{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T23:10:39Z","timestamp":1783552239169,"version":"3.55.0"},"reference-count":68,"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":["62576243"],"award-info":[{"award-number":["62576243"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2024YFB4710704"],"award-info":[{"award-number":["2024YFB4710704"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3664998","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:07:48Z","timestamp":1771276068000},"page":"5422-5436","source":"Crossref","is-referenced-by-count":2,"title":["Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3343-2497","authenticated-orcid":false,"given":"Jinyuan","family":"Li","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyan","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Li","sequence":"additional","affiliation":[{"name":"College of Mathematics, Taiyuan University of Technology, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8380-0609","authenticated-orcid":false,"given":"Jianfei","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0621-1058","authenticated-orcid":false,"given":"Rui","family":"Xia","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2793-7066","authenticated-orcid":false,"given":"Di","family":"Sun","sequence":"additional","affiliation":[{"name":"Tianjin University of Science and Technology, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2155-4689","authenticated-orcid":false,"given":"Gang","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1078"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2920620"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2757769"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2867718"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00104"},{"key":"ref10","article-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"Huang","year":"2015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1101"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548427"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3013398"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859972"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.232"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.437"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548228"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291503"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3175374"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.508"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612322"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.85"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.239"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref32","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":"ref33","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref38","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ordonez","year":"2011"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.184"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.76"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612095"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1037\/h0031619"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.2307\/1932409.JSTOR1932409"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref55","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lafferty","year":"2001"},{"key":"ref56","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_1"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"ref59","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90 ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref60","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.63317\/48465grj4cjm"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.880"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679793"},{"key":"ref64","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":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref66","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.451"},{"key":"ref68","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11397194.pdf?arnumber=11397194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:53:39Z","timestamp":1783108419000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3664998","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}