{"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":1779948117390,"version":"3.53.1"},"reference-count":103,"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\/3dv69130.2026.00080","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"783-794","source":"Crossref","is-referenced-by-count":0,"title":["ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation"],"prefix":"10.1109","author":[{"given":"Hongjie","family":"Li","sequence":"first","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong-Xing","family":"Yu","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaman","family":"Li","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02032"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00220"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref6","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00109"},{"key":"ref9","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0506"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01595"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01992"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01244"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00846"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14739"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00512"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref22","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00430"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591525"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0307"},{"key":"ref28","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01930"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01607"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687595"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01623"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_24"},{"key":"ref37","article-title":"GMD: Controllable human motion synthesis via guided diffusion models","volume-title":"ICCV","author":"Karunratanakul","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_23"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00055"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00096"},{"key":"ref44","article-title":"Deliffas: Deformable light fields for fast avatar synthesis","author":"Kwon","year":"2024","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00886"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01879"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01644"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3618333"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_4"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01934"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00301"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01864"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480528"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680674"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392474"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00271"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref67","article-title":"Single motion diffusion","author":"Raab","year":"2024","journal-title":"ICLR"},{"key":"ref68","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref69","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Human motion diffusion as a generative prior","author":"Shafir","year":"2024","journal-title":"ICLR"},{"key":"ref71","article-title":"Controllable motion diffusion model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00202"},{"key":"ref73","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01291"},{"key":"ref76","volume-title":"Kling image-to-video model","year":"2024"},{"key":"ref77","year":"2025","journal-title":"Wan: Open and advanced large-scale video generative models"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref79","article-title":"Human motion diffusion model","author":"Tevet","year":"2023","journal-title":"ICLR"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151614"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01981"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_1"},{"key":"ref85","article-title":"HUMANISE: Language-conditioned human motion generation in 3d scenes","author":"Wang","year":"2022","journal-title":"NeurIPS"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref87","article-title":"SAGA: Stochastic wholebody grasping with contact","author":"Wu","year":"2022","journal-title":"ECCV"},{"key":"ref88","article-title":"Unified human-scene interaction via prompted chain-of-contacts","author":"Xiao","year":"2024","journal-title":"ICLR"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3606931"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"ref91","article-title":"Interdreamer: Zero-shot text to 3d dynamic human-object interaction","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref92","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_2"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01625"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459830"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657515"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01354"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00064"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_39"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00095"}],"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\/11533274.pdf?arnumber=11533274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:02:24Z","timestamp":1779944544000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533274\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":103,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00080","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}