{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T12:44:42Z","timestamp":1770468282951,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11208990","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Spatial 3D-LLM : Exploring Spatial Awareness in 3D Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Xiaoyan","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing Digital Native Digital City Research Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeju","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Digital Native Digital City Research Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Digital Native Digital City Research Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxing","family":"Qi","sequence":"additional","affiliation":[{"name":"Beijing Digital Native Digital City Research Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifei","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing Digital Native Digital City Research Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruifei","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing Digital Native Digital City Research Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangde","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Digital Native Digital City Research Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Digital Native Digital City Research Center"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning.","author":"Li","year":"2022"},{"key":"ref2","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"20482","article-title":"3d-llm: Injecting the 3d world into large language models","volume":"36","author":"Hong","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW63481.2024.10645462"},{"key":"ref5","article-title":"Chat-3d v2: Bridging 3d scene and large language models with object identifiers","author":"Huang","year":"2023"},{"key":"ref6","article-title":"An embodied generalist agent in 3d world","volume-title":"Forty-first International Conference on Machine Learning","author":"Huang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610090"},{"key":"ref8","article-title":"Vr-gpt: Visual language model for intelligent virtual reality applications","author":"Konenkov","year":"2024"},{"key":"ref9","article-title":"Llplace: The 3d indoor scene layout generation and editing via large language model","author":"Yang","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref11","article-title":"Grounded 3d-llm with referent tokens","author":"Chen","year":"2024"},{"key":"ref12","article-title":"Spatialrgpt: Grounded spatial reasoning in vision language model","author":"Cheng","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref14","article-title":"M3dbench: Let\u2019s instruct large models with multi-modal 3d prompts","author":"Li","year":"2023"},{"key":"ref15","article-title":"Mmscan: A multi-modal 3d scene dataset with hierarchical grounded language annotations","author":"Lyu","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref17","article-title":"Sqa3d: Situated question answering in 3d scenes","author":"Ma","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref22","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387838"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref27","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref28","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610443"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_9"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11208990.pdf?arnumber=11208990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:22Z","timestamp":1761888622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11208990","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}