{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:51:07Z","timestamp":1791913867649,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","funder":[{"name":"Hubei Provincial Key Research and Development Program","award":["2024BAB050, 2024BAB039"],"award-info":[{"award-number":["2024BAB050, 2024BAB039"]}]},{"name":"the National Natural Science Foundation of China","award":["62476224"],"award-info":[{"award-number":["62476224"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755438","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"1802-1811","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Leader is Guided: Interactive Motion Generation via Lead-Follow Paradigm and Trajectory Guidance"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5034-6899","authenticated-orcid":false,"given":"Runqi","family":"Wang","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China and EVOL Lab, The Institute of AI (TeleAI), China Telecom, China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2963-6244","authenticated-orcid":false,"given":"Caoyuan","family":"Ma","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China and EVOL Lab, The Institute of AI (TeleAI), China Telecom, China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3508-756X","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"EVOL Lab, The Institute of AI (TeleAI), China Telecom, China, Beijing, China and Northwestern Polytechnical University, Xi'an Shanxi, P.R. China, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7423-8846","authenticated-orcid":false,"given":"Hanrui","family":"Xu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8717-5395","authenticated-orcid":false,"given":"Dongfang","family":"Sun","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3152-4111","authenticated-orcid":false,"given":"Haoyang","family":"Chen","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3545-227X","authenticated-orcid":false,"given":"Lin","family":"Xiong","sequence":"additional","affiliation":[{"name":"ShensiliCon, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3846-9157","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China and The Institute of AI (TeleAI), China Telecom, China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0019-4197","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"The Institute of AI (TeleAI), China Telecom, China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00062"},{"key":"e_1_3_2_1_2_1","volume-title":"Subjective Camera: Bridging Human Cognition and Visual Reconstruction through Sequence-Aware Sketch-Guided Diffusion. arXiv preprint arXiv:2506.23711","author":"Chen Haoyang","year":"2025","unstructured":"Haoyang Chen, Dongfang Sun, Caoyuan Ma, Shiqin Wang, Kewei Zhang, Zheng Wang, and Zhixiang Wang. 2025. Subjective Camera: Bridging Human Cognition and Visual Reconstruction through Sequence-Aware Sketch-Guided Diffusion. arXiv preprint arXiv:2506.23711 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes. arXiv preprint arXiv:2410.10790","author":"Chen Jianqi","year":"2024","unstructured":"Jianqi Chen, Panwen Hu, Xiaojun Chang, Zhenwei Shi, Michael Kampffmeyer, and Xiaodan Liang. 2024a. Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes. arXiv preprint arXiv:2410.10790 (2024)."},{"key":"e_1_3_2_1_4_1","volume-title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos. arxiv:2405.20340","author":"Chen Ling-Hao","year":"2024","unstructured":"Ling-Hao Chen, Shunlin Lu, Ailing Zeng, Hao Zhang, Benyou Wang, Ruimao Zhang, and Lei Zhang. 2024b. MotionLLM: Understanding Human Behaviors from Human Motions and Videos. arxiv:2405.20340 (2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681034"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681013"},{"key":"e_1_3_2_1_10_1","unstructured":"Bradley Efron. 2011. Tweedie's formula and selection bias. J. Amer. Statist. Assoc. (2011)."},{"key":"e_1_3_2_1_11_1","volume-title":"European Conference on Computer Vision.","author":"Fan Ke","year":"2024","unstructured":"Ke Fan, Junshu Tang, Weijian Cao, Ran Yi, Moran Li, Jingyu Gong, Jiangning Zhang, Yabiao Wang, Chengjie Wang, and Lizhuang Ma. 2024. Freemotion: A unified framework for number-free text-to-motion synthesis. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_12_1","volume-title":"European Conference on Computer Vision.","author":"Ghosh Anindita","year":"2024","unstructured":"Anindita Ghosh, Rishabh Dabral, Vladislav Golyanik, Christian Theobalt, and Philipp Slusallek. 2024. ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730108"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681657"},{"key":"e_1_3_2_1_17_1","volume-title":"Geometry-Aware Retargeting for Two-Skinned Characters Interaction. ACM Transactions on Graphics (TOG)","author":"Jang Inseo","year":"2024","unstructured":"Inseo Jang, Soojin Choi, Seokhyeon Hong, Chaelin Kim, and Junyong Noh. 2024. Geometry-Aware Retargeting for Two-Skinned Characters Interaction. ACM Transactions on Graphics (TOG) (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00057"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00196"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887687"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02719"},{"key":"e_1_3_2_1_23_1","volume-title":"Intergen: Diffusion-based multi-human motion generation under complex interactions. International Journal of Computer Vision","author":"Liang Han","year":"2024","unstructured":"Han Liang, Wenqian Zhang, Wenxuan Li, Jingyi Yu, and Lan Xu. 2024. Intergen: Diffusion-based multi-human motion generation under complex interactions. International Journal of Computer Vision (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02224"},{"key":"e_1_3_2_1_25_1","volume":"202","author":"Loper Matthew","unstructured":"Matthew Loper, Naureen Mahmood, Javier Romero, Gerard Pons-Moll, and Michael J Black. 2023. SMPL: A skinned multi-person linear model. In Seminal Graphics Papers: Pushing the Boundaries, Volume 2.","journal-title":"Michael J Black."},{"key":"e_1_3_2_1_26_1","volume-title":"HumanTOMATO: Text-aligned Whole-body Motion Generation. 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:2310.12978 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01949"},{"key":"e_1_3_2_1_29_1","volume-title":"Does adding a modality really make a positive impacts in incomplete multi-modal brain tumor segmentation? IEEE Transactions on Medical Imaging","author":"Qiu Yansheng","year":"2025","unstructured":"Yansheng Qiu, Kui Jiang, Hongdou Yao, Zheng Wang, and Shin'ichi Satoh. 2025a. Does adding a modality really make a positive impacts in incomplete multi-modal brain tumor segmentation? IEEE Transactions on Medical Imaging (2025)."},{"key":"e_1_3_2_1_30_1","volume-title":"Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans. arXiv preprint arXiv:2505.11141","author":"Qiu Yansheng","year":"2025","unstructured":"Yansheng Qiu, Li Xiao, Zhaopan Xu, Pengfei Zhou, Zheng Wang, and Kaipeng Zhang. 2025b. Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans. arXiv preprint arXiv:2505.11141 (2025)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611712"},{"key":"e_1_3_2_1_32_1","volume-title":"Human motion diffusion as a generative prior. arXiv preprint arXiv:2303.01418","author":"Shafir Yonatan","year":"2023","unstructured":"Yonatan Shafir, Guy Tevet, Roy Kapon, and Amit H Bermano. 2023. Human motion diffusion as a generative prior. arXiv preprint arXiv:2303.01418 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Towards open domain text-driven synthesis of multi-person motions. arXiv preprint arXiv:2405.18483","author":"Shan Mengyi","year":"2024","unstructured":"Mengyi Shan, Lu Dong, Yutao Han, Yuan Yao, Tao Liu, Ifeoma Nwogu, Guo-Jun Qi, and Mitch Hill. 2024. Towards open domain text-driven synthesis of multi-person motions. arXiv preprint arXiv:2405.18483 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"Duolando: Follower gpt with off-policy reinforcement learning for dance accompaniment. arXiv preprint arXiv:2403.18811","author":"Siyao Li","year":"2024","unstructured":"Li Siyao, Tianpei Gu, Zhitao Yang, Zhengyu Lin, Ziwei Liu, Henghui Ding, Lei Yang, and Chen Change Loy. 2024. Duolando: Follower gpt with off-policy reinforcement learning for dance accompaniment. arXiv preprint arXiv:2403.18811 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00084"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01466"},{"key":"e_1_3_2_1_38_1","volume-title":"Human Motion Diffusion Model. In The Eleventh International Conference on Learning Representations.","author":"Tevet Guy","year":"2023","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yoni Shafir, Daniel Cohen-or, and Amit Haim Bermano. 2023. Human Motion Diffusion Model. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence.","author":"Tian Likai","year":"2024","unstructured":"Likai Tian, Zhengwei Yang, Zechao Hu, Hao Li, Yifang Yin, and Zheng Wang. 2024. Expressiveness is effectiveness: self-supervised fashion-aware clip for video-to-shop retrieval. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00376"},{"key":"e_1_3_2_1_41_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems (2017)."},{"key":"e_1_3_2_1_42_1","volume-title":"Tlcontrol: Trajectory and language control for human motion synthesis. arXiv preprint arXiv:2311.17135","author":"Wan Weilin","year":"2023","unstructured":"Weilin Wan, Zhiyang Dou, Taku Komura, Wenping Wang, Dinesh Jayaraman, and Lingjie Liu. 2023. Tlcontrol: Trajectory and language control for human motion synthesis. arXiv preprint arXiv:2311.17135 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"You ACT: The New Task of Arbitrary Text to Motion Generation. arXiv preprint arXiv:2404.14745","author":"Wang Runqi","year":"2024","unstructured":"Runqi Wang, Caoyuan Ma, Guopeng Li, Hanrui Xu, Yuke Li, and Zheng Wang. 2024. You Think, You ACT: The New Task of Arbitrary Text to Motion Generation. arXiv preprint arXiv:2404.14745 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"InterControl: Generate Human Motion Interactions by Controlling Every Joint. arXiv preprint arXiv:2311.15864","author":"Wang Zhenzhi","year":"2023","unstructured":"Zhenzhi Wang, Jingbo Wang, Dahua Lin, and Bo Dai. 2023. InterControl: Generate Human Motion Interactions by Controlling Every Joint. arXiv preprint arXiv:2311.15864 (2023)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611797"},{"key":"e_1_3_2_1_46_1","volume-title":"Omnicontrol: Control any joint at any time for human motion generation. arXiv preprint arXiv:2310.08580","author":"Xie Yiming","year":"2023","unstructured":"Yiming Xie, Varun Jampani, Lei Zhong, Deqing Sun, and Huaizu Jiang. 2023a. Omnicontrol: Control any joint at any time for human motion generation. arXiv preprint arXiv:2310.08580 (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681487"},{"key":"e_1_3_2_1_49_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. 2023b. 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_1_50_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023a. Adding Conditional Control to Text-to-Image Diffusion Models.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_51_1","volume-title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model. arXiv preprint arXiv:2208.15001","author":"Zhang Mingyuan","year":"2022","unstructured":"Mingyuan Zhang, Zhongang Cai, Liang Pan, Fangzhou Hong, Xinying Guo, Lei Yang, and Ziwei Liu. 2022. MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model. arXiv preprint arXiv:2208.15001 (2022)."},{"key":"e_1_3_2_1_52_1","volume-title":"Behave Your Motion: Habit-preserved Cross-category Animal Motion Transfer. arXiv preprint arXiv:2507.07394","author":"Zhang Zhimin","year":"2025","unstructured":"Zhimin Zhang, Bi'an Du, Caoyuan Ma, Zheng Wang, and Wei Hu. 2025. Behave Your Motion: Habit-preserved Cross-category Animal Motion Transfer. arXiv preprint arXiv:2507.07394 (2025)."},{"key":"e_1_3_2_1_53_1","volume-title":"A unified framework for multimodal, multi-part human motion synthesis. arXiv preprint arXiv:2311.16471","author":"Zhou Zixiang","year":"2023","unstructured":"Zixiang Zhou, Yu Wan, and Baoyuan Wang. 2023. A unified framework for multimodal, multi-part human motion synthesis. arXiv preprint arXiv:2311.16471 (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:14:08Z","timestamp":1765340048000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755438"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":53,"alternative-id":["10.1145\/3746027.3755438","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755438","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}