{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:06:42Z","timestamp":1780949202179,"version":"3.54.1"},"reference-count":72,"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":["62506003"],"award-info":[{"award-number":["62506003"]}],"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":["62376004"],"award-info":[{"award-number":["62376004"]}],"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":["U24A20342"],"award-info":[{"award-number":["U24A20342"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2408085QF201"],"award-info":[{"award-number":["2408085QF201"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project of Anhui Provincial Key Laboratory of Intelligent Detection and Diagnosis for Traffic Infrastructure","award":["KY-2025-03"],"award-info":[{"award-number":["KY-2025-03"]}]}],"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.2026.3663260","type":"journal-article","created":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T21:06:49Z","timestamp":1770757609000},"page":"8930-8940","source":"Crossref","is-referenced-by-count":0,"title":["Revisiting Frequency Domain: Spatial-Frequency Joint Tuning for Referring Image Segmentation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6198-8230","authenticated-orcid":false,"given":"Guyue","family":"Hu","sequence":"first","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, and Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxing","family":"Tong","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, and Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongtao","family":"Liu","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Intelligent Detection and Diagnosis for Traffic Infrastructure, Anhui Jiaojian Traffic Development and Research Center Company Ltd., Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1356-4798","authenticated-orcid":false,"given":"Dong","family":"Geng","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Intelligent Detection and Diagnosis for Traffic Infrastructure, Anhui Jiaojian Traffic Development and Research Center Company Ltd., Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7233-2739","authenticated-orcid":false,"given":"Chenglong","family":"Li","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, and Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00909"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3437645"},{"key":"ref6","article-title":"LidaRefer: Context-aware outdoor 3D visual grounding for autonomous driving","author":"Baek","year":"2024","journal-title":"arXiv:2411.04351"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32902"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160748"},{"key":"ref9","first-page":"655","article-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Majumdar"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref14","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32380"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"ref24","article-title":"Barleria: An efficient tuning framework for referring image segmentation","volume-title":"Proc. 12th Int. Conf. Learn. Represent","author":"Wang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00395"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128679"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_19"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00183"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0193"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00446"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01085"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CRV52889.2021.00011"},{"key":"ref35","first-page":"980","article-title":"Global filter networks for image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rao"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25212"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3287038"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01434"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.187"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021088"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00171"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00181"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249468"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref47","article-title":"Multimodal referring segmentation: A survey","author":"Ding","year":"2025","journal-title":"arXiv:2508.00265"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-3216-7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2953325"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00989"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01868"},{"key":"ref52","article-title":"Spatial-Mamba: Effective visual state space models via structure-aware state fusion","volume-title":"Proc. 13th Int. Conf. Learn. Represent. (ICLR)","author":"Xiao"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0180"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3553781"},{"issue":"8","key":"ref55","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref56","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"Proc. ICLR"},{"key":"ref57","first-page":"2790","article-title":"Parameter-efficient transfer learning foR NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3540211"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130286"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129442"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3569834"},{"key":"ref64","volume-title":"A Wavelet Tour of Signal Processing","author":"Mallat","year":"1999"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02258"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3367127"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-051581-6.50065-9"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3049869"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2890574"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11390680.pdf?arnumber=11390680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:17Z","timestamp":1780948457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11390680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":72,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3663260","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}