{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:44:51Z","timestamp":1778082291360,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":63,"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:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Scientific Research Program of Beijing Municipal Education Commission","award":["KZ201911417048"],"award-info":[{"award-number":["KZ201911417048"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62320106007,62032022,62236006"],"award-info":[{"award-number":["62320106007,62032022,62236006"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681013","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"4024-4033","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Realistic Full-Body Motion Generation from Sparse Tracking with State Space Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3714-1650","authenticated-orcid":false,"given":"Kun","family":"Dong","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9460-802X","authenticated-orcid":false,"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1732-8627","authenticated-orcid":false,"given":"Zehai","family":"Niu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3624-5926","authenticated-orcid":false,"given":"Xing","family":"Lan","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0176-3088","authenticated-orcid":false,"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences & Peng Cheng Laboratory, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5877-2126","authenticated-orcid":false,"given":"Qingyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9720-3220","authenticated-orcid":false,"given":"Xiaoyu","family":"Qin","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2004. Carnegie Mellon University MoCap Dataset. http:\/\/mocap.cs.cmu.edu\/."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3463499"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01290"},{"key":"e_1_3_2_2_4_1","volume-title":"International Conference on Machine Learning. PMLR, 1692--1717","author":"Bao Fan","year":"2023","unstructured":"Fan Bao, Shen Nie, Kaiwen Xue, Chongxuan Li, Shi Pu, Yaole Wang, Gang Yue, Yue Cao, Hang Su, and Jun Zhu. 2023. One transformer fits all distributions in multi-modal diffusion at scale. In International Conference on Machine Learning. PMLR, 1692--1717."},{"key":"e_1_3_2_2_5_1","volume-title":"Ilvr: Conditioning method for denoising diffusion probabilistic models. arXiv preprint arXiv:2108.02938","author":"Choi Jooyoung","year":"2021","unstructured":"Jooyoung Choi, Sungwon Kim, Yonghyun Jeong, Youngjune Gwon, and Sungroh Yoon. 2021. Ilvr: Conditioning method for denoising diffusion probabilistic models. arXiv preprint arXiv:2108.02938 (2021)."},{"key":"e_1_3_2_2_6_1","volume-title":"Twins: Revisiting the design of spatial attention in vision transformers. Advances in neural information processing systems 34","author":"Chu Xiangxiang","year":"2021","unstructured":"Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, and Chunhua Shen. 2021. Twins: Revisiting the design of spatial attention in vision transformers. Advances in neural information processing systems 34 (2021), 9355--9366."},{"key":"e_1_3_2_2_7_1","volume-title":"Text-to-Image Diffusion Models are Zero Shot Classifiers. Advances in Neural Information Processing Systems 36","author":"Clark Kevin","year":"2024","unstructured":"Kevin Clark and Priyank Jaini. 2024. Text-to-Image Diffusion Models are Zero Shot Classifiers. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"e_1_3_2_2_9_1","volume-title":"Dual Attention Poser: Dual Path Body Tracking Based on Attention. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2795--2804","author":"Di Xinhan","year":"2023","unstructured":"Xinhan Di, Xiaokun Dai, Xinkang Zhang, and Xinrong Chen. 2023. Dual Attention Poser: Dual Path Body Tracking Based on Attention. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2795--2804."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01148"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00054"},{"key":"e_1_3_2_2_13_1","volume-title":"Reinforcement learning for fine-tuning text-to-image diffusion models. Advances in Neural Information Processing Systems 36","author":"Fan Ying","year":"2024","unstructured":"Ying Fan, Olivia Watkins, Yuqing Du, Hao Liu, Moonkyung Ryu, Craig Boutilier, Pieter Abbeel, Mohammad Ghavamzadeh, Kangwook Lee, and Kimin Lee. 2024. Reinforcement learning for fine-tuning text-to-image diffusion models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_2_14_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)."},{"key":"e_1_3_2_2_15_1","volume-title":"Hippo: Recurrent memory with optimal polynomial projections. Advances in neural information processing systems 33","author":"Gu Albert","year":"2020","unstructured":"Albert Gu, Tri Dao, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2020. Hippo: Recurrent memory with optimal polynomial projections. Advances in neural information processing systems 33 (2020), 1474--1487."},{"key":"e_1_3_2_2_16_1","first-page":"35971","article-title":"On the parameterization and initialization of diagonal state space models","volume":"35","author":"Gu Albert","year":"2022","unstructured":"Albert Gu, Karan Goel, Ankit Gupta, and Christopher R\u00e9. 2022. On the parameterization and initialization of diagonal state space models. Advances in Neural Information Processing Systems 35 (2022), 35971--35983.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_17_1","volume-title":"Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396","author":"Gu Albert","year":"2021","unstructured":"Albert Gu, Karan Goel, and Christopher R\u00e9. 2021. Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)."},{"key":"e_1_3_2_2_18_1","volume-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in neural information processing systems 34","author":"Gu Albert","year":"2021","unstructured":"Albert Gu, Isys Johnson, Karan Goel, Khaled Saab, Tri Dao, Atri Rudra, and Christopher R\u00e9. 2021. Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in neural information processing systems 34 (2021), 572--585."},{"key":"e_1_3_2_2_19_1","first-page":"22982","article-title":"Diagonal state spaces are as effective as structured state spaces","volume":"35","author":"Gupta Ankit","year":"2022","unstructured":"Ankit Gupta, Albert Gu, and Jonathan Berant. 2022. Diagonal state spaces are as effective as structured state spaces. Advances in Neural Information Processing Systems 35 (2022), 22982--22994.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_20_1","volume-title":"Liquid structural state-space models. arXiv preprint arXiv:2209.12951","author":"Hasani Ramin","year":"2022","unstructured":"Ramin Hasani, Mathias Lechner, Tsun-Hsuan Wang, Makram Chahine, Alexander Amini, and Daniela Rus. 2022. Liquid structural state-space models. arXiv preprint arXiv:2209.12951 (2022)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"e_1_3_2_2_22_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_2_23_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3272127.3275108","article-title":"Deep inertial poser: Learning to reconstruct human pose from sparse inertial measurements in real time","volume":"37","author":"Huang Yinghao","year":"2018","unstructured":"Yinghao Huang, Manuel Kaufmann, Emre Aksan, Michael J Black, Otmar Hilliges, and Gerard Pons-Moll. 2018. Deep inertial poser: Learning to reconstruct human pose from sparse inertial measurements in real time. ACM Transactions on Graphics (TOG) 37, 6 (2018), 1--15.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_26"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612674"},{"key":"e_1_3_2_2_26_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_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01644"},{"key":"e_1_3_2_2_28_1","volume-title":"Snapfusion: Text-to-image diffusion model on mobile devices within two seconds. Advances in Neural Information Processing Systems 36","author":"Li Yanyu","year":"2024","unstructured":"Yanyu Li, Huan Wang, Qing Jin, Ju Hu, Pavlo Chemerys, Yun Fu, Yanzhi Wang, Sergey Tulyakov, and Jian Ren. 2024. Snapfusion: Text-to-image diffusion model on mobile devices within two seconds. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"e_1_3_2_2_31_1","volume-title":"Humantomato: Text-aligned whole-body motion generation. arXiv preprint arXiv:2310.12978","author":"Lu Shunlin","year":"2023","unstructured":"Shunlin Lu, Ling-Hao Chen, Ailing Zeng, Jing Lin, Ruimao Zhang, Lei Zhang, and Heung-Yeung Shum. 2023. Humantomato: Text-aligned whole-body motion generation. arXiv preprint arXiv:2310.12978 (2023)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1177\/1471082X211065785"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_2_2_35_1","volume-title":"Mocap database hdm05","author":"M\u00fcller Meinard","year":"2007","unstructured":"Meinard M\u00fcller, Tido R\u00f6der, Michael Clausen, Bernhard Eberhardt, Bj\u00f6rn Kr\u00fcger, and Andreas Weber. 2007. Mocap database hdm05. Institut f\u00fcr Informatik II, Universit\u00e4t Bonn 2, 7 (2007)."},{"key":"e_1_3_2_2_36_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_2_37_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_2_38_1","volume-title":"SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series. arXiv preprint arXiv:2403.15360","author":"Patro Badri N","year":"2024","unstructured":"Badri N Patro and Vijay S Agneeswaran. 2024. SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series. arXiv preprint arXiv:2403.15360 (2024)."},{"key":"e_1_3_2_2_39_1","volume-title":"SpectFormer: Frequency and Attention is what you need in a Vision Transformer. arXiv preprint arXiv:2304.06446","author":"Patro Badri N","year":"2023","unstructured":"Badri N Patro, Vinay P Namboodiri, and Vijay Srinivas Agneeswaran. 2023. SpectFormer: Frequency and Attention is what you need in a Vision Transformer. arXiv preprint arXiv:2304.06446 (2023)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"e_1_3_2_2_41_1","volume-title":"Moe-mamba: Efficient selective state space models with mixture of experts. arXiv preprint arXiv:2401.04081","author":"Pi\u00f3ro Maciej","year":"2024","unstructured":"Maciej Pi\u00f3ro, Kamil Ciebiera, Krystian Kr\u00f3l, Jan Ludziejewski, and Sebastian Jaszczur. 2024. Moe-mamba: Efficient selective state space models with mixture of experts. arXiv preprint arXiv:2401.04081 (2024)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625264"},{"key":"e_1_3_2_2_43_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1, 2","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1, 2 (2022), 3."},{"key":"e_1_3_2_2_44_1","volume-title":"Vm-unet: Vision mamba unet for medical image segmentation. arXiv preprint arXiv:2402.02491","author":"Ruan Jiacheng","year":"2024","unstructured":"Jiacheng Ruan and Suncheng Xiang. 2024. Vm-unet: Vision mamba unet for medical image segmentation. arXiv preprint arXiv:2402.02491 (2024)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28270"},{"key":"e_1_3_2_2_46_1","volume-title":"Simplified state space layers for sequence modeling. arXiv preprint arXiv:2208.04933","author":"Smith Jimmy TH","year":"2022","unstructured":"Jimmy TH Smith, Andrew Warrington, and Scott W Linderman. 2022. Simplified state space layers for sequence modeling. arXiv preprint arXiv:2208.04933 (2022)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1167\/2.5.2"},{"key":"e_1_3_2_2_48_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, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_49_1","volume-title":"State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory. Advances in Neural Information Processing Systems 36","author":"Wang Shida","year":"2024","unstructured":"Shida Wang and Beichen Xue. 2024. State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"e_1_3_2_2_51_1","volume-title":"Lobstr: Real-time lowerbody pose prediction from sparse upper-body tracking signals. In Computer Graphics Forum","author":"Yang Dongseok","year":"2021","unstructured":"Dongseok Yang, Doyeon Kim, and Sung-Hee Lee. 2021. Lobstr: Real-time lowerbody pose prediction from sparse upper-body tracking signals. In Computer Graphics Forum, Vol. 40. Wiley Online Library, 265--275."},{"key":"e_1_3_2_2_52_1","volume-title":"Vivim: a video vision mamba for medical video object segmentation. arXiv preprint arXiv:2401.14168","author":"Yang Yijun","year":"2024","unstructured":"Yijun Yang, Zhaohu Xing, and Lei Zhu. 2024. Vivim: a video vision mamba for medical video object segmentation. arXiv preprint arXiv:2401.14168 (2024)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28483"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01282"},{"key":"e_1_3_2_2_56_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Zhang Jianrong","year":"2023","unstructured":"Jianrong Zhang, Yangsong Zhang, Xiaodong Cun, Shaoli Huang, Yong Zhang, Hongwei Zhao, Hongtao Lu, and Xi Shen. 2023. T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_57_1","volume-title":"Vmunet-v2 rethinking vision mamba unet for medical image segmentation. arXiv preprint arXiv:2403.09157","author":"Zhang Mingya","year":"2024","unstructured":"Mingya Zhang, Yue Yu, Limei Gu, Tingsheng Lin, and Xianping Tao. 2024. Vmunet-v2 rethinking vision mamba unet for medical image segmentation. arXiv preprint arXiv:2403.09157 (2024)."},{"key":"e_1_3_2_2_58_1","volume-title":"Motion mamba: Efficient and long sequence motion generation with hierarchical and bidirectional selective ssm. arXiv preprint arXiv:2403.07487","author":"Zhang Zeyu","year":"2024","unstructured":"Zeyu Zhang, Akide Liu, Ian Reid, Richard Hartley, Bohan Zhuang, and Hao Tang. 2024. Motion mamba: Efficient and long sequence motion generation with hierarchical and bidirectional selective ssm. arXiv preprint arXiv:2403.07487 (2024)."},{"key":"e_1_3_2_2_59_1","volume-title":"Uni-controlnet: All-in-one control to text-toimage diffusion models. Advances in Neural Information Processing Systems 36","author":"Zhao Shihao","year":"2024","unstructured":"Shihao Zhao, Dongdong Chen, Yen-Chun Chen, Jianmin Bao, Shaozhe Hao, Lu Yuan, and Kwan-Yee K Wong. 2024. Uni-controlnet: All-in-one control to text-toimage diffusion models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01349"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_2_2_62_1","volume-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417","author":"Zhu Lianghui","year":"2024","unstructured":"Lianghui Zhu, Bencheng Liao, Qian Zhang, Xinlong Wang, Wenyu Liu, and Xinggang Wang. 2024. Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417 (2024)."},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"}],"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\/3664647.3681013","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:36Z","timestamp":1750295856000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681013"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":63,"alternative-id":["10.1145\/3664647.3681013","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681013","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"}}]}}