{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:57Z","timestamp":1779948117447,"version":"3.53.1"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"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":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00077","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"750-759","source":"Crossref","is-referenced-by-count":0,"title":["InterPose: Learning to Generate Human-Object Interactions from Large-Scale Web Videos"],"prefix":"10.1109","author":[{"given":"Yangsong","family":"Zhang","sequence":"first","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdul Ahad","family":"Butt","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G\u00fcl","family":"Varol","sequence":"additional","affiliation":[{"name":"LIGM, École des Ponts, IP Paris, Univ Gustave Eiffel, CNRS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"InterPose project webpage"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00916"},{"key":"ref4","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025","journal-title":"arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00109"},{"key":"ref7","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","year":"2019","journal-title":"arXiv"},{"key":"ref8","article-title":"Brandon Castellano","year":"2021","journal-title":"Pyscenedetect"},{"key":"ref9","article-title":"Generative human motion stylization in latent space","author":"Guo","year":"2024","journal-title":"ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"ref12","article-title":"CooHOI: Learning cooperative human-object interaction with manipulated object dynamics","author":"Gao","year":"2024","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14739"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3516429"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687595"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00176"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"ref23","article-title":"ZeroHSI: Zero-shot 4D human-scene interaction by video generation","author":"Li","year":"2024","journal-title":"arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"ref25","article-title":"Controllable human-object interaction synthesis","author":"Li","year":"2023","journal-title":"arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3618333"},{"key":"ref27","article-title":"Motion-X: A large-scale 3D expressive whole-body human motion dataset","author":"Lin","year":"2023","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02235"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref30","author":"Lou","year":"2025","journal-title":"Zero-shot human-object interaction synthesis with multimodal priors"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01013"},{"key":"ref32","article-title":"MediaPipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019","journal-title":"arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0070"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_17"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref36","article-title":"GHOST: Grounded human motion generation with open vocabulary scene-and-text contexts","author":"Milacski","year":"2024","journal-title":"arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00506"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref40","article-title":"HOI- Diff: Text-driven synthesis of 3D human-object interactions using diffusion models","author":"Peng","year":"2023","journal-title":"arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00197"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00202"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01291"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3687951"},{"key":"ref49","article-title":"Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref51","article-title":"HUMANISE: Language-conditioned human motion generation in 3D scenes","author":"Wang","year":"2022","journal-title":"NeurIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_15"},{"key":"ref53","article-title":"Human-object interaction from human-level instructions","author":"Wu","year":"2024","journal-title":"arXiv"},{"key":"ref54","article-title":"OmniControl: Control any joint at any time for human motion generation","author":"Xie","year":"2023","journal-title":"arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"ref56","article-title":"InterDreamer: Zero-shot text to 3D dynamic human-object interaction","author":"Xu","year":"2024","journal-title":"arXiv"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00661"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01145"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3330016"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_20"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00338"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01354"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01016"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533358.pdf?arnumber=11533358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:03:25Z","timestamp":1779944605000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533358\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00077","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}