{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:07:15Z","timestamp":1784268435224,"version":"3.55.0"},"reference-count":121,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01091","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11731-11743","source":"Crossref","is-referenced-by-count":1,"title":["SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis"],"prefix":"10.1109","author":[{"given":"Wenkun","family":"He","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruitao","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Yi","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/16M1060248"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_22"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00156"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2011.940459"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591528"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2018.2849904"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01992"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00931"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687563"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01636"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128777"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818095"},{"key":"ref17","volume-title":"Visual vibration analysis","author":"Davis","year":"2016"},{"key":"ref18","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01393.x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01244"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3573414"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340947"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14739"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2166668"},{"key":"ref29","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref30","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2009.2014357"},{"key":"ref34","volume-title":"Controllable hand grasp generation for hoi and efficient evaluation methods","author":"Rongliang Wu","year":"2025"},{"issue":"2","key":"ref35","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109245"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"ref38","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS47582.2021.9555788"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_4"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3618333"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02279"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342334"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01884"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02054"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2168690"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"issue":"2","key":"ref51","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561802"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3030849"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.108736"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.09.005"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00061"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00271"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00443"},{"issue":"2","key":"ref60","author":"Qi","year":"2025","journal-title":"Human grasp generation for rigid and deformable objects with decomposed vq-vae"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref62","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1080\/00207170902948027"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2007.4434153"},{"issue":"2","key":"ref68","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv"},{"issue":"2","key":"ref69","article-title":"Bermano. Human motion diffusion as a generative prior","author":"Shafir","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00082"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.1130119"},{"issue":"2","key":"ref72","article-title":"Learning structured output representation using deep conditional generative models","volume":"28","author":"Sohn","year":"2015","journal-title":"Advances in neural information processing systems"},{"issue":"2","key":"ref73","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"issue":"3","key":"ref74","volume-title":"Multi-scale stochastic modelling of complex natural phenomena","author":"Stam","year":"1995"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.00152"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01291"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01466"},{"issue":"2","key":"ref79","article-title":"Bermano. Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.12.035"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.07.007"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.03.023"},{"issue":"2","key":"ref83","author":"Tian","year":"2025","journal-title":"Towards semantic 3d hand-object interaction generation via functional text guidance"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00360"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.05.029"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2293413"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01203"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91578-9_2"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01548"},{"issue":"2","key":"ref92","article-title":"Thor: Text to human-object interaction diffusion via relation intervention","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"issue":"2","key":"ref93","article-title":"Human-object interaction from human-level instructions","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01011"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00173"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01145"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01091"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02028"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_14"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00050"},{"key":"ref104","article-title":"Core4d: A 4d human-object-human interaction dataset for collaborative object rearrangement","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459830"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00016"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_22"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3588302"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"issue":"2","key":"ref110","article-title":"Motiondiffuse: Text-driven human motion generation with diffusion model","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02579"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"issue":"2","key":"ref113","author":"Zhang","year":"2024","journal-title":"Ood-hoi: Text-driven 3d whole-body human-object interactions generation beyond training domains"},{"issue":"2","key":"ref114","author":"Zhang","year":"2025","journal-title":"Motion-x++: A large-scale multimodal 3d whole-body human motion dataset"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_18"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01354"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00064"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_23"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i34.40127"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_1"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2857008"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444500.pdf?arnumber=11444500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:41Z","timestamp":1777613381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444500\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":121,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01091","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}