{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:07:20Z","timestamp":1780949240547,"version":"3.54.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["62425603"],"award-info":[{"award-number":["62425603"]}],"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":["62372233"],"award-info":[{"award-number":["62372233"]}],"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":["62272230"],"award-info":[{"award-number":["62272230"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018554","name":"Major Science and Technology Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BG2024042"],"award-info":[{"award-number":["BG2024042"]}],"id":[{"id":"10.13039\/501100018554","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005145","name":"Basic Research Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20240011"],"award-info":[{"award-number":["BK20240011"]}],"id":[{"id":"10.13039\/501100005145","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3686876","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:00:24Z","timestamp":1776974424000},"page":"8675-8686","source":"Crossref","is-referenced-by-count":0,"title":["FineG-RAG: Fine-Grained Retrieval-Augmented Generation for Multimodal Large Language Models"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2964-426X","authenticated-orcid":false,"given":"Lu","family":"Jin","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6682-0338","authenticated-orcid":false,"given":"Cheng","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2344-6174","authenticated-orcid":false,"given":"Xinguang","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6249-5596","authenticated-orcid":false,"given":"Yanpeng","family":"Sun","sequence":"additional","affiliation":[{"name":"NExT++ Laboratory, School of Computing, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5341-5985","authenticated-orcid":false,"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"Nanjing Forestry University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref3","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3336371"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2688"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.14"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355640"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521708"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3597097"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref14","first-page":"1","article-title":"Democratizing fine-grained visual recognition with large language models","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291819"},{"key":"ref16","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02093"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01836"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref22","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref23","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref24","first-page":"3929","article-title":"Retrieval augmented language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guu"},{"key":"ref25","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lewis"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02238"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00188"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.002"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3535818"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3244340"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090274"},{"key":"ref34","article-title":"RAR: Retrieving and ranking augmented MLLMs for visual recognition","author":"Liu","year":"2024","journal-title":"arXiv:2403.13805"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3406443"},{"key":"ref36","first-page":"1027","article-title":"K-means++: The advantages of careful seeding","volume-title":"Soda","author":"Arthur","year":"2007"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214431"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3495533"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331336"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3325001"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref42","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res. J."},{"key":"ref43","first-page":"1","article-title":"Data filtering networks","volume-title":"Proc. ICLR","author":"Fang"},{"key":"ref44","article-title":"The caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"issue":"1","key":"ref45","first-page":"2","article-title":"Novel datasets for fine-grained image categorization","volume-title":"Proc. 1st Workshop Fine Grained Vis. Categorization","volume":"5","author":"Dataset"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref49","article-title":"Kimi-VL technical report","volume-title":"arXiv:2504.07491","author":"Team","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref51","article-title":"LLaVA-NeXT-interleave: Tackling multi-image, video, and 3D in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv:2407.07895"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28034"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11494024.pdf?arnumber=11494024","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:55:18Z","timestamp":1780948518000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11494024\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":53,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3686876","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}