{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:55:41Z","timestamp":1773154541795,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62431015"],"award-info":[{"award-number":["62431015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["No.24511106200"],"award-info":[{"award-number":["No.24511106200"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012656","name":"Shanghai Key Laboratory of Digital Media Processing and Transmission","doi-asserted-by":"publisher","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}],"id":[{"id":"10.13039\/501100012656","id-type":"DOI","asserted-by":"publisher"}]},{"name":"111 Project","award":["BP0719010"],"award-info":[{"award-number":["BP0719010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758217","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"12769-12775","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["PA-HOI: A Physics-Aware Human and Object Interaction Dataset"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0885-8311","authenticated-orcid":false,"given":"Ruiyan","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6333-8867","authenticated-orcid":false,"given":"Lin","family":"Zuo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2793-1374","authenticated-orcid":false,"given":"Zonghao","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5360-9997","authenticated-orcid":false,"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Visionstar Information Technology (Shanghai) Co., Ltd, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5364-7427","authenticated-orcid":false,"given":"Zhengxue","family":"Cheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8261-5337","authenticated-orcid":false,"given":"Rong","family":"Xie","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7260-7141","authenticated-orcid":false,"given":"Jun","family":"Ling","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7124-5182","authenticated-orcid":false,"given":"Li","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"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\/CVPR52688.2022.01547"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00156"},{"key":"e_1_3_2_1_3_1","volume-title":"Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss. arXiv preprint arXiv:2501.18232","author":"Chen Wenshuo","year":"2025","unstructured":"Wenshuo Chen, Haozhe Jia, Songning Lai, Keming Wu, Hongru Xiao, Lijie Hu, and Yutao Yue. 2025. Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss. arXiv preprint arXiv:2501.18232 (2025)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"e_1_3_2_1_5_1","volume-title":"SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance. arXiv preprint arXiv:2503.01291","author":"Cong Peishan","year":"2025","unstructured":"Peishan Cong, Ziyi Wang, Yuexin Ma, and Xiangyu Yue. 2025. SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance. arXiv preprint arXiv:2503.01291 (2025)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01244"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"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","volume-title":"SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing. arXiv preprint arXiv:2503.13836","author":"Hong Seokhyeon","year":"2025","unstructured":"Seokhyeon Hong, Chaelin Kim, Serin Yoon, Junghyun Nam, Sihun Cha, and Junyong Noh. 2025. SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing. arXiv preprint arXiv:2503.13836 (2025)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_18"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681657"},{"key":"e_1_3_2_1_13_1","first-page":"20067","article-title":"Motiongpt: Human motion as a foreign language","volume":"36","author":"Jiang Biao","year":"2023","unstructured":"Biao Jiang, Xin Chen, Wen Liu, Jingyi Yu, Gang Yu, and Tao Chen. 2023. Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems, Vol. 36 (2023), 20067-20079.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","volume-title":"Computer Vision - ECCV","author":"Kim Hyeonwoo","year":"2024","unstructured":"Hyeonwoo Kim, Sookwan Han, Patrick Kwon, and Hanbyul Joo. 2025. Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models. In Computer Vision - ECCV 2024, Ale\u0161 Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, and G\u00fcl Varol (Eds.). Springer Nature Switzerland, Cham, 400-419."},{"key":"e_1_3_2_1_15_1","volume-title":"Parahome: Parameterizing everyday home activities towards 3d generative modeling of human-object interactions. arXiv preprint arXiv:2401.10232","author":"Kim Jeonghwan","year":"2024","unstructured":"Jeonghwan Kim, Jisoo Kim, Jeonghyeon Na, and Hanbyul Joo. 2024. Parahome: Parameterizing everyday home activities towards 3d generative modeling of human-object interactions. arXiv preprint arXiv:2401.10232 (2024)."},{"key":"e_1_3_2_1_16_1","first-page":"4","article-title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-Body Mesh Recovery","volume":"47","author":"Li Jiefeng","year":"2025","unstructured":"Jiefeng Li, Siyuan Bian, Chao Xu, Zhicun Chen, Lixin Yang, and Cewu Lu. 2025. HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-Body Mesh Recovery. IEEE Trans. Pattern Anal. Mach. Intell., Vol. 47, 4 (Jan. 2025), 2754-2769.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618333"},{"key":"e_1_3_2_1_18_1","first-page":"25268","article-title":"Motion-x: A large-scale 3d expressive whole-body human motion dataset","volume":"36","author":"Lin Jing","year":"2023","unstructured":"Jing Lin, Ailing Zeng, Shunlin Lu, Yuanhao Cai, Ruimao Zhang, Haoqian Wang, and Lei Zhang. 2023. Motion-x: A large-scale 3d expressive whole-body human motion dataset. Advances in Neural Information Processing Systems, Vol. 36 (2023), 25268-25280.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"e_1_3_2_1_20_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_1_21_1","volume-title":"HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects. In European Conference on Computer Vision. Springer, 300-318","author":"Lv Xintao","year":"2024","unstructured":"Xintao Lv, Liang Xu, Yichao Yan, Xin Jin, Congsheng Xu, Shuwen Wu, Yifan Liu, Lincheng Li, Mengxiao Bi, Wenjun Zeng, et al., 2024. HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects. In European Conference on Computer Vision. Springer, 300-318."},{"key":"e_1_3_2_1_22_1","volume-title":"European Conference on Computer Vision. Springer, 19-35","author":"Moon Gyeongsik","year":"2024","unstructured":"Gyeongsik Moon, Takaaki Shiratori, and Shunsuke Saito. 2024. Expressive whole-body 3D gaussian avatar. In European Conference on Computer Vision. Springer, 19-35."},{"key":"e_1_3_2_1_23_1","unstructured":"Noitom. [n.d.]. Noitom PN Hybrid VTS System. https:\/\/noitom.com\/."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_2_1_25_1","volume-title":"The kit motion-language dataset. Big data","author":"Plappert Matthias","year":"2016","unstructured":"Matthias Plappert, Christian Mandery, and Tamim Asfour. 2016. The kit motion-language dataset. Big data, Vol. 4, 4 (2016), 236-252."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925867"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01291"},{"key":"e_1_3_2_1_28_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_29_1","volume-title":"Human motion diffusion model. arXiv preprint arXiv:2209.14916","author":"Tevet Guy","year":"2022","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, and Amit H Bermano. 2022. Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022)."},{"key":"e_1_3_2_1_30_1","unstructured":"Tripo3d. [n.d.]. Generate 3D model Powered by AI in One Clip within Seconds. https:\/\/www.tripo3d.ai\/."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"e_1_3_2_1_33_1","volume-title":"Guiding Human-Object Interactions with Rich Geometry and Relations. arXiv preprint arXiv:2503.20172","author":"Xue Mengqing","year":"2025","unstructured":"Mengqing Xue, Yifei Liu, Ling Guo, Shaoli Huang, and Changxing Ding. 2025. Guiding Human-Object Interactions with Rich Geometry and Relations. arXiv preprint arXiv:2503.20172 (2025)."},{"key":"e_1_3_2_1_34_1","volume-title":"ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation. arXiv preprint arXiv:2503.13130","author":"Zeng Ling-An","year":"2025","unstructured":"Ling-An Zeng, Guohong Huang, Yi-Lin Wei, Shengbo Gu, Yu-Ming Tang, Jingke Meng, and Wei-Shi Zheng. 2025. ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation. arXiv preprint arXiv:2503.13130 (2025)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00056"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"e_1_3_2_1_38_1","volume-title":"Sebastian Starke, Ilya Petrov, Vladimir Guzov, Helisa Dhamo, Eduardo P\u00e9rez-Pellitero, and Gerard Pons-Moll.","author":"Zhang Xiaohan","year":"2024","unstructured":"Xiaohan Zhang, Bharat Lal Bhatnagar, Sebastian Starke, Ilya Petrov, Vladimir Guzov, Helisa Dhamo, Eduardo P\u00e9rez-Pellitero, and Gerard Pons-Moll. 2024a. Force: Dataset and method for intuitive physics guided human-object interaction. CoRR (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Motion-X: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset. arXiv preprint arXiv:2501.05098","author":"Zhang Yuhong","year":"2025","unstructured":"Yuhong Zhang, Jing Lin, Ailing Zeng, Guanlin Wu, Shunlin Lu, Yurong Fu, Yuanhao Cai, Ruimao Zhang, Haoqian Wang, and Lei Zhang. 2025. Motion-X: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset. arXiv preprint arXiv:2501.05098 (2025)."}],"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\/3746027.3758217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:02:53Z","timestamp":1765342973000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758217"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":39,"alternative-id":["10.1145\/3746027.3758217","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758217","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"}}]}}