{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:23:46Z","timestamp":1786119826385,"version":"build-2736575974"},"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"}],"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.2026.3681596","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:02:42Z","timestamp":1775592162000},"page":"12465-12478","source":"Crossref","is-referenced-by-count":0,"title":["MiCA: Intra-Modal Integration and Cross-Modal Alignment Adapters for Parameter-Efficient Referring Image Segmentation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5672-4110","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7599-445X","authenticated-orcid":false,"given":"Zitong","family":"Feng","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingrui","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0510-3307","authenticated-orcid":false,"given":"Chenyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1496-405X","authenticated-orcid":false,"given":"Xin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref3","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Faghri"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794287"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231964"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3508752"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3524543"},{"key":"ref8","first-page":"1","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. ICML","author":"Houlsby"},{"key":"ref9","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01869"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.98"},{"key":"ref15","article-title":"Global compression commander: Plug-and-play inference acceleration for high-resolution large vision-language models","author":"Liu","year":"2025","journal-title":"arXiv:2501.05179"},{"key":"ref16","article-title":"Mixing importance with diversity: Joint optimization for KV cache compression in large vision-language models","author":"Liu","year":"2025","journal-title":"arXiv:2510.20707"},{"key":"ref17","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Mahabadi"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3233\/faia240489"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1399"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3557570"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3551766"},{"key":"ref23","first-page":"1","article-title":"BarLeRIa: An efficient tuning framework for referring image segmentation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32380"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00602"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.143"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00180"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3104"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01139"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref37","article-title":"AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning","author":"Zhang","year":"2023","journal-title":"arXiv:2303.10512"},{"key":"ref38","first-page":"32100","article-title":"DoRA: Weight-decomposed low-rank adaptation","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01926"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02213"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680940"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02699"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688132"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3618553"},{"key":"ref46","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref47","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref50","first-page":"19769","article-title":"Segment everything everywhere all at once","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gao"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02509"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_7"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.258"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111144"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1086"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.287"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681071"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111144"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11643439\/11475681.pdf?arnumber=11475681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T19:06:33Z","timestamp":1786043193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11475681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":64,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3681596","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}