{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T00:59:37Z","timestamp":1794617977175,"version":"4.9.1"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372014"],"award-info":[{"award-number":["62372014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["4252040"],"award-info":[{"award-number":["4252040"]}]},{"name":"State Key Laboratory of General Artificial Intelligence, BIGAI"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754910","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"9491-9499","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["InteractMove: Text-Controlled Human-Object Interaction Generation in 3D Scenes with Movable Objects"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5459-3458","authenticated-orcid":false,"given":"Xinhao","family":"Cai","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1612-975X","authenticated-orcid":false,"given":"Minghang","family":"Zheng","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3873-1653","authenticated-orcid":false,"given":"Xin","family":"Jin","sequence":"additional","affiliation":[{"name":"Beijing Electronic Science and Technology Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4259-3882","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China and State Key Laboratory of General Artificial Intelligence, Peking University, 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":"10.1007\/978-3-030-58452-8_25"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02032"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_23"},{"key":"e_1_3_2_1_5_1","volume-title":"Jae Shin Yoon, and Seungryul Baek","author":"Cha Junuk","year":"2024","unstructured":"Junuk Cha, Jihyeon Kim, Jae Shin Yoon, and Seungryul Baek. 2024. Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction. arXiv:2404.00562 [cs.CV] https:\/\/arxiv.org\/abs\/2404.00562"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01880"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"e_1_3_2_1_10_1","volume-title":"Denoising Diffusion Probabilistic Models. arXiv preprint arxiv:2006.11239","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. arXiv preprint arxiv:2006.11239 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00859"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Ting Lei Fabian Caba Qingchao Chen Hailin Ji Yuxin Peng and Yang Liu. 2023. Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory.","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01576"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618333"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01265"},{"key":"e_1_3_2_1_18_1","unstructured":"Xiaogang Peng Yiming Xie Zizhao Wu Varun Jampani Deqing Sun and Huaizu Jiang. 2023. HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models. arXiv:2312.06553 [cs.CV]"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925867"},{"key":"e_1_3_2_1_20_1","volume-title":"Learning structured output representation using deep conditional generative models. Advances in neural information processing systems","author":"Sohn Kihyuk","year":"2015","unstructured":"Kihyuk Sohn, Honglak Lee, and Xinchen Yan. 2015. Learning structured output representation using deep conditional generative models. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01291"},{"key":"e_1_3_2_1_22_1","volume-title":"GRAB: A dataset of whole-body human grasping of objects. In Computer Vision-ECCV 2020: 16th European Conference","author":"Taheri Omid","year":"2020","unstructured":"Omid Taheri, Nima Ghorbani, Michael J Black, and Dimitrios Tzionas. 2020. GRAB: A dataset of whole-body human grasping of objects. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part IV 16. Springer, 581-600."},{"key":"e_1_3_2_1_23_1","volume-title":"Human Motion Diffusion Model. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SJ1kSyO2jwu","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. https:\/\/openreview.net\/forum?id=SJ1kSyO2jwu"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00049"},{"key":"e_1_3_2_1_25_1","first-page":"14959","article-title":"Humanise: Language-conditioned human motion generation in 3d scenes","volume":"35","author":"Wang Zan","year":"2022","unstructured":"Zan Wang, Yixin Chen, Tengyu Liu, Yixin Zhu, Wei Liang, and Siyuan Huang. 2022. Humanise: Language-conditioned human motion generation in 3d scenes. Advances in Neural Information Processing Systems, Vol. 35 (2022), 14959-14971.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01371"},{"key":"e_1_3_2_1_27_1","volume-title":"Semantic-Aware Human Object Interaction Image Generation. In Forty-first International Conference on Machine Learning.","author":"Xu Zhu","year":"2024","unstructured":"Zhu Xu, Qingchao Chen, Yuxin Peng, and Yang Liu. 2024. Semantic-Aware Human Object Interaction Image Generation. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-24","author":"Yang Dejie","year":"2024","unstructured":"Dejie Yang, Zhu Xu, Wentao Mo, Qingchao Chen, Siyuan Huang, and Yang Liu. 2024. 3D Vision and Language Pretraining with Large-Scale Synthetic Data. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-24. International Joint Conferences on Artificial Intelligence Organization."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on 3D Vision (3DV)","volume":"2","author":"Zhang Siwei","year":"2020","unstructured":"Siwei Zhang, Yan Zhang, Qianli Ma, Michael J Black, and Siyu Tang. 2020b. Generating person-scene interactions in 3d scenes. In International Conference on 3D Vision (3DV), Vol. 2."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00623"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"}],"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\/3746027.3754910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:18:15Z","timestamp":1765340295000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754910"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":32,"alternative-id":["10.1145\/3746027.3754910","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754910","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"}}]}}