{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T07:12:31Z","timestamp":1765177951146,"version":"3.37.3"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T00:00:00Z","timestamp":1567468800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T00:00:00Z","timestamp":1567468800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61603402","91420302"],"award-info":[{"award-number":["61603402","91420302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61603403","61703417"],"award-info":[{"award-number":["61603403","61703417"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61806212"],"award-info":[{"award-number":["61806212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1007\/s00371-019-01740-4","type":"journal-article","created":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T09:03:23Z","timestamp":1567501403000},"page":"1401-1410","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["3D human pose estimation by depth map"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8671-7210","authenticated-orcid":false,"given":"Jianzhai","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dewen","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengtao","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingsheng","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiongming","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,3]]},"reference":[{"key":"1740_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2d human pose estimation: new benchmark and state of the art analysis. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"1740_CR2","doi-asserted-by":"crossref","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"1740_CR3","doi-asserted-by":"crossref","unstructured":"Bulat, A., Tzimiropoulos, G.: Human pose estimation via convolutional part heatmap regression. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46478-7_44"},{"key":"1740_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"1740_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C.H., Ramanan, D.: 3d human pose estimation = 2d pose estimation + matching. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.610"},{"key":"1740_CR6","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"1740_CR7","unstructured":"Girshick, R., He, K., Gkioxari, G., Doll\u00e1r, P.: Mask r-cnn. In: ICCV (2017)"},{"key":"1740_CR8","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: efficient convolutional neural networks for mobile vision applications (2017). arXiv preprint \narXiv:1704.04861"},{"key":"1740_CR9","doi-asserted-by":"crossref","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: Deepercut: a deeper, stronger, and faster multiperson pose estimation model. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46466-4_3"},{"issue":"7","key":"1740_CR10","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1740_CR11","doi-asserted-by":"publisher","first-page":"1326","DOI":"10.1007\/s11263-018-1066-6","volume":"126","author":"I Katircioglu","year":"2018","unstructured":"Katircioglu, I., Tekin, B., Salzmann, M., Lepetit, V., Fua, P.: Learning latent representations of 3d human pose with deep neural networks. Int. J. Comput. Vis. 126, 1326\u20131341 (2018)","journal-title":"Int. J. Comput. Vis."},{"key":"1740_CR12","unstructured":"Li, S., Chan, A.B.: 3d human pose estimation from monocular images with deep convolutional neural network. In: ACCV (2014)"},{"issue":"1","key":"1740_CR13","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s11263-016-0962-x","volume":"122","author":"S Li","year":"2017","unstructured":"Li, S., Zhang, W., Chan, A.B.: Maximum-margin structured learning with deep networks for 3d human pose estimation. Int. J. Comput. Vis. 122(1), 149\u2013168 (2017)","journal-title":"Int. J. Comput. Vis."},{"issue":"6\u20138","key":"1740_CR14","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1007\/s00371-013-0822-4","volume":"29","author":"H Liang","year":"2013","unstructured":"Liang, H., Yuan, J., Thalmann, D., Zhang, Z.: Model-based hand pose estimation via spatial-temporal hand parsing and 3d fingertip localization. Vis. Comput. 29(6\u20138), 837\u2013848 (2013)","journal-title":"Vis. Comput."},{"key":"1740_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1740_CR16","doi-asserted-by":"crossref","unstructured":"Liu, F., Shen, C., Lin, G.: Deep convolutional neural fields for depth estimation from a single image. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299152"},{"issue":"6","key":"1740_CR17","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: A skinned multi-person linear model. ACM Trans. Graph. 34(6), 248 (2015)","journal-title":"ACM Trans. Graph."},{"issue":"6\u20138","key":"1740_CR18","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1007\/s00371-018-1556-0","volume":"34","author":"C Ma","year":"2018","unstructured":"Ma, C., Wang, A., Chen, G., Xu, C.: Hand joints-based gesture recognition for noisy dataset using nested interval unscented kalman filter with lstm network. Vis. Comput. 34(6\u20138), 1053\u20131063 (2018)","journal-title":"Vis. Comput."},{"key":"1740_CR19","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3d human pose estimation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"1740_CR20","unstructured":"Mehta, D., Rhodin, H., Casas, D., Sotnychenko, O., Xu, W., Theobalt, C.: Monocular 3d human pose estimation using transfer learning and improved cnn supervision (2016). arXiv preprint \narXiv:1611.09813"},{"key":"1740_CR21","doi-asserted-by":"crossref","unstructured":"Moreno-Noguer, F.: 3d human pose estimation from a single image via distance matrix regression. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.170"},{"key":"1740_CR22","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"1740_CR23","doi-asserted-by":"crossref","unstructured":"Nie, B.X., Wei, P., Zhu, S.C.: Monocular 3d human pose estimation by predicting depth on joints. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.373"},{"key":"1740_CR24","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K.: Coarse-to-fine volumetric prediction for single-image 3d human pose. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.139"},{"key":"1740_CR25","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3d human pose and shape from a single color image. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00055"},{"key":"1740_CR26","doi-asserted-by":"crossref","unstructured":"Peng, X., Tang, Z., Yang, F., Feris, R.S., Metaxas, D.: Jointly optimize data augmentation and network training: adversarial data augmentation in human pose estimation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00237"},{"key":"1740_CR27","doi-asserted-by":"crossref","unstructured":"Pfister, T., Charles, J., Zisserman, A.: Flowing convnets for human pose estimation in videos. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.222"},{"key":"1740_CR28","doi-asserted-by":"crossref","unstructured":"Popa, A., Zanfir, M., Sminchisescu, C.: Deep multitask architecture for integrated 2d and 3d human sensing. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.501"},{"issue":"9","key":"1740_CR29","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1007\/s11263-018-1071-9","volume":"126","author":"G Rogez","year":"2018","unstructured":"Rogez, G., Schmid, C.: Image-based synthesis for deep 3d human pose estimation. Int. J. Comput. Vis. 126(9), 993\u20131008 (2018)","journal-title":"Int. J. Comput. Vis."},{"key":"1740_CR30","doi-asserted-by":"crossref","unstructured":"Rogez, G., Weinzaepfel, P., Schmid, C.: Lcr-net: Localization-classification-regression for human pose. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.134"},{"key":"1740_CR31","doi-asserted-by":"crossref","unstructured":"Sanzari, M., Ntouskos, V., Pirri, F.: Bayesian image based 3d pose estimation. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_34"},{"key":"1740_CR32","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, I.A.: 3d human pose estimation: a review of the literature and analysis of covariates. Comput. Vis. Image Underst. 152, 1\u201320 (2016)","journal-title":"Comput. Vis. Image Underst."},{"key":"1740_CR33","doi-asserted-by":"crossref","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Learning 3-d scene structure from a single still image. In: ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408828"},{"key":"1740_CR34","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/s11263-011-0493-4","volume":"98","author":"L Sigal","year":"2012","unstructured":"Sigal, L., Isard, M., Haussecker, H., Black, M.J.: Loose-limbed people: estimating 3d human pose and motion using non-parametric belief propagation. Int. J. Comput. Vis. 98, 15\u201348 (2012)","journal-title":"Int. J. Comput. Vis."},{"key":"1740_CR35","doi-asserted-by":"crossref","unstructured":"Song, J., Wang, L., Gool, L.V., Hilliges, O.: Thin-slicing network: a deep structured model for pose estimation in videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.590"},{"key":"1740_CR36","unstructured":"Tekin, B., Katircioglu, I., Salzmann, M., Lepetit, V., Fua, P.: Structured prediction of 3d human pose with deep neural networks (2016). arXiv preprint \narXiv:1605.05180"},{"key":"1740_CR37","unstructured":"Tekin, B., M\u00e1rquez-Neila, P., Salzmann, M., Fua, P.: Fusing 2d uncertainty and 3d cues for monocular body pose estimation (2016). arXiv preprint \narXiv:1611.05708"},{"key":"1740_CR38","doi-asserted-by":"crossref","unstructured":"Tekin, B., Rozantsev, A., Lepetit, V., Fua, P.: Direct prediction of 3d body poses from motion compensated sequences. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.113"},{"key":"1740_CR39","doi-asserted-by":"crossref","unstructured":"Tome, D., Russell, C., Agapito, L.: Lifting from the deep: convolutional 3d pose estimation from a single image. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.603"},{"key":"1740_CR40","doi-asserted-by":"publisher","first-page":"1227","DOI":"10.1109\/TPAMI.2018.2828427","volume":"41","author":"C Wang","year":"2018","unstructured":"Wang, C., Wang, Y., Lin, Z., Yuille, A.: Robust 3d human pose estimation from single images or video sequences. IEEE Trans. Pattern Anal. Mach. Intell. 41, 1227\u20131241 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1740_CR41","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"1740_CR42","doi-asserted-by":"crossref","unstructured":"Yasin, H., Iqbal, U., Kruger, B., Weber, A., Gall, J.: A dual-source approach for 3d pose estimation from a single image. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.535"},{"issue":"8","key":"1740_CR43","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1109\/34.784284","volume":"21","author":"R Zhang","year":"1999","unstructured":"Zhang, R., Tsai, P.S., Cryer, J.E., Shah, M.: Shape from shading: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 21(8), 690\u2013706 (1999)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1740_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, X., Huang, Q., Sun, X., Xue, X., Wei, Y.: Towards 3d human pose estimation in the wild: a weakly-supervised approach. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.51"},{"key":"1740_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, X., Sun, X., Zhang, W., Liang, S., Wei, Y.: Deep kinematic pose regression. In: ECCV (2016)","DOI":"10.1007\/978-3-319-49409-8_17"},{"key":"1740_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhu, M., Leonardos, S., Derpanis, K.G., Daniilidis, K.: Sparseness meets deepness: 3d human pose estimation from monocular video. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.537"},{"key":"1740_CR47","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1109\/TPAMI.2018.2816031","volume":"41","author":"X Zhou","year":"2018","unstructured":"Zhou, X., Zhu, M., Pavlakos, G., Leonardos, S., Derpanis, K.G., Daniilidis, K.: Monocap: monocular human motion capture using a cnn coupled with a geometric prior. IEEE Trans. Pattern Anal. Mach. Intell. 41, 901\u2013914 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-019-01740-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00371-019-01740-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-019-01740-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T23:10:02Z","timestamp":1599001802000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00371-019-01740-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,3]]},"references-count":47,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["1740"],"URL":"https:\/\/doi.org\/10.1007\/s00371-019-01740-4","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2019,9,3]]},"assertion":[{"value":"3 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"All authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}