{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T21:51:04Z","timestamp":1786139464670,"version":"3.56.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030695248","type":"print"},{"value":"9783030695255","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69525-5_14","type":"book-chapter","created":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T16:21:16Z","timestamp":1614356476000},"page":"227-243","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Anatomy and Geometry Constrained One-Stage Framework for 3D Human Pose Estimation"],"prefix":"10.1007","author":[{"given":"Xin","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,27]]},"reference":[{"key":"14_CR1","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":"14_CR2","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, 1325\u20131339 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR3","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1023\/B:VISI.0000042934.15159.49","volume":"61","author":"PF Felzenszwalb","year":"2005","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. Int. J. Comput. Vis. 61, 55\u201379 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Yub Jung, H., Lee, S., Seok Heo, Y., Dong Yun, I.: Random tree walk toward instantaneous 3D human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2467\u20132474 (2015)","DOI":"10.1109\/CVPR.2015.7298861"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 2017 Fifth International Conference on 3D Vision (3DV). IEEE (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"14_CR6","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 398\u2013407 (2017)","DOI":"10.1109\/ICCV.2017.51"},{"key":"14_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/978-3-030-01231-1_33","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Sun","year":"2018","unstructured":"Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y.: Integral human pose regression. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 536\u2013553. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_33"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Yang, W., Ouyang, W., Wang, X., Ren, J., Li, H., Wang, X.: 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 (2018)","DOI":"10.1109\/CVPR.2018.00551"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Rhodin, H., Salzmann, M., Fua, P.: Unsupervised geometry-aware representation for 3D human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 750\u2013767 (2018)","DOI":"10.1007\/978-3-030-01249-6_46"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Li, C., Lee, G.H.: Generating multiple hypotheses for 3D human pose estimation with mixture density network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9887\u20139895 (2019)","DOI":"10.1109\/CVPR.2019.01012"},{"key":"14_CR11","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta, D., et al.: VNect: real-time 3D human pose estimation with a single RGB camera. ACM Trans. Graph. 36, 44 (2017)","journal-title":"ACM Trans. Graph."},{"key":"14_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Sun, X., Shang, J., Liang, S., Wei, Y.: Compositional human pose regression. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2602\u20132611 (2017)","DOI":"10.1109\/ICCV.2017.284"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Habibie, I., Xu, W., Mehta, D., Pons-Moll, G., Theobalt, C.: In the wild human pose estimation using explicit 2D features and intermediate 3D representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10905\u201310914 (2019)","DOI":"10.1109\/CVPR.2019.01116"},{"key":"14_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1007\/978-3-319-16808-1_23","volume-title":"Computer Vision \u2013 ACCV 2014","author":"S Li","year":"2015","unstructured":"Li, S., Chan, A.B.: 3D human pose estimation from monocular images with deep convolutional neural network. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9004, pp. 332\u2013347. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16808-1_23"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Tekin, B., Katircioglu, I., Salzmann, M., Lepetit, V., Fua, P.: Structured prediction of 3D human pose with deep neural networks. arXiv preprint arXiv:1605.05180 (2016)","DOI":"10.5244\/C.30.130"},{"key":"14_CR17","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7025\u20137034 (2017)","DOI":"10.1109\/CVPR.2017.139"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Rhodin, H., et al.: 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 (2018)","DOI":"10.1109\/CVPR.2018.00880"},{"key":"14_CR19","unstructured":"Mount, D.M.: CMSC 425 game programming (2013)"},{"key":"14_CR20","unstructured":"Zhou, X., Wan, Q., Zhang, W., Xue, X., Wei, Y.: Model-based deep hand pose estimation. arXiv preprint arXiv:1606.06854 (2016)"},{"key":"14_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1007\/978-3-319-49409-8_17","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"X Zhou","year":"2016","unstructured":"Zhou, X., Sun, X., Zhang, W., Liang, S., Wei, Y.: Deep kinematic pose regression. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 186\u2013201. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_17"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Chen, C.H., Ramanan, D.: 3D human pose estimation = 2D pose estimation + matching. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.610"},{"key":"14_CR23","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"14_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1007\/978-3-030-11018-5_7","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"D Drover","year":"2019","unstructured":"Drover, D., Rohith, M.V., Chen, C.-H., Agrawal, A., Tyagi, A., Huynh, C.P.: Can 3D pose be learned from 2D projections alone? In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11132, pp. 78\u201394. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11018-5_7"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Wandt, B., Rosenhahn, B.: RepNet: weakly supervised training of an adversarial reprojection network for 3D human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7782\u20137791 (2019)","DOI":"10.1109\/CVPR.2019.00797"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Akhter, I., Black, M.J.: Pose-conditioned joint angle limits for 3D human pose reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1446\u20131455 (2015)","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.N.: Semantic graph convolutional networks for 3D human pose regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3425\u20133435 (2019)","DOI":"10.1109\/CVPR.2019.00354"},{"key":"14_CR28","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: Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"14_CR29","unstructured":"S\u00e1r\u00e1ndi, I., Linder, T., Arras, K.O., Leibe, B.: How robust is 3D human pose estimation to occlusion? arXiv preprint arXiv:1808.09316 (2018)"},{"key":"14_CR30","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024\u20138035 (2019)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Rogez, G., Weinzaepfel, P., Schmid, C.: LCR- Net: localization-classification-regression for human pose. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.134"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Trumble, M., Gilbert, A., Malleson, C., Hilton, A., Collomosse, J.: Total capture: 3D human pose estimation fusing video and inertial sensors. In: British Machine Vision Conference 2017 (2017)","DOI":"10.5244\/C.31.14"},{"key":"14_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1007\/978-3-030-01249-6_48","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Trumble","year":"2018","unstructured":"Trumble, M., Gilbert, A., Hilton, A., Collomosse, J.: Deep autoencoder for combined human pose estimation and body model upscaling. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 800\u2013816. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_48"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Mehta, D., Sotnychenko, O., Mueller, F., Xu, W., Theobalt, C.: Single-shot multi-person 3D pose estimation from monocular RGB. In: 2018 International Conference on 3D Vision (3DV) (2018)","DOI":"10.1109\/3DV.2018.00024"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Chen, C.H., Tyagi, A., Agrawal, A., Drover, D., Stojanov, S., Rehg, J.M.: Unsupervised 3D pose estimation with geometric self-supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5714\u20135724 (2019)","DOI":"10.1109\/CVPR.2019.00586"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69525-5_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T16:47:33Z","timestamp":1614358053000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69525-5_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695248","9783030695255"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69525-5_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"27 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"254","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}