{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:50:39Z","timestamp":1774893039870,"version":"3.50.1"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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":["62225603"],"award-info":[{"award-number":["62225603"]}],"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":["62206103"],"award-info":[{"award-number":["62206103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFC2305102"],"award-info":[{"award-number":["2022YFC2305102"]}],"id":[{"id":"10.13039\/501100012166","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":[[2024,9]]},"DOI":"10.1109\/tpami.2024.3379828","type":"journal-article","created":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T14:20:20Z","timestamp":1710944420000},"page":"6040-6054","source":"Crossref","is-referenced-by-count":21,"title":["Turning a CLIP Model Into a Scene Text Spotter"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4666-3646","authenticated-orcid":false,"given":"Wenwen","family":"Yu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3037-173X","authenticated-orcid":false,"given":"Yuliang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0561-4390","authenticated-orcid":false,"given":"Xingkui","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3789-9705","authenticated-orcid":false,"given":"Haoyu","family":"Cao","sequence":"additional","affiliation":[{"name":"Tencent, YouTu Lab, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8132-9083","authenticated-orcid":false,"given":"Xing","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent, YouTu Lab, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3449-5940","authenticated-orcid":false,"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref3","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01523"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00592"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_17"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"ref12","first-page":"9328","article-title":"Shape robust text detection with progressive scale expansion network","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00853"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00452"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.451"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.331"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.87"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01080"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00661"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00314"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00870"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00134"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25430"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3286657"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref32","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3095916"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.242"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00595"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2937086"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00480"},{"key":"ref40","first-page":"9075","article-title":"TextDragon: An end-to-end framework for arbitrary shaped text spotting","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Wei"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"ref42","first-page":"9125","article-title":"Convolutional character networks","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Linjie"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223908"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00455"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref48","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00930"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547942"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"ref53","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00030","article-title":"Multimodal neurons in artificial neural networks","volume-title":"Distill","author":"Goh","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247787"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00334-z"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3176122"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00920"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2900589"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00353"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/72"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3155612"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00922"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_30"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6864"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00917"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3077555"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16383"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16348"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_15"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69535-4_18"},{"key":"ref87","article-title":"PVANET: Deep but lightweight neural networks for real-time object detection","author":"Kim","year":"2016"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2737-0"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00985"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2021.1931535"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.3390\/rs12193262"},{"key":"ref93","first-page":"11830","article-title":"Rethinking rotated object detection with gaussian wasserstein distance loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref94","first-page":"18381","article-title":"Learning high-precision bounding box for rotated object detection via kullback-leibler divergence","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10627928\/10476714.pdf?arnumber=10476714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:30:52Z","timestamp":1756755052000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10476714\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":98,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3379828","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":[[2024,9]]}}}