{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T03:25:30Z","timestamp":1783740330941,"version":"3.55.0"},"reference-count":60,"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\/iccv51701.2025.01310","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14117-14127","source":"Crossref","is-referenced-by-count":2,"title":["SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation"],"prefix":"10.1109","author":[{"given":"Wenjia","family":"Wang","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Pan","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyang","family":"Dou","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jidong","family":"Mei","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhouyingcheng","family":"Liao","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuke","family":"Lou","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingbo","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taku","family":"Komura","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02032"},{"key":"ref3","first-page":"3","author":"Cong","year":"2024","journal-title":"Laserhuman: language-guided scene-aware human motion generation in free environment"},{"key":"ref4","first-page":"3","author":"Devlin","year":"2018","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618205"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01390"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2532"},{"key":"ref9","first-page":"3","author":"Ge","year":"2024","journal-title":"3d human reconstruction in the wild with synthetic data using generative models"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01093"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591525"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01152"},{"key":"ref15","first-page":"3","article-title":"Motiongpt: Human motion as a foreign language","volume":"36","author":"Jiang","year":"2023","journal-title":"NeuraIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555391"},{"key":"ref18","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"NeuralPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02595"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01000"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref23","first-page":"2","author":"Makoviychuk","year":"2021","journal-title":"Isaac gym: High performance gpu-based physics simulation for robot learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3522618"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00149"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00506"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530110"},{"key":"ref32","first-page":"1","author":"Pi","year":"2025","journal-title":"Coda: Coordinated diffusion noise optimization for wholebody manipulation of articulated objects"},{"key":"ref33","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356505"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610948"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00180"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591541"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3687951"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref41","first-page":"6","article-title":"Human motion diffusion model","author":"Tevet","year":"2023","journal-title":"ICLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.70675\/a4b835c3z7030z4699zbeb2zb5faccaee2de"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01981"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_22"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00363"},{"key":"ref46","article-title":"Humanise: Language-conditioned human motion generation in 3d scenes","volume":"35","author":"Wang","year":"2022","journal-title":"NeuralPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00049"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530067"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3687904"},{"key":"ref50","article-title":"Unified human-scene interaction via prompted chain-of-contacts","author":"Xiao","year":"2024","journal-title":"ICLR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3606931"},{"key":"ref52","first-page":"1","author":"Xu","year":"2025","journal-title":"Mospa: Human motion generation driven by spatial audio"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01145"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_14"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355414\/mm2"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00130"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01354"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_2"}],"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\/11443967.pdf?arnumber=11443967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:45Z","timestamp":1777613325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443967\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01310","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}