{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:24:23Z","timestamp":1782318263296,"version":"3.54.5"},"reference-count":71,"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\/iccv51701.2025.01040","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11176-11186","source":"Crossref","is-referenced-by-count":2,"title":["Human-Object Interaction from Human-level Instructions"],"prefix":"10.1109","author":[{"given":"Zhen","family":"Wu","sequence":"first","affiliation":[{"name":"Stanford University,Stanford,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaman","family":"Li","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei","family":"Xu","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. Karen","family":"Liu","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Open-universe indoor scene generation using 11 m program synthesis and uncurated object databases","volume-title":"arXiv preprint","author":"Aguina-Kang","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02032"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967960"},{"key":"ref4","article-title":"Physically plausible fullbody hand-object interaction synthesis","volume-title":"arXiv preprint","author":"Braun","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687563"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01880"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342169"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01244"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14739"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14739"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00152"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591525"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref17","article-title":"Look before you leap: Unveiling the power of gpt4v in robotic vision-language planning","volume-title":"arXiv preprint","author":"Hu","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01607"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01092"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687595"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00043"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3618333"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00301"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2007.1033"},{"key":"ref28","article-title":"Visual instruction tuning","volume-title":"Advances in neural information processing systems","volume":"36","author":"Liu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201315"},{"key":"ref30","article-title":"Geneoh diffusion: Towards generalizable hand-object interaction denoising via denoising diffusion","volume-title":"arXiv preprint","author":"Liu","year":"2024"},{"key":"ref31","article-title":"Grasping diverse objects with simulated humanoids","volume-title":"arXiv preprint","author":"Luo","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00061"},{"key":"ref33","article-title":"Hello gpt-4o","volume-title":"OpenAI","author":"OpenAI","year":"2024"},{"issue":"5","key":"ref34","article-title":"Gpt-4 technical report","volume-title":"arxiv","volume":"2","author":"OpenAI","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00271"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1073368.1073413"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00443"},{"key":"ref40","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":"ref41","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912442972"},{"key":"ref42","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv preprint","author":"Schulman","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01291"},{"key":"ref45","article-title":"Grip: Generating interaction poses using latent consistency and spatial cues","volume-title":"arXiv preprint","author":"Taheri","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02029"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3477090"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01981"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160982"},{"key":"ref51","article-title":"F \u201c urelise: Capturing and physically synthesizing hand motions of piano performance","volume-title":"arXiv preprint","author":"Wang","year":"2024"},{"key":"ref52","article-title":"Physhoi: Physics-based imitation of dynamic human-object interaction","volume-title":"arXiv preprint","author":"Wang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1088"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00049"},{"key":"ref55","article-title":"Thor: Text to human-object interaction diffusion via relation intervention","volume-title":"arXiv preprint","author":"Wu","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_15"},{"key":"ref57","article-title":"Unified human-scene interaction via prompted chain-of-contacts","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xiao","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530735"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3480148"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687692"},{"key":"ref61","article-title":"Interdreamer: Zero-shot text to 3d dynamic human-object interaction","volume-title":"arXiv preprint","author":"Xu","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3658137"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185537"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_14"},{"key":"ref66","article-title":"Distilling functional rearrangement priors from large models","volume-title":"arXiv preprint","author":"Zeng","year":"2023"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459830"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01354"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"}],"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\/11444791.pdf?arnumber=11444791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:12Z","timestamp":1777613412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01040","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}