{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:20Z","timestamp":1777890080086,"version":"3.51.4"},"reference-count":47,"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"}],"funder":[{"DOI":"10.13039\/501100010418","name":"IITP","doi-asserted-by":"publisher","award":["RS-2021-II211341"],"award-info":[{"award-number":["RS-2021-II211341"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012266","name":"NRF","doi-asserted-by":"publisher","award":["RS-2023-00208197"],"award-info":[{"award-number":["RS-2023-00208197"]}],"id":[{"id":"10.13039\/501100012266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01084","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11654-11664","source":"Crossref","is-referenced-by-count":0,"title":["Event-Driven Storytelling with Multiple Lifelike Humans in a 3D Scene"],"prefix":"10.1109","author":[{"given":"Donggeun","family":"Lim","sequence":"first","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinseok","family":"Bae","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inwoo","family":"Hwang","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungmin","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hwanhee","family":"Lee","sequence":"additional","affiliation":[{"name":"Chung-Ang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Young Min","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02032"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00182"},{"key":"ref5","article-title":"Sitcom-crafter: A plot-driven human motion generation system in 3d scenes","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"5","article-title":"Motion matching and the road to nextgen animation","volume-title":"Proc. of GDC, page 4","author":"Clavet","year":"2016"},{"key":"ref7","first-page":"4","article-title":"Llms are not intelligent thinkers: Introducing mathematical topic tree benchmark for comprehensive evaluation of 11 ms","author":"Gholami Davoodi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_24"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341989"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"ref14","first-page":"20413","article-title":"An embodied generalist agent in 3d world","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Huang","year":"2024"},{"key":"ref15","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International conference on machine learning","author":"Huang","year":"2022"},{"key":"ref16","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.272"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687595"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802322"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref22","first-page":"2","article-title":"Interactive task planning with language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680636"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00061"},{"key":"ref27","article-title":"Gsmsymbolic: Understanding the limitations of mathematical reasoning in large language models","author":"Mirzadeh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801291"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3586183.3606763","article-title":"Generative agents: Interactive simulacra of human behavior","volume-title":"Proceedings of the 36th annual acm symposium on user interface software and technology","author":"Sung Park","year":"2023"},{"key":"ref30","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning","author":"Rana","year":"2023","journal-title":"CoRL"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73650-6_5"},{"key":"ref32","first-page":"31210","article-title":"Large language models can be easily distracted by irrelevant context","volume-title":"International Conference on Machine Learning","author":"Shi","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v1i1.18726"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01466"},{"key":"ref36","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01981"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1088"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00049"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref42","first-page":"2","article-title":"Hallucination is inevitable: An innate limitation of large language models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610443"},{"key":"ref45","first-page":"246","article-title":"Generating human interaction motions in scenes with text control","volume-title":"European Conference on Computer Vision","author":"Yi","year":"2024"},{"key":"ref46","first-page":"2","article-title":"Building cooperative embodied agents modularly with large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhang","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01354"}],"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\/11444762.pdf?arnumber=11444762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:05Z","timestamp":1777613405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444762\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01084","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}