{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:17:31Z","timestamp":1783455451052,"version":"3.55.0"},"reference-count":98,"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":"publisher","award":["62225207"],"award-info":[{"award-number":["62225207"]}],"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":["62436008"],"award-info":[{"award-number":["62436008"]}],"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":["62422609"],"award-info":[{"award-number":["62422609"]}],"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":["62276243"],"award-info":[{"award-number":["62276243"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAS Project for Young Scientists in Basic Research","award":["YSBR-122"],"award-info":[{"award-number":["YSBR-122"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3681112","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:01Z","timestamp":1775505361000},"page":"9859-9875","source":"Crossref","is-referenced-by-count":0,"title":["SkyFind: A Large-Scale Benchmark Unveiling Referring Expression Comprehension for UAV"],"prefix":"10.1109","volume":"48","author":[{"given":"Kunyu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanbo","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8036-4071","authenticated-orcid":false,"given":"Xueyang","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingbo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kean","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengjie","family":"Ge","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5695-8291","authenticated-orcid":false,"given":"Wei","family":"Zhai","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy11020203"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-022-00452-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00109"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02108-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3149507"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1342-3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.190"},{"key":"ref9","article-title":"CityNav: Language-goal aerial navigation dataset with geographic information","author":"Lee","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/EEEIC.2015.7165356"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114937"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/rs15133266"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00431"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413905"},{"key":"ref21","article-title":"GREC: Generalized referring expression comprehension","author":"He","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01444"},{"key":"ref23","article-title":"InstructDET: Diversifying referring object detection with generalized instructions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3232854"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01507"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02509"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339628"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186410"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3587251"},{"key":"ref42","article-title":"Ref-diff: Zero-shot referring image segmentation with generative models","author":"Ni","year":"2023"},{"key":"ref43","article-title":"Position-aware contrastive alignment for referring image segmentation","author":"Chen","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref45","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859880"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3314153"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3860"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.253500"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref60","article-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023"},{"key":"ref61","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref62","article-title":"One-PEACE: Exploring one general representation model toward unlimited modalities","author":"Wang","year":"2023"},{"key":"ref63","article-title":"MiniGPT-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref66","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gan"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3168279"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00374"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196845"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.446"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06430-2_53"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.267"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_33"},{"key":"ref76","article-title":"Semantic drone dataset","year":"2019"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.05.009"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03398-9_30"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3390\/rs12111760"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00168"},{"key":"ref81","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-61257-2"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref87","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":"ref88","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.3390\/systems11080400"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3176400"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/MAES.2013.6516147"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0483-z"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.3390\/drones6070154"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01411"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.3390\/rs15082139"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.06.002"},{"key":"ref97","article-title":"RefDrone: A challenging benchmark for referring expression comprehension in drone scenes","author":"Sun","year":"2025"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00492"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11475181.pdf?arnumber=11475181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:44:30Z","timestamp":1783453470000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11475181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":98,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3681112","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":[[2026,8]]}}}