{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:05:45Z","timestamp":1767261945674,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":65,"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":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072383, 61702433, 62372212"],"award-info":[{"award-number":["62072383, 61702433, 62372212"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100000288","name":"Royal Society","doi-asserted-by":"publisher","award":["IEC\\NSFC\\211022"],"award-info":[{"award-number":["IEC\\NSFC\\211022"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100000288","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Public Technology Service Platform Project of Xiamen City","award":["No.3502Z20231043"],"award-info":[{"award-number":["No.3502Z20231043"]}]},{"name":"Guangdong Province Science Foundation","award":["2024A1515011515"],"award-info":[{"award-number":["2024A1515011515"]}]},{"name":"Xiaomi Young Talents Program\/Xiaomi Foundation"},{"name":"the Fundamental Research Funds for the Central Universities"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681654","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"6192-6201","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["SATPose: Improving Monocular 3D Pose Estimation with Spatial-aware Ground Tactility"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6008-1450","authenticated-orcid":false,"given":"Lishuang","family":"Zhan","sequence":"first","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0646-1751","authenticated-orcid":false,"given":"Enting","family":"Ying","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7755-5967","authenticated-orcid":false,"given":"Jiabao","family":"Gan","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1473-297X","authenticated-orcid":false,"given":"Shihui","family":"Guo","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8523-2828","authenticated-orcid":false,"given":"BoYu","family":"Gao","sequence":"additional","affiliation":[{"name":"Jinan University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1551-9126","authenticated-orcid":false,"given":"Yipeng","family":"Qin","sequence":"additional","affiliation":[{"name":"Cardiff University, Cardiff, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Recovering 3D human pose from monocular images","author":"Agarwal Ankur","year":"2005","unstructured":"Ankur Agarwal and Bill Triggs. 2005. Recovering 3D human pose from monocular images. IEEE transactions on pattern analysis and machine intelligence, Vol. 28, 1 (2005), 44--58."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_2_1","DOI":"10.1109\/CVPR.2009.5206754"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_3_1","DOI":"10.1109\/BHI50953.2021.9508570"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_4_1","DOI":"10.1109\/CVPR.2017.143"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_5_1","DOI":"10.1007\/s11548-018-1895-3"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_6_1","DOI":"10.1145\/3651296"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_7_1","DOI":"10.1109\/CVPR.2018.00742"},{"key":"e_1_3_2_2_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."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_9_1","DOI":"10.1109\/CVPR42600.2020.00625"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_10_1","DOI":"10.1609\/aaai.v37i1.25120"},{"key":"e_1_3_2_2_11_1","volume-title":"International journal of sports physical therapy","author":"Cook Gray","year":"2014","unstructured":"Gray Cook, Lee Burton, Barbara J Hoogenboom, and Michael Voight. 2014. Functional movement screening: The use of fundamental movements as an assessment of function-part 1. International journal of sports physical therapy, Vol. 9, 3 (2014), 396."},{"key":"e_1_3_2_2_12_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Doersch Carl","year":"2019","unstructured":"Carl Doersch and Andrew Zisserman. 2019. Sim2real transfer learning for 3d human pose estimation: motion to the rescue. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020).","key":"e_1_3_2_2_13_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_14_1","DOI":"10.1145\/3569461"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_15_1","DOI":"10.1109\/BIBM.2013.6732499"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_16_1","DOI":"10.1109\/ICPR48806.2021.9412785"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_17_1","DOI":"10.1109\/CVPR46437.2021.00430"},{"key":"e_1_3_2_2_18_1","volume-title":"Crossformer: Cross spatio-temporal transformer for 3d human pose estimation. arXiv preprint arXiv:2203.13387","author":"Hassanin Mohammed","year":"2022","unstructured":"Mohammed Hassanin, Abdelwahed Khamiss, Mohammed Bennamoun, Farid Boussaid, and Ibrahim Radwan. 2022. Crossformer: Cross spatio-temporal transformer for 3d human pose estimation. arXiv preprint arXiv:2203.13387 (2022)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_19_1","DOI":"10.1109\/ICCV.2017.322"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_20_1","DOI":"10.1145\/3474085.3475219"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_21_1","DOI":"10.1109\/ICCV.2011.6126500"},{"key":"e_1_3_2_2_22_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."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_23_1","DOI":"10.3390\/s20195453"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_24_1","DOI":"10.1016\/j.bios.2020.112946"},{"key":"e_1_3_2_2_25_1","volume-title":"International Conference on Machine Learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. PMLR, 12888--12900."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_26_1","DOI":"10.1109\/TMM.2022.3141231"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_27_1","DOI":"10.1109\/CVPR52688.2022.01280"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_28_1","DOI":"10.1109\/CVPR46437.2021.00199"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_29_1","DOI":"10.1109\/CVPR42600.2020.00511"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_30_1","DOI":"10.1109\/ICPICS47731.2019.8942566"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_31_1","DOI":"10.1007\/978-3-031-19833-5_28"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_32_1","DOI":"10.1109\/CVPR46437.2021.01110"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_33_1","DOI":"10.1109\/3DV.2017.00058"},{"key":"e_1_3_2_2_34_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_2_35_1","volume-title":"Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture. In SIGGRAPH Asia 2023 Conference Papers. 1--11","author":"Pan Shaohua","year":"2023","unstructured":"Shaohua Pan, Qi Ma, Xinyu Yi, Weifeng Hu, Xiong Wang, Xingkang Zhou, Jijunnan Li, and Feng Xu. 2023. Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture. In SIGGRAPH Asia 2023 Conference Papers. 1--11."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_36_1","DOI":"10.1145\/3126594.3126652"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_37_1","DOI":"10.3390\/s20185342"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_38_1","DOI":"10.1109\/CVPR.2017.139"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_39_1","DOI":"10.1109\/CVPR.2019.00794"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_40_1","DOI":"10.1145\/3332165.3347895"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_41_1","DOI":"10.1109\/CVPR52688.2022.00307"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_42_1","DOI":"10.1016\/j.cviu.2016.09.002"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_43_1","DOI":"10.1007\/978-3-031-20065-6_27"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_44_1","DOI":"10.1145\/3474085.3475504"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_45_1","DOI":"10.1109\/ISMAR.2019.000-6"},{"key":"e_1_3_2_2_46_1","volume-title":"Ziwei Liu, Lei Yang, et al.","author":"Sun Qingping","year":"2024","unstructured":"Qingping Sun, Yanjun Wang, Ailing Zeng, Wanqi Yin, Chen Wei, Wenjia Wang, Haiyi Mei, Chi Sing Leung, Ziwei Liu, Lei Yang, et al. 2024. AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation. arXiv preprint arXiv:2403.17934 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_47_1","DOI":"10.1145\/2632048.2636088"},{"key":"e_1_3_2_2_48_1","volume-title":"MLP-JCG: Multi-Layer Perceptron with Joint-Coordinate Gating for Efficient 3D Human Pose Estimation","author":"Tang Zhenhua","year":"2023","unstructured":"Zhenhua Tang, Jia Li, Yanbin Hao, and Richang Hong. 2023. MLP-JCG: Multi-Layer Perceptron with Joint-Coordinate Gating for Efficient 3D Human Pose Estimation. IEEE Transactions on Multimedia (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_49_1","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"e_1_3_2_2_50_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)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_51_1","DOI":"10.3390\/s21020426"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_52_1","DOI":"10.1109\/JSEN.2022.3225290"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_53_1","DOI":"10.1016\/j.cviu.2021.103225"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_54_1","DOI":"10.1007\/978-3-030-58601-0_45"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_55_1","DOI":"10.1609\/aaai.v32i1.12328"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_56_1","DOI":"10.1109\/ICCV51070.2023.00810"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_57_1","DOI":"10.1109\/ICRA48891.2023.10161049"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_58_1","DOI":"10.1145\/3631454"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_59_1","DOI":"10.1109\/CVPR52688.2022.01288"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_60_1","DOI":"10.1109\/CVPR.2019.00354"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_61_1","DOI":"10.1109\/CVPR52729.2023.00857"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_62_1","DOI":"10.1145\/3603618"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_63_1","DOI":"10.1109\/ICCV48922.2021.01145"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_64_1","DOI":"10.1007\/978-3-030-01240-3_24"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_65_1","DOI":"10.1016\/j.image.2020.115802"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '24","name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681654","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681654"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":65,"alternative-id":["10.1145\/3664647.3681654","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681654","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"}}]}}