{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T22:01:01Z","timestamp":1786053661819,"version":"3.56.0"},"reference-count":64,"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":"crossref","award":["U23B2031"],"award-info":[{"award-number":["U23B2031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Scientific and Technological Research Project of Hunan Province, China,","award":["2024QK2010"],"award-info":[{"award-number":["2024QK2010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tcsvt.2026.3684576","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T19:55:06Z","timestamp":1776369306000},"page":"11391-11401","source":"Crossref","is-referenced-by-count":0,"title":["Text-Guided Vision Token Reduction With Low-Rank Adaptation for Efficient Visual Grounding"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5934-8837","authenticated-orcid":false,"given":"Liangtao","family":"Shi","sequence":"first","affiliation":[{"name":"Hefei University of Technology","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2597-3020","authenticated-orcid":false,"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Hunan Police College","place":["Changsha, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxia","family":"Xie","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology","place":["Nanjing, China"],"department":["Department of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3867-6753","authenticated-orcid":false,"given":"Ning","family":"Li","sequence":"additional","affiliation":[{"name":"Guangxi Normal University","place":["Guilin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3423-1539","authenticated-orcid":false,"given":"Bineng","family":"Zhong","sequence":"additional","affiliation":[{"name":"Guangxi Normal University","place":["Guilin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296823"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.287"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681071"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3867"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3618553"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321501"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32866"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32158"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3630635"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref14","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv:2306.15195"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688132"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3551766"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4438"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref21","article-title":"Referring expression object segmentation with caption-aware consistency","volume-title":"Proc. BMVC","author":"Chen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475313"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147385"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3407785"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3502621"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3308969"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01393"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3557570"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3541960"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3327605"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3429192"},{"key":"ref36","first-page":"2","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3595896"},{"key":"ref38","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. NeurIPS","author":"Rao"},{"key":"ref39","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","volume-title":"Proc. ICLR","author":"Liang"},{"key":"ref40","article-title":"Token merging: Your ViT but faster","volume-title":"Proc. ICLR","author":"Bolya"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3395481"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3488181"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01277"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3289624"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28286"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755282"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328185"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183827"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25085-9_1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3324362"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3343736"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3334099"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339628"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11643439\/11482608.pdf?arnumber=11482608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T19:06:39Z","timestamp":1786043199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11482608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":64,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3684576","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}