{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T08:27:25Z","timestamp":1773476845404,"version":"3.50.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62406053"],"award-info":[{"award-number":["62406053"]}],"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":["62441231"],"award-info":[{"award-number":["62441231"]}],"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":["62206039"],"award-info":[{"award-number":["62206039"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["DUT24YG119"],"award-info":[{"award-number":["DUT24YG119"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["DUT24RC(3)025"],"award-info":[{"award-number":["DUT24RC(3)025"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557620","type":"journal-article","created":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T17:24:33Z","timestamp":1746120273000},"page":"2899-2911","source":"Crossref","is-referenced-by-count":6,"title":["3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding"],"prefix":"10.1109","volume":"27","author":[{"given":"Haomiao","family":"Xiong","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4288-4516","authenticated-orcid":false,"given":"Yunzhi","family":"Zhuge","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5431-1654","authenticated-orcid":false,"given":"Jiawen","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4648-4437","authenticated-orcid":false,"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Chatgpt: Optimizing language models for dialogue","year":"2022"},{"key":"ref2","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref3","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref4","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref5","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Li","year":"2023"},{"key":"ref6","article-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref8","article-title":"X-Instructblip: A framework for aligning X-modal instruction-aware representations to LLMs and emergent cross-modal reasoning","author":"Panagopoulou","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref10","article-title":"SQA3D: Situated question answering in 3D scenes","author":"Ma","year":"2022"},{"key":"ref11","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref13","first-page":"20482","article-title":"3D-LLM: Injecting the 3D world into large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hong","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref16","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref18","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref19","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90 ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"},{"issue":"140","key":"ref22","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Representations"},{"key":"ref23","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"issue":"240","key":"ref26","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Representations"},{"key":"ref27","article-title":"Baichuan 2: Open large-scale language models","author":"Yang","year":"2023"},{"key":"ref28","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac","year":"2022"},{"key":"ref29","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02510"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3125981"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01413"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00761"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_31"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref43","first-page":"44860","article-title":"OpenShape: Scaling up 3D shape representation towards open-world understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2024"},{"key":"ref44","first-page":"28223","article-title":"Contrast with reconstruct: Contrastive 3D representation learning guided by generative pretraining","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Qi","year":"2023"},{"key":"ref45","article-title":"LLaMA-adapter V2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref46","article-title":"Bamboo: A comprehensive benchmark for evaluating long text modeling capacities of large language models","author":"Dong","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"ref48","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Liu","year":"2024"},{"key":"ref49","article-title":"MiniGPT-V2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"issue":"8","key":"ref50","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref51","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":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197519"},{"key":"ref55","article-title":"Languagebind: Extending video-language pretraining to N-modality by language-based semantic alignment","author":"Zhu","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref60","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref61","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref63","first-page":"46595","article-title":"Judging LLM-as-a-judge with MT-bench and ChatBot arena","volume-title":"Proc. Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Zheng","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref65","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref66","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32248-9_23"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10981614.pdf?arnumber=10981614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:30:56Z","timestamp":1748539856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10981614\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557620","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}