{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:07:16Z","timestamp":1771952836760,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. U21B2013, 62325109"],"award-info":[{"award-number":["No. U21B2013, 62325109"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658110","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"589-598","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Visibility-guided Human Body Reconstruction from Uncalibrated Multi-view Cameras"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7394-5183","authenticated-orcid":false,"given":"Zhenyu","family":"Xie","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4110-1919","authenticated-orcid":false,"given":"Huanyu","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4307-8152","authenticated-orcid":false,"given":"Gui","family":"Zou","sequence":"additional","affiliation":[{"name":"AVIC Aeronautical Radio Electronics Research Institute, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8937-6791","authenticated-orcid":false,"given":"Jie","family":"Wu","sequence":"additional","affiliation":[{"name":"AVIC Aeronautical Radio Electronics Research Institute, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2813-2051","authenticated-orcid":false,"given":"Guoliang","family":"Liu","sequence":"additional","affiliation":[{"name":"AVIC Aeronautical Radio Electronics Research Institute, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2920-7448","authenticated-orcid":false,"given":"Jun","family":"Zhao","sequence":"additional","affiliation":[{"name":"AVIC Aeronautical Radio Electronics Research Institute, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0818-7885","authenticated-orcid":false,"given":"Yingxue","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Risk Perception and Prevention, China Academic of Electronics and Information Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5519-1954","authenticated-orcid":false,"given":"Hui","family":"Lin","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Risk Perception and Prevention, China Academic of Electronics and Information Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8307-7107","authenticated-orcid":false,"given":"Weiyao","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073207"},{"key":"e_1_3_2_1_2_1","volume-title":"Computer Vision--ECCV 2008: 10th European Conference on Computer Vision","author":"Black Alexandru O","year":"2008","unstructured":"Alexandru O Bua lan and Michael J Black. 2008. The naked truth: Estimating body shape under clothing. In Computer Vision--ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, October 12--18, 2008, Proceedings, Part II 10. Springer, 15--29."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.216"},{"key":"e_1_3_2_1_4_1","volume-title":"3d pictorial structures revisited: Multiple human pose estimation","author":"Belagiannis Vasileios","year":"2015","unstructured":"Vasileios Belagiannis, Sikandar Amin, Mykhaylo Andriluka, Bernt Schiele, Nassir Navab, and Slobodan Ilic. 2015. 3d pictorial structures revisited: Multiple human pose estimation. IEEE transactions on pattern analysis and machine intelligence, Vol. 38, 10 (2015), 1929--1942."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings, Part V 14","author":"Bogo Federica","year":"2016","unstructured":"Federica Bogo, Angjoo Kanazawa, Christoph Lassner, Peter Gehler, Javier Romero, and Michael J Black. 2016. Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part V 14. Springer, 561--578."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.464"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings, Part VII 16","author":"Choi Hongsuk","year":"2020","unstructured":"Hongsuk Choi, Gyeongsik Moon, and Kyoung Mu Lee. 2020. Pose2mesh: Graph convolutional network for 3d human pose and mesh recovery from a 2d human pose. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part VII 16. Springer, 769--787."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings, Part X 16","author":"Choutas Vasileios","year":"2020","unstructured":"Vasileios Choutas, Georgios Pavlakos, Timo Bolkart, Dimitrios Tzionas, and Michael J Black. 2020. Monocular expressive body regression through body-driven attention. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part X 16. Springer, 20--40."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-020-01064-7"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01097"},{"key":"e_1_3_2_1_12_1","volume-title":"RMPE: Regional Multi-person Pose Estimation. In ICCV.","author":"Fang Hao-Shu","year":"2017","unstructured":"Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, and Cewu Lu. 2017. RMPE: Regional Multi-person Pose Estimation. In ICCV."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_33"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings, Part XVII 16","author":"Georgakis Georgios","year":"2020","unstructured":"Georgios Georgakis, Ren Li, Srikrishna Karanam, Terrence Chen, Jana Kovs eck\u00e1, and Ziyan Wu. 2020. Hierarchical kinematic human mesh recovery. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XVII 16. Springer, 768--784."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459300"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01114"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539853"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00526"},{"key":"e_1_3_2_1_20_1","volume-title":"Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior. arXiv preprint arXiv:2207.05375","author":"Huang Buzhen","year":"2022","unstructured":"Buzhen Huang, Yuan Shu, Jingyi Ju, and Yangang Wang. 2022a. Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior. arXiv preprint arXiv:2207.05375 (2022)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00080"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3199449"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.330"},{"key":"e_1_3_2_1_24_1","volume-title":"6m: Large scale datasets and predictive methods for 3d human sensing in natural environments","author":"Ionescu Catalin","year":"2013","unstructured":"Catalin Ionescu, Dragos Papava, Vlad Olaru, and Cristian Sminchisescu. 2013. Human3. 6m: Large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE transactions on pattern analysis and machine intelligence, Vol. 36, 7 (2013), 1325--1339."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00781"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25179"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00015"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00744"},{"key":"e_1_3_2_1_29_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00234"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00463"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01140"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.500"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00445"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661273"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.288"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_44"},{"key":"e_1_3_2_1_41_1","volume-title":"Pose2pose: 3d positional pose-guided 3d rotational pose prediction for expressive 3d human pose and mesh estimation. arXiv preprint arXiv:2011.11534","author":"Moon Gyeongsik","year":"2020","unstructured":"Gyeongsik Moon and Kyoung Mu Lee. 2020b. Pose2pose: 3d positional pose-guided 3d rotational pose prediction for expressive 3d human pose and mesh estimation. arXiv preprint arXiv:2011.11534, Vol. 1, 2 (2020)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00986"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings, Part VIII 14","author":"Newell Alejandro","year":"2016","unstructured":"Alejandro Newell, Kaiyu Yang, and Jia Deng. 2016. Stacked hourglass networks for human pose estimation. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part VIII 14. Springer, 483--499."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00062"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00055"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00444"},{"key":"e_1_3_2_1_47_1","volume-title":"How robust is 3D human pose estimation to occlusion? arXiv preprint arXiv:1808.09316","author":"S\u00e1r\u00e1ndi Istv\u00e1n","year":"2018","unstructured":"Istv\u00e1n S\u00e1r\u00e1ndi, Timm Linder, Kai O Arras, and Bastian Leibe. 2018. How robust is 3D human pose estimation to occlusion? arXiv preprint arXiv:1808.09316 (2018)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01583"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01364"},{"key":"e_1_3_2_1_50_1","volume-title":"Multi-view human pose and shape estimation using learnable volumetric aggregation. arXiv preprint arXiv:2011.13427","author":"Shin Soyong","year":"2020","unstructured":"Soyong Shin and Eni Halilaj. 2020. Multi-view human pose and shape estimation using learnable volumetric aggregation. arXiv preprint arXiv:2011.13427 (2020)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3188716"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.603"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_2"},{"key":"e_1_3_2_1_56_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems , Vol. 30 (2017)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01122"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01370"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00785"},{"key":"e_1_3_2_1_61_1","volume-title":"Legoformer: Transformers for block-by-block multi-view 3d reconstruction. arXiv preprint arXiv:2106.12102","author":"Yagubbayli Farid","year":"2021","unstructured":"Farid Yagubbayli, Yida Wang, Alessio Tonioni, and Federico Tombari. 2021. Legoformer: Transformers for block-by-block multi-view 3d reconstruction. arXiv preprint arXiv:2106.12102 (2021)."},{"key":"e_1_3_2_1_62_1","volume-title":"Densebody: Directly regressing dense 3d human pose and shape from a single color image. arXiv preprint arXiv:1903.10153","author":"Yao Pengfei","year":"2019","unstructured":"Pengfei Yao, Zheng Fang, Fan Wu, Yao Feng, and Jiwei Li. 2019. Densebody: Directly regressing dense 3d human pose and shape from a single color image. arXiv preprint arXiv:1903.10153 (2019)."},{"key":"e_1_3_2_1_63_1","first-page":"7879","article-title":"Multiview Human Body Reconstruction from Uncalibrated Cameras","volume":"35","author":"Yu Zhixuan","year":"2022","unstructured":"Zhixuan Yu, Linguang Zhang, Yuanlu Xu, Chengcheng Tang, Luan Tran, Cem Keskin, and Hyun Soo Park. 2022. Multiview Human Body Reconstruction from Uncalibrated Cameras. Advances in Neural Information Processing Systems , Vol. 35 (2022), 7879--7891.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_64_1","volume-title":"Proceedings, Part VI 16","author":"Zanfir Andrei","year":"2020","unstructured":"Andrei Zanfir, Eduard Gabriel Bazavan, Hongyi Xu, William T Freeman, Rahul Sukthankar, and Cristian Sminchisescu. 2020. Weakly supervised 3d human pose and shape reconstruction with normalizing flows. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part VI 16. Springer, 465--481."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00229"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00708"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01125"},{"key":"e_1_3_2_1_68_1","first-page":"13153","article-title":"Direct multi-view multi-person 3d pose estimation","volume":"34","author":"Zhang Jianfeng","year":"2021","unstructured":"Jianfeng Zhang, Yujun Cai, Shuicheng Yan, Jiashi Feng, et al. 2021a. Direct multi-view multi-person 3d pose estimation. Advances in Neural Information Processing Systems , Vol. 34 (2021), 13153--13164.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00740"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00140"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00551"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00618"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658110","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:52:40Z","timestamp":1755766360000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658110"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":72,"alternative-id":["10.1145\/3652583.3658110","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658110","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}