{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:44:05Z","timestamp":1780357445847,"version":"3.54.1"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585648","type":"print"},{"value":"9783030585655","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\/978-3-030-58565-5_24","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T12:03:19Z","timestamp":1605096199000},"page":"396-412","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Occlusion-Aware Siamese Network for Human Pose Estimation"],"prefix":"10.1007","author":[{"given":"Lu","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingying","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunze","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanqing","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"key":"24_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: Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"24_CR2","unstructured":"Chen, L., et al.: Symmetric variational autoencoder and connections to adversarial learning. In: International Conference on Artificial Intelligence and Statistics, pp. 661\u2013669 (2018)"},{"key":"24_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":"24_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Shen, C., Wei, X.S., Liu, L., Yang, J.: Adversarial PoseNet: a structure-aware convolutional network for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1212\u20131221 (2017)","DOI":"10.1109\/ICCV.2017.137"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chou, C.J., Chien, J.T., Chen, H.T.: Self adversarial training for human pose estimation. arXiv preprint arXiv:1707.02439 (2017)","DOI":"10.23919\/APSIPA.2018.8659538"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Chu, X., Ouyang, W., Li, H., Wang, X.: Structured feature learning for pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4715\u20134723 (2016)","DOI":"10.1109\/CVPR.2016.510"},{"key":"24_CR7","unstructured":"Chu, X., Ouyang, W., Wang, X., et al.: CRF-CNN: modeling structured information in human pose estimation. In: Advances in Neural Information Processing Systems, pp. 316\u2013324 (2016)"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1831\u20131840 (2017)","DOI":"10.1109\/CVPR.2017.601"},{"key":"24_CR9","unstructured":"Genevay, A., Peyr\u00e9, G., Cuturi, M.: Learning generative models with Sinkhorn divergences. arXiv preprint arXiv:1706.00292 (2017)"},{"key":"24_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-319-46466-4_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"E Insafutdinov","year":"2016","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34\u201350. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_3"},{"key":"24_CR11","unstructured":"Jain, A., Tompson, J., Andriluka, M., Taylor, G.W., Bregler, C.: Learning human pose estimation features with convolutional networks. arXiv preprint arXiv:1312.7302 (2013)"},{"key":"24_CR12","unstructured":"Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: BMVC, vol. 2, p. 5. Citeseer (2010)"},{"key":"24_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1007\/978-3-030-01216-8_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L Ke","year":"2018","unstructured":"Ke, L., Chang, M.-C., Qi, H., Lyu, S.: Multi-scale structure-aware network for human pose estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 731\u2013746. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_44"},{"key":"24_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"24_CR15","unstructured":"Li, H., Dai, B., Shi, S., Ouyang, W., Wang, X.: Feature intertwiner for object detection. In: International Conference on Learning Representations (2018)"},{"key":"24_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, J., Li, C., Qian, C., Chu, X., Hu, X.: A cascaded inception of inception network with attention modulated feature fusion for human pose estimation. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12334"},{"key":"24_CR18","unstructured":"Lu, Y., Chen, L., Saidi, A.: Optimal transport for deep joint transfer learning. arXiv preprint arXiv:1709.02995 (2017)"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Marras, I., Palasek, P., Patras, I.: Deep globally constrained MRFs for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3466\u20133475 (2017)","DOI":"10.1109\/ICCV.2017.375"},{"issue":"3","key":"24_CR20","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1006\/cviu.2000.0897","volume":"81","author":"TB Moeslund","year":"2001","unstructured":"Moeslund, T.B., Granum, E.: A survey of computer vision-based human motion capture. Comput. Vis. Image Underst. 81(3), 231\u2013268 (2001)","journal-title":"Comput. Vis. Image Underst."},{"key":"24_CR21","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":"24_CR22","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Zuo, Y., Yan, S.: Human pose estimation with parsing induced learner. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2100\u20132108 (2018)","DOI":"10.1109\/CVPR.2018.00224"},{"issue":"5","key":"24_CR23","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.1109\/TMM.2017.2762010","volume":"20","author":"G Ning","year":"2018","unstructured":"Ning, G., Zhang, Z., He, Z.: Knowledge-guided deep fractal neural networks for human pose estimation. IEEE Trans. Multimedia 20(5), 1246\u20131259 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Rafi, U., Leibe, B., Gall, J., Kostrikov, I.: An efficient convolutional network for human pose estimation. In: BMVC, vol. 1, p. 2 (2016)","DOI":"10.5244\/C.30.109"},{"key":"24_CR25","unstructured":"Salimans, T., Zhang, H., Radford, A., Metaxas, D.: Improving GANs using optimal transport. arXiv preprint arXiv:1803.05573 (2018)"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Skeleton-based action recognition with directed graph neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7912\u20137921 (2019)","DOI":"10.1109\/CVPR.2019.00810"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Su, C., Li, J., Zhang, S., Xing, J., Gao, W., Tian, Q.: Pose-driven deep convolutional model for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3960\u20133969 (2017)","DOI":"10.1109\/ICCV.2017.427"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Tang, W., Wu, Y.: Does learning specific features for related parts help human pose estimation? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1107\u20131116 (2019)","DOI":"10.1109\/CVPR.2019.00120"},{"key":"24_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/978-3-030-01219-9_12","volume-title":"Computer Vision \u2013 ECCV 2018","author":"W Tang","year":"2018","unstructured":"Tang, W., Yu, P., Wu, Y.: Deeply learned compositional models for human pose estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 197\u2013214. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_12"},{"key":"24_CR31","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-RMSprop: divide the gradient by a running average of its recent magnitude. COURSERA Neural Netw. Mach. Learn. 4(2), 26\u201331 (2012)"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 648\u2013656 (2015)","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"24_CR33","unstructured":"Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in Neural Information Processing Systems, pp. 1799\u20131807 (2014)"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131660 (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"24_CR35","unstructured":"Wang, W., Xu, H., Wang, G., Wang, W., Carin, L.: An optimal transport framework for zero-shot learning. arXiv preprint arXiv:1910.09057 (2019)"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4724\u20134732 (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"24_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-030-01231-1_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Xiao","year":"2018","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 472\u2013487. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_29"},{"key":"24_CR38","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":"24_CR39","doi-asserted-by":"crossref","unstructured":"Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1290\u20131299. IEEE (2017)","DOI":"10.1109\/ICCV.2017.144"},{"key":"24_CR40","unstructured":"Zhang, H., et al.: Human pose estimation with spatial contextual information. arXiv preprint arXiv:1901.01760 (2019)"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, L., Chen, Y., Wang, J., Lu, H.: Progressive bi-c3d pose grammar for human pose estimation. In: AAAI, pp. 13033\u201313040 (2020)","DOI":"10.1609\/aaai.v34i07.7004"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, L., Chen, Y., Wang, J., Tang, M., Lu, H.: Bi-directional message passing based scanet for human pose estimation. In: 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 1048\u20131053. IEEE (2019)","DOI":"10.1109\/ICME.2019.00184"}],"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\/978-3-030-58565-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:08:22Z","timestamp":1731283702000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58565-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585648","9783030585655"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58565-5_24","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":"12 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.","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)"}}]}}