C, Liu R, Shen J, Kehtarnavaz N, Shah M (2020) Deep learning-based human pose estimation: a survey. CoRR, arXiv:2012.13392"},{"key":"261_CR252","doi-asserted-by":"crossref","unstructured":"Charles J, Pfister T, Magee D, Hogg D, Zisserman A (2016) Personalizing human video pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3063\u20133072","DOI":"10.1109\/CVPR.2016.334"},{"key":"261_CR253","doi-asserted-by":"crossref","unstructured":"Liu Z, Chen H, Feng R, Wu S, Ji S, Yang B, Wang X (2021) Deep dual consecutive network for human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 525\u2013534","DOI":"10.1109\/CVPR46437.2021.00059"},{"key":"261_CR254","doi-asserted-by":"crossref","unstructured":"Xu L, Jin S, Liu W, Qian C, Ouyang W, Luo P, Wang X (2022) Zoomnas: searching for whole-body human pose estimation in the wild. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2022.3197352"},{"key":"261_CR255","doi-asserted-by":"crossref","unstructured":"Zhang D, Wu Y, Guo M, Chen Y (2021) Deep learning methods for 3d human pose estimation under different supervision paradigms: a survey. Electronics 10(18):2267","DOI":"10.3390\/electronics10182267"},{"key":"261_CR256","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104260","volume":"102","author":"C Wang","year":"2021","unstructured":"Wang C, Zhang F, Ge SS (2021) A comprehensive survey on 2d multi-person pose estimation methods. Eng Appl Artif Intell 102:104260","journal-title":"Eng Appl Artif Intell"},{"key":"261_CR257","unstructured":"Giryes R, Sapiro G, Bronstein AM (2014) On the stability of deep networks. arXiv preprint arXiv:1412.5896"},{"key":"261_CR258","doi-asserted-by":"crossref","unstructured":"Zheng S, Song Y, Leung T, Goodfellow I (2016) Improving the robustness of deep neural networks via stability training. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4480\u20134488","DOI":"10.1109\/CVPR.2016.485"},{"key":"261_CR259","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli SM, Fawzi A, Fawzi O, Frossard P(2017) Universal adversarial perturbations. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1765\u20131773","DOI":"10.1109\/CVPR.2017.17"},{"issue":"1","key":"261_CR260","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/aa9a90","volume":"34","author":"E Haber","year":"2017","unstructured":"Haber E, Ruthotto L (2017) Stable architectures for deep neural networks. Inverse Prob 34(1):014004","journal-title":"Inverse Prob"},{"key":"261_CR261","doi-asserted-by":"crossref","unstructured":"Chen R, Chen H, Ren J, Huang G, Zhang Q (2019) Explaining neural networks semantically and quantitatively. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9187\u20139196","DOI":"10.1109\/ICCV.2019.00928"},{"key":"261_CR262","doi-asserted-by":"crossref","unstructured":"Zhang Y, Ti\u0148o P, Leonardis A, Tang K (2021) A survey on neural network interpretability. IEEE Trans Emerg Top Comput Intell","DOI":"10.1109\/TETCI.2021.3100641"},{"key":"261_CR263","unstructured":"Liu J, Akhtar N, Mian A (2020) Adversarial attack on skeleton-based human action recognition. IEEE Trans Neural Netw Learn Syst"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-022-00261-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13735-022-00261-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-022-00261-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T15:07:46Z","timestamp":1671289666000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13735-022-00261-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,19]]},"references-count":263,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["261"],"URL":"https:\/\/doi.org\/10.1007\/s13735-022-00261-6","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"value":"2192-6611","type":"print"},{"value":"2192-662X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,19]]},"assertion":[{"value":"10 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 November 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Yes.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}