{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:49:33Z","timestamp":1772909373073,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":72,"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 Key R\\&D Program of Zhejiang Province","award":["No. 2023C01217"],"award-info":[{"award-number":["No. 2023C01217"]}]},{"name":"Graduate Innovation Fund of Jilin University","award":["No. 2024CX089"],"award-info":[{"award-number":["No. 2024CX089"]}]},{"name":"the National Natural Science Foundation of China","award":["No. 62276112, No. 62372402"],"award-info":[{"award-number":["No. 62276112, No. 62372402"]}]},{"name":"Key Projects of Science and Technology Development Plan of Jilin Province","award":["No. 20230201088GX"],"award-info":[{"award-number":["No. 20230201088GX"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681179","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"8962-8971","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Joint-Motion Mutual Learning for Pose Estimation in Video"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2828-0158","authenticated-orcid":false,"given":"Sifan","family":"Wu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Jilin University & Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9410-4120","authenticated-orcid":false,"given":"Haipeng","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University & Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6525-6133","authenticated-orcid":false,"given":"Yifang","family":"Yin","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), A*STAR, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3297-6991","authenticated-orcid":false,"given":"Sihao","family":"Hu","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, Georgia, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4912-6646","authenticated-orcid":false,"given":"Runyang","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5630-7271","authenticated-orcid":false,"given":"Yingying","family":"Jiao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University & Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4995-7085","authenticated-orcid":false,"given":"Ziqi","family":"Yang","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University & Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7981-9873","authenticated-orcid":false,"given":"Zhenguang","family":"Liu","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University & Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, 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.2018.00542"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00706"},{"key":"e_1_3_2_1_3_1","volume-title":"Pose-Guided Tracking-by-Detection: Robust Multi-Person Pose Tracking","author":"Bao Qian","year":"2020","unstructured":"Qian Bao, Wu Liu, Yuhao Cheng, Boyan Zhou, and Tao Mei. 2020. Pose-Guided Tracking-by-Detection: Robust Multi-Person Pose Tracking. IEEE Transactions on Multimedia (2020)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00103"},{"key":"e_1_3_2_1_5_1","unstructured":"Gedas Bertasius Christoph Feichtenhofer Du Tran Jianbo Shi and Lorenzo Torresani. 2019. Learning temporal pose estimation from sparsely-labeled videos. In Advances in Neural Information Processing Systems. 3027--3038."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00208"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Meng-Jiun Chiou Zhenguang Liu Yifang Yin An-An Liu and Roger Zimmermann. 2020. Zero-Shot Multi-View Indoor Localization via Graph Location Networks. In ACM Multimedia. 3431--3440. https:\/\/doi.org\/10.1145\/3394171.3413856","DOI":"10.1145\/3394171.3413856"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02029"},{"key":"e_1_3_2_1_11_1","volume-title":"Joint flow: Temporal flow fields for multi person tracking. arXiv preprint arXiv:1805.04596","author":"Doering Andreas","year":"2018","unstructured":"Andreas Doering, Umar Iqbal, and Juergen Gall. 2018. Joint flow: Temporal flow fields for multi person tracking. arXiv preprint arXiv:1805.04596 (2018)."},{"key":"e_1_3_2_1_12_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_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01643"},{"key":"e_1_3_2_1_15_1","volume-title":"Improving Multi-Person Pose Tracking with A Confidence Network","author":"Fu Zehua","year":"2023","unstructured":"Zehua Fu, Wenhang Zuo, Zhenghui Hu, Qingjie Liu, and Yunhong Wang. 2023. Improving Multi-Person Pose Tracking with A Confidence Network. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3269666"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00044"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0--0.","author":"Guo Hengkai","year":"2018","unstructured":"Hengkai Guo, Tang Tang, Guozhong Luo, Riwei Chen, Yongchen Lu, and Linfu Wen. 2018. Multi-domain pose network for multi-person pose estimation and tracking. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0--0."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.33448\/rsd-v10i3.12823"},{"key":"e_1_3_2_1_20_1","volume-title":"Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670","author":"Hjelm R Devon","year":"2018","unstructured":"R Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Phil Bachman, Adam Trischler, and Yoshua Bengio. 2018. Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)."},{"key":"e_1_3_2_1_21_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems 33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851734"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.495"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.10.038"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00568"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00581"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01225"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3124981"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Krystel Libert Elaine Mosconi and Nathalie Cadieux. 2020. Human-machine interaction and human resource management perspective for collaborative robotics implementation and adoption. (2020).","DOI":"10.24251\/HICSS.2020.066"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29314"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00059"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01073"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/171"},{"key":"e_1_3_2_1_37_1","volume-title":"Associative Embedding: End-to-End Learning for Joint Detection and Grouping. Advances in Neural Information Processing Systems 30","author":"Newell Alejandro","year":"2017","unstructured":"Alejandro Newell, Zhiao Huang, and Jia Deng. 2017. Associative Embedding: End-to-End Learning for Joint Detection and Grouping. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.533"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"e_1_3_2_1_40_1","volume-title":"Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation. arXiv preprint arXiv:2306.17074","author":"Qiu Zhongwei","year":"2023","unstructured":"Zhongwei Qiu, Qiansheng Yang, Jian Wang, Xiyu Wang, Chang Xu, Dongmei Fu, Kun Yao, Junyu Han, Errui Ding, and Jingdong Wang. 2023. Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation. arXiv preprint arXiv:2306.17074 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00475"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_3"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_30"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","unstructured":"Chao Shuai Jieming Zhong Shuang Wu Feng Lin Zhibo Wang Zhongjie Ba Zhenguang Liu Lorenzo Cavallaro and Kui Ren. 2023. Locate and Verify: A Two-Stream Network for Improved Deepfake Detection. In ACM Multimedia. 7131--7142. https:\/\/doi.org\/10.1145\/3581783.3612386","DOI":"10.1145\/3581783.3612386"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.590"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21113784"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","unstructured":"Pengxiang Su Zhenguang Liu Shuang Wu Lei Zhu Yifang Yin and Xuanjing Shen. 2021. Motion Prediction via Joint Dependency Modeling in Phase Space. In ACM Multimedia. 713--721. https:\/\/doi.org\/10.1145\/3474085.3475237","DOI":"10.1145\/3474085.3475237"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248079"},{"key":"e_1_3_2_1_50_1","volume-title":"Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision-ECCV 2020: 16th European Conference","author":"Teed Zachary","year":"2020","unstructured":"Zachary Teed and Jia Deng. 2020. Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part II 16. Springer, 402--419."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00157"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"e_1_3_2_1_53_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","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 30 (2017)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.83"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01110"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88690-7_53"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 4724--4732","author":"Ramakrishna Varun","year":"2016","unstructured":"Shih-EnWei, Varun Ramakrishna, Takeo Kanade, and Yaser Sheikh. 2016. Convolutional pose machines. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 4724--4732."},{"key":"e_1_3_2_1_58_1","volume-title":"Do as I Do: Pose Guided Human Motion Copy","author":"Wu Sifan","year":"2024","unstructured":"Sifan Wu, Zhenguang Liu, Beibei Zhang, Roger Zimmermann, Zhongjie Ba, Xiaosong Zhang, and Kui Ren. 2024. Do as I Do: Pose Guided Human Motion Copy. IEEE Transactions on Dependable and Secure Computing (2024)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"e_1_3_2_1_60_1","volume-title":"Pose Flow: Efficient online pose tracking. arXiv preprint arXiv:1802.00977","author":"Xiu Yuliang","year":"2018","unstructured":"Yuliang Xiu, Jiefeng Li, Haoyu Wang, Yinghong Fang, and Cewu Lu. 2018. Pose Flow: Efficient online pose tracking. arXiv preprint arXiv:1802.00977 (2018)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"e_1_3_2_1_62_1","volume-title":"Action Recognition with Multistream Motion Modeling and Mutual Information Maximization. arXiv preprint arXiv:2306.07576","author":"Yang Yuheng","year":"2023","unstructured":"Yuheng Yang, Haipeng Chen, Zhenguang Liu, Yingda Lyu, Beibei Zhang, Shuang Wu, Zhibo Wang, and Kui Ren. 2023. Action Recognition with Multistream Motion Modeling and Mutual Information Maximization. arXiv preprint arXiv:2306.07576 (2023)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00798"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00867"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447410"},{"key":"e_1_3_2_1_67_1","volume-title":"Improving depth gradient continuity in transformers: A comparative study on monocular depth estimation with cnn. arXiv preprint arXiv:2308.08333","author":"Yao Jiawei","year":"2023","unstructured":"Jiawei Yao, Tong Wu, and Xiaofeng Zhang. 2023. Improving depth gradient continuity in transformers: A comparative study on monocular depth estimation with cnn. arXiv preprint arXiv:2308.08333 (2023)."},{"key":"e_1_3_2_1_68_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). 0--0.","author":"Yu Dongdong","year":"2018","unstructured":"Dongdong Yu, Kai Su, Jia Sun, and Changhu Wang. 2018. Multi-person pose estimation for pose tracking with enhanced cascaded pyramid network. In Proceedings of the European Conference on Computer Vision (ECCV). 0--0."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00707"},{"key":"e_1_3_2_1_70_1","volume-title":"Fastpose: Towards real-time pose estimation and tracking via scale-normalized multi-task networks. arXiv preprint arXiv:1908.05593","author":"Zhang Jiabin","year":"2019","unstructured":"Jiabin Zhang, Zheng Zhu, Wei Zou, Peng Li, Yanwei Li, Hu Su, and Guan Huang. 2019. Fastpose: Towards real-time pose estimation and tracking via scale-normalized multi-task networks. arXiv preprint arXiv:1908.05593 (2019)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592272"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"}],"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\/3664647.3681179","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:02Z","timestamp":1750295882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681179"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":72,"alternative-id":["10.1145\/3664647.3681179","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681179","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"}}]}}