{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:08:00Z","timestamp":1790273280594,"version":"4.1.0"},"reference-count":65,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2336213,62376259,62306301"],"award-info":[{"award-number":["U2336213,62376259,62306301"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00411","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4317-4327","source":"Crossref","is-referenced-by-count":1,"title":["HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding"],"prefix":"10.1109","author":[{"given":"Jiahe","family":"Zhao","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Laboratory of AI Safety,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruibing","family":"Hou","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Laboratory of AI Safety,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zejie","family":"Tian","sequence":"additional","affiliation":[{"name":"Communication University of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Chang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Laboratory of AI Safety,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Laboratory of AI Safety,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Gpt-4v(ision) system card.","year":"2023"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02032"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref6","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref7","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref9","article-title":"Motionllm: Understanding human behaviors from human motions and videos","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref12","article-title":"Grounded 3d-1lm with referent tokens","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01355"},{"key":"ref15","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.","author":"Chiang","year":"2023"},{"key":"ref16","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2023","journal-title":"JMLR"},{"key":"ref17","volume-title":"Scaling instructionfinetuned language models","author":"Won Chung","year":"2024"},{"key":"ref18","article-title":"Laserhuman: language-guided scene-aware human motion generation in free environment","author":"Cong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_20"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01379"},{"key":"ref21","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Motion question answering via modular motion programs","author":"Endo","year":"2023","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00204"},{"key":"ref24","article-title":"Scene-llm: Extending language model for 3d visual understanding and reasoning","author":"Fu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"ref30","article-title":"3d-llm: Injecting the 3d world into large language models","author":"Hong","year":"2023","journal-title":"NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02494"},{"key":"ref32","article-title":"Chat-scene: Bridging 3d scene and large language models with object identifiers","author":"Huang","year":"2024","journal-title":"NeurIPS"},{"key":"ref33","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Motiongpt: Human motion as a foreign language","author":"Jiang","year":"2023","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"ref36","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"TMLR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00027"},{"key":"ref38","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02589"},{"key":"ref40","article-title":"Motion-x: A largescale 3d expressive whole-body human motion dataset","author":"Lin","year":"2023","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref42","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref43","article-title":"M3gpt: An advanced multimodal, multitask framework for motion comprehension and generation","author":"Luo","year":"2024","journal-title":"NeurIPS"},{"key":"ref44","article-title":"Sqa3d: Situated question answering in 3d scenes","author":"Ma","year":"2022","journal-title":"ICLR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00593"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_13"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02495"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00119"},{"key":"ref52","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"NeurIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"ref54","article-title":"3d-grand: A million-scale dataset for $3 ~\\mathrm{d}-11 ~\\text{ms}$ with better grounding and less hallucination","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01874"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535389"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_23"},{"key":"ref58","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref60","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref61","article-title":"Spartun3d: Situated spatial understanding of 3d world in large language models","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref62","volume-title":"3d-vla: A 3d vision-language-action generative world model.","author":"Zhen","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_39"},{"key":"ref64","article-title":"Uni3d: Exploring unified 3d representation at scale","author":"Zhou","year":"2024","journal-title":"ICLR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00135"}],"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\/11445788.pdf?arnumber=11445788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:36Z","timestamp":1777612116000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445788\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00411","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}