{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T23:40:41Z","timestamp":1769557241764,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Zhejiang Provincial Science and Technology Program in China","award":["LQ22F020026"],"award-info":[{"award-number":["LQ22F020026"]}]},{"name":"the National Natural Science Foundation of China","award":["62202130, U22A2033, U20A20386, 62302134"],"award-info":[{"award-number":["62202130, U22A2033, U20A20386, 62302134"]}]},{"name":"the Open project of State Key Laboratory of CAD & CG at Zhejiang University","award":["A2212"],"award-info":[{"award-number":["A2212"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680990","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"10363-10372","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["3D Human Pose Estimation from Multiple Dynamic Views via Single-view Pretraining with Procrustes Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3900-2148","authenticated-orcid":false,"given":"Renshu","family":"Gu","sequence":"first","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5232-8692","authenticated-orcid":false,"given":"Jiajun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2903-5345","authenticated-orcid":false,"given":"Yixuan","family":"Si","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8714-0975","authenticated-orcid":false,"given":"Fei","family":"Gao","sequence":"additional","affiliation":[{"name":"Hangzhou Institute of Technology, Xidian University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7750-7761","authenticated-orcid":false,"given":"Jiamin","family":"Xu","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3557-9529","authenticated-orcid":false,"given":"Gang","family":"Xu","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.216"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00586"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00334"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01115"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16194"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"e_1_3_2_1_8_1","volume-title":"ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention. arXiv preprint arXiv:2304.02147","author":"Diaz-Arias Alec","year":"2023","unstructured":"Alec Diaz-Arias and Dmitriy Shin. 2023. ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention. arXiv preprint arXiv:2304.02147 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00798"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0--0.","author":"Drover Dylan","year":"2018","unstructured":"Dylan Drover, Rohith MV, Ching-Hang Chen, Amit Agrawal, Ambrish Tyagi, and Cong Phuoc Huynh. 2018. Can 3d pose be learned from 2d projections alone?. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0--0."},{"key":"e_1_3_2_1_11_1","volume-title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","author":"Fang Hao-Shu","year":"2022","unstructured":"Hao-Shu Fang, Jiefeng Li, Hongyang Tang, Chao Xu, Haoyi Zhu, Yuliang Xiu, Yong-Lu Li, and Cewu Lu. 2022. AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs8080671"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_11"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00780"},{"key":"e_1_3_2_1_15_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_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00529"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00781"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.381"},{"key":"e_1_3_2_1_19_1","unstructured":"Hanbyul Joo Natalia Neverova and Andrea Vedaldi. 2020. Exemplar Fine-Tuning for 3D Human Pose Fitting Towards In-the-Wild 3D Human Pose Estimation. In 3DV."},{"key":"e_1_3_2_1_20_1","volume-title":"Anipose: a toolkit for robust markerless 3D pose estimation. Cell reports","author":"Karashchuk Pierre","year":"2021","unstructured":"Pierre Karashchuk, Katie L Rupp, Evyn S Dickinson, Sarah Walling-Bell, Elischa Sanders, Eiman Azim, Bingni W Brunton, and John C Tuthill. 2021. Anipose: a toolkit for robust markerless 3D pose estimation. Cell reports, Vol. 36, 13 (2021)."},{"key":"e_1_3_2_1_21_1","volume-title":"Proc. International Conference on Computer Vision (ICCV). 11127--11137","author":"Kocabas Muhammed","unstructured":"Muhammed Kocabas, Chun-Hao P. Huang, Otmar Hilliges, and Michael J. Black. 2021. PARE: Part Attention Regressor for 3D Human Body Estimation. In Proc. International Conference on Computer Vision (ICCV). 11127--11137."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00117"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Nikos Kolotouros Georgios Pavlakos Michael J Black and Kostas Daniilidis. 2019. Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop. In ICCV.","DOI":"10.1109\/ICCV.2019.00234"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Kevin Lin Lijuan Wang and Zicheng Liu. 2021. End-to-End Human Pose and Mesh Reconstruction with Transformers. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01570-9"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.288"},{"key":"e_1_3_2_1_29_1","volume-title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network. arXiv preprint arXiv:2310.16288","author":"Mehraban Soroush","year":"2023","unstructured":"Soroush Mehraban, Vida Adeli, and Babak Taati. 2023. MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network. arXiv preprint arXiv:2310.16288 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"MEEV: Body Mesh Estimation On Egocentric Video. arXiv preprint arXiv:2210.14165","author":"Monet Nicolas","year":"2022","unstructured":"Nicolas Monet and Dongyoon Wee. 2022. MEEV: Body Mesh Estimation On Egocentric Video. arXiv preprint arXiv:2210.14165 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00794"},{"key":"e_1_3_2_1_32_1","volume-title":"HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation. arXiv preprint arXiv:2301.07322","author":"Qian Xiaoye","year":"2023","unstructured":"Xiaoye Qian, Youbao Tang, Ning Zhang, Mei Han, Jing Xiao, Ming-Chun Huang, and Ruei-Sung Lin. 2023. HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation. arXiv preprint arXiv:2301.07322 (2023)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00444"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01494"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00880"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings, Part I 16","author":"Tu Hanyue","year":"2020","unstructured":"Hanyue Tu, Chunyu Wang, and Wenjun Zeng. 2020. Voxelpose: Towards multi-camera 3d human pose estimation in wild environment. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part I 16. Springer, 197--212."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00664"},{"key":"e_1_3_2_1_38_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_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00797"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01309"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103225"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_11"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612098"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.51"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01385"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680990","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:35Z","timestamp":1750295855000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680990"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":48,"alternative-id":["10.1145\/3664647.3680990","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680990","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}