{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T20:07:13Z","timestamp":1779739633397,"version":"3.53.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/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"}]},{"DOI":"10.13039\/100031931","name":"Shanghai Artificial Intelligence Laboratory","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100031931","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3654372","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:40:43Z","timestamp":1768941643000},"page":"3739-3754","source":"Crossref","is-referenced-by-count":5,"title":["Visual Position Prompt for MLLM Based Visual Grounding"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3414-2421","authenticated-orcid":false,"given":"Wei","family":"Tang","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\/0000-0001-6249-5596","authenticated-orcid":false,"given":"Yanpeng","family":"Sun","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\/0000-0002-8863-0810","authenticated-orcid":false,"given":"Qinying","family":"Gu","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3428317"},{"key":"ref2","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref4","article-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref5","article-title":"Descriptive caption enhancement with visual specialists for multi-modal perception","author":"Sun","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_24"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.253500"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548206"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3365104"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3543062"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535345"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321501"},{"key":"ref13","article-title":"MiniGPT-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3511621"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"},{"key":"ref18","first-page":"37484","article-title":"Singular value fine-tuning: Few-shot segmentation requires few-parameters fine-tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Sun","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535323"},{"key":"ref21","article-title":"Shikra: Unleashing multimodal LLMs referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref22","first-page":"87310","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal LLMS","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tong","year":"2024"},{"key":"ref23","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref24","article-title":"Improving multi-modal large language model through boosting vision capabilities","author":"Sun","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.360"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_10"},{"key":"ref29","first-page":"2886","article-title":"Scaffolding coordinates to promote vision-language coordination in large multi-modal models","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Lei","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3393512"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680763"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02145"},{"key":"ref33","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3452418"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339628"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186410"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3139467"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181516"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref43","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref46","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref47","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%  ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref48","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref49","article-title":"Kosmos-2: Grounding multimodal large language models to the world","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Peng","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01313"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01236"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00865"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3293484"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28034"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3554410"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424566"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.504"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.763"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02224"},{"key":"ref64","first-page":"24993","article-title":"Fine-grained visual prompting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang","year":"2024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02508"},{"key":"ref67","article-title":"Rethinking visual prompting for multi-modal large language models with external knowledge","author":"Lin","year":"2024"},{"key":"ref68","article-title":"Contextdet: Temporal action detection with adaptive context aggregation","author":"Wang","year":"2024"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3320435.3320439"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_8"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"ref75","article-title":"Eagle: Exploring the design space for multimodal llms with mixture of encoders","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2024"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.02130"},{"key":"ref79","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024"},{"key":"ref80","article-title":"Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024"},{"key":"ref81","article-title":"Mistral-small-3.1-24b-instruct-2503","year":"2024"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11359555.pdf?arnumber=11359555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T19:55:07Z","timestamp":1779738907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11359555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3654372","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}