{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:36:04Z","timestamp":1774539364983,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586003","type":"print"},{"value":"9783030586010","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58601-0_45","type":"book-chapter","created":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T19:02:52Z","timestamp":1606503772000},"page":"764-780","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":176,"title":["Motion Guided 3D Pose Estimation from Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9700-6262","authenticated-orcid":false,"given":"Jingbo","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4398-0590","authenticated-orcid":false,"given":"Sijie","family":"Yan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6391-4921","authenticated-orcid":false,"given":"Yuanjun","family":"Xiong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8865-7896","authenticated-orcid":false,"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,28]]},"reference":[{"key":"45_CR1","unstructured":"Atwood, J., Towsley, D.: Diffusion-convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1993\u20132001 (2016)"},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Y., et al.: Exploiting spatial-temporal relationships for 3D pose estimation via graph convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2272\u20132281 (2019)","DOI":"10.1109\/ICCV.2019.00236"},{"key":"45_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"45_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Yang, B., Wang, B., Yan, W., Tan, R.T.: Occlusion-aware networks for 3D human pose estimation in video. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 723\u2013732 (2019)","DOI":"10.1109\/ICCV.2019.00081"},{"key":"45_CR5","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mundhada, A., Kusupati, U., Afaque, S., Sharma, A., Jain, A.: Learning 3D human pose from structure and motion. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 668\u2013683 (2018)","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"45_CR6","unstructured":"Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems, pp. 3844\u20133852 (2016)"},{"key":"45_CR7","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xu, Y., Wang, W., Liu, X., Zhu, S.C.: Learning pose grammar to encode human body configuration for 3D pose estimation. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12270"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Carreira, J., Sminchisescu, C.: Iterated second-order label sensitive pooling for 3D human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1661\u20131668 (2014)","DOI":"10.1109\/CVPR.2014.215"},{"key":"45_CR9","doi-asserted-by":"crossref","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 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"45_CR10","doi-asserted-by":"crossref","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)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Iskakov, K., Burkov, E., Lempitsky, V., Malkov, Y.: Learnable triangulation of human pose. arXiv preprint arXiv:1905.05754 (2019)","DOI":"10.1109\/ICCV.2019.00781"},{"key":"45_CR12","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Lee, K., Lee, I., Lee, S.: Propagating LSTM: 3D pose estimation based on joint interdependency. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 119\u2013135 (2018)","DOI":"10.1007\/978-3-030-01234-2_8"},{"key":"45_CR14","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":"45_CR15","unstructured":"Lin, J., Lee, G.H.: Trajectory space factorization for deep video-based 3D human pose estimation. arXiv preprint arXiv:1908.08289 (2019)"},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"Lin, M., Lin, L., Liang, X., Wang, K., Cheng, H.: Recurrent 3D pose sequence machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 810\u2013819 (2017)","DOI":"10.1109\/CVPR.2017.588"},{"key":"45_CR17","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":"45_CR18","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/3dv.2017.00064","DOI":"10.1109\/3dv.2017.00064"},{"issue":"4","key":"45_CR19","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. (TOG) 36(4), 44 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"45_CR20","unstructured":"Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: International Conference on Machine Learning, pp. 2014\u20132023 (2016)"},{"key":"45_CR21","doi-asserted-by":"crossref","unstructured":"Ning, G., Huang, H.: Lighttrack: A generic framework for online top-down human pose tracking. arXiv preprint arXiv:1905.02822 (2019)","DOI":"10.1109\/CVPRW50498.2020.00525"},{"key":"45_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-319-49409-8_15","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"S Park","year":"2016","unstructured":"Park, S., Hwang, J., Kwak, N.: 3D human pose estimation using convolutional neural networks with 2D pose information. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 156\u2013169. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_15"},{"key":"45_CR23","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Daniilidis, K.: Ordinal depth supervision for 3D human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7307\u20137316 (2018)","DOI":"10.1109\/CVPR.2018.00763"},{"key":"45_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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7025\u20137034 (2017)","DOI":"10.1109\/CVPR.2017.139"},{"key":"45_CR25","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"45_CR26","doi-asserted-by":"crossref","unstructured":"Qiu, H., Wang, C., Wang, J., Wang, N., Zeng, W.: Cross view fusion for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4342\u20134351 (2019)","DOI":"10.1109\/ICCV.2019.00444"},{"key":"45_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1007\/978-3-642-33765-9_41","volume-title":"Computer Vision \u2013 ECCV 2012","author":"V Ramakrishna","year":"2012","unstructured":"Ramakrishna, V., Kanade, T., Sheikh, Y.: Reconstructing 3D human pose from 2D image landmarks. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 573\u2013586. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33765-9_41"},{"key":"45_CR28","doi-asserted-by":"crossref","unstructured":"Rayat Imtiaz Hossain, M., Little, J.J.: Exploiting temporal information for 3D human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 68\u201384 (2018)","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"45_CR29","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, June 2019","DOI":"10.1109\/CVPR.2019.00584"},{"key":"45_CR30","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":"45_CR31","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":"45_CR32","doi-asserted-by":"crossref","unstructured":"Tekin, B., M\u00e1rquez-Neila, P., Salzmann, M., Fua, P.: 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 (2017)","DOI":"10.1109\/ICCV.2017.425"},{"key":"45_CR33","doi-asserted-by":"crossref","unstructured":"Tekin, B., Rozantsev, A., Lepetit, V., Fua, P.: Direct prediction of 3D body poses from motion compensated sequences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 991\u20131000 (2016)","DOI":"10.1109\/CVPR.2016.113"},{"key":"45_CR34","doi-asserted-by":"crossref","unstructured":"Tome, D., Russell, C., Agapito, L.: 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 (2017)","DOI":"10.1109\/CVPR.2017.603"},{"key":"45_CR35","doi-asserted-by":"crossref","unstructured":"Yan, S., Li, Z., Xiong, Y., Yan, H., Lin, D.: Convolutional sequence generation for skeleton-based action synthesis. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4394\u20134402 (2019)","DOI":"10.1109\/ICCV.2019.00449"},{"key":"45_CR36","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"45_CR37","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":"45_CR38","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4903\u20134911 (2017)","DOI":"10.1109\/ICCV.2017.525"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58601-0_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:20:50Z","timestamp":1732666850000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58601-0_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586003","9783030586010"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58601-0_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"28 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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 due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}