{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T20:55:19Z","timestamp":1775768119385,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["62276061"],"award-info":[{"award-number":["62276061"]}],"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":["62436002"],"award-info":[{"award-number":["62436002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Fund for the Advanced Ocean Institute of Southeast University","award":["MP202404"],"award-info":[{"award-number":["MP202404"]}]},{"DOI":"10.13039\/501100001809","name":"Southeast University (SEU) Innovation Capability Enhancement Plan for Doctoral Students","doi-asserted-by":"publisher","award":["CXJH SEU 25125"],"award-info":[{"award-number":["CXJH SEU 25125"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3632245","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:46:04Z","timestamp":1763059564000},"page":"4827-4841","source":"Crossref","is-referenced-by-count":0,"title":["GC\n                    <sup>3<\/sup>\n                    VG: Generalized Multi-Task Visual Grounding With Coarse-to-Fine Consistency Constraints"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6133-0035","authenticated-orcid":false,"given":"Ming","family":"Dai","sequence":"first","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9053-3469","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5915-9565","authenticated-orcid":false,"given":"Wenxuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiedong","family":"Zhuang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4485-4249","authenticated-orcid":false,"given":"Zhenhua","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4310-9140","authenticated-orcid":false,"given":"Pengfei","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6385-6776","authenticated-orcid":false,"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183827"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521844"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3433547"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3374786"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231964"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3460874"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3508752"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3524543"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref15","first-page":"1","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Li"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27896"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32265"},{"key":"ref22","article-title":"GREC: Generalized referring expression comprehension","author":"He","year":"2023","journal-title":"arXiv:2308.16182"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref28","first-page":"1","article-title":"Fine-grained visual prompting","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Yang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01277"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_14"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3462100"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3528657"},{"key":"ref33","first-page":"7058","article-title":"PropVG: End-to-end proposal-driven visual grounding with multi-granularity discrimination","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Dai"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref35","first-page":"14729","article-title":"CoupAlign: Coupling word-pixel with sentence-mask alignments for referring image segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612117"},{"key":"ref37","article-title":"DeRIS: Decoupling perception and cognition for enhanced referring image segmentation through loopback synergy","author":"Dai","year":"2025","journal-title":"arXiv:2507.01738"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3593543"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01559-4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3607387"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref45","article-title":"A survey on benchmarks of multimodal large language models","author":"Li","year":"2024","journal-title":"arXiv:2408.08632"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3280906"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3371348"},{"key":"ref50","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00395"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681058"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref56","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref58","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"28","author":"Ren"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref62","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref63","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_19"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref67","article-title":"CoHD: A counting-aware hierarchical decoding framework for generalized referring expression segmentation","author":"Luo","year":"2024","journal-title":"arXiv:2405.15658"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3867"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296823"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328185"},{"key":"ref72","first-page":"1","article-title":"Ferret: Refer and ground anything anywhere at any granularity","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"You"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4438"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2291"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11245514.pdf?arnumber=11245514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:48:41Z","timestamp":1775764121000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":76,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3632245","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}