{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:17:39Z","timestamp":1783455459482,"version":"3.55.0"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":["U24A20326"],"award-info":[{"award-number":["U24A20326"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572423"],"award-info":[{"award-number":["62572423"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3679561","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:52:44Z","timestamp":1774986764000},"page":"9813-9825","source":"Crossref","is-referenced-by-count":0,"title":["Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2813-6574","authenticated-orcid":false,"given":"Haifeng","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3372-8703","authenticated-orcid":false,"given":"Yilun","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6711-9319","authenticated-orcid":false,"given":"Jiangmiao","family":"Pang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-0384","authenticated-orcid":false,"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref2","article-title":"GPT-4 technical report","year":"2023","journal-title":""},{"key":"ref3","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"issue":"240","key":"ref4","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3571946"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref9","article-title":"BuboGPT: Enabling visual grounding in multi-modal LLMs","author":"Zhao","year":"2023"},{"key":"ref10","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref13","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref19","article-title":"SQA3D: Situated question answering in 3D scenes","author":"Ma","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref21","article-title":"An embodied generalist agent in 3D world","author":"Huang","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.18"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3620"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref26","article-title":"UNI3D: Exploring unified 3D representation at scale","author":"Zhou","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00202"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00847"},{"key":"ref30","article-title":"OpenAI o1","year":"2025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1492"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.656"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00251"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_12"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387838"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00593"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref47","first-page":"487","article-title":"D3Net: A unified speaker-listener architecture for 3D dense captioning and visual grounding","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Chen","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"issue":"2","key":"ref50","first-page":"1","article-title":"A survey on fine-grained multimodal large language models","volume":"35","author":"Yuxin","year":"2026","journal-title":"Chin. J. Electron."},{"key":"ref51","article-title":"ImageBind-LLM: Multi-modality instruction tuning","author":"Han","year":"2023"},{"key":"ref52","article-title":"Point-bind & point-LLM: Aligning point cloud with multi-modality for 3D understanding, generation, and instruction following","author":"Guo","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref54","article-title":"Grounded 3D-LLM with referent tokens","author":"Chen","year":"2024"},{"key":"ref55","article-title":"Scene-LLM: Extending language model for 3D visual understanding and reasoning","author":"Fu","year":"2024"},{"key":"ref56","first-page":"1","article-title":"Towards reliable multimodal intelligence via uncertainty-aware inference","volume":"35","author":"Tianxiang","year":"2026","journal-title":"Chin. J. Electron."},{"issue":"4","key":"ref57","first-page":"1","article-title":"Formation-guided multimodal representation learning for group action quality assessment","volume":"35","author":"Zexing","year":"2026","journal-title":"Chin. J. Electron."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1962"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1944"},{"key":"ref63","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref66","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref69","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref70","article-title":"The LLAMA 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33001"},{"key":"ref74","article-title":"OccLLaMA: An occupancy-language-action generative world model for autonomous driving","author":"Wei","year":"2024"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00356"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i16.38386"},{"key":"ref77","article-title":"LLAMA-Adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11458668.pdf?arnumber=11458668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:45:13Z","timestamp":1783453513000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11458668\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":78,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3679561","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}