{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:13:38Z","timestamp":1775578418202,"version":"3.50.1"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":["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 Advanced Ocean Institute of Southeast University","award":["MP202404"],"award-info":[{"award-number":["MP202404"]}]},{"name":"SEU Innovation Capability Enhancement Plan for Doctoral Students","award":["CXJH_SEU 25125"],"award-info":[{"award-number":["CXJH_SEU 25125"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tpami.2025.3607387","type":"journal-article","created":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:45:16Z","timestamp":1757353516000},"page":"448-465","source":"Crossref","is-referenced-by-count":2,"title":["Improving Generalized Visual Grounding With Instance-Aware Joint Learning"],"prefix":"10.1109","volume":"48","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"}]},{"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1341-2763","authenticated-orcid":false,"given":"Jiang-Jiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2725-8947","authenticated-orcid":false,"given":"Lingfeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4485-4249","authenticated-orcid":false,"given":"Zhenhua","family":"Feng","sequence":"additional","affiliation":[{"name":"JiangNan University, Wuxi, China"}]},{"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328185"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612117"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00395"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3867"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.073"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296823"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277791"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref29","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27896"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref36","article-title":"HDC: Hierarchical semantic decoding with counting assistance for generalized referring expression segmentation","author":"Luo","year":"2024"},{"key":"ref37","article-title":"GREC: Generalized referring expression comprehension","author":"He","year":"2023"},{"key":"ref38","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01349"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref42","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref44","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref47","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3090426"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25331"},{"key":"ref52","first-page":"139854","article-title":"OneRef: Unified one-tower expression grounding and segmentation with mask referring modeling","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3371348"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_8"},{"key":"ref59","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref60","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref67","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref70","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gan"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25261"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref74","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"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681071"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref84","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref85","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11275622\/11153716.pdf?arnumber=11153716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T21:01:29Z","timestamp":1764882089000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11153716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":85,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3607387","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}