{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T18:33:17Z","timestamp":1770834797911,"version":"3.50.1"},"reference-count":105,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0118700"],"award-info":[{"award-number":["2022ZD0118700"]}]},{"name":"National Key R&D Program of China","award":["2022YFC2305102"],"award-info":[{"award-number":["2022YFC2305102"]}]},{"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":["62206104"],"award-info":[{"award-number":["62206104"]}],"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":["61936003"],"award-info":[{"award-number":["61936003"]}],"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":["62476093"],"award-info":[{"award-number":["62476093"]}],"id":[{"id":"10.13039\/501100001809","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":[[2025,4]]},"DOI":"10.1109\/tpami.2025.3528950","type":"journal-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:49:27Z","timestamp":1736884167000},"page":"2957-2972","source":"Crossref","is-referenced-by-count":3,"title":["VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-Domain Generalization"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3037-173X","authenticated-orcid":false,"given":"Yuliang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]},{"given":"Mingxin","family":"Huang","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"given":"Hao","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]},{"given":"Linger","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]},{"given":"Weijia","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3854-8664","authenticated-orcid":false,"given":"Hao","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5456-0957","authenticated-orcid":false,"given":"Lianwen","family":"Jin","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, 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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00595"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00930"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547942"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3379828"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00334-z"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00262"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01786"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00773"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2937086"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00917"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00480"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3077555"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00853"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223908"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref27","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00455"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2554321"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.207"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351093"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038520"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2014.6836024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2014.6890248"},{"key":"ref37","first-page":"1","article-title":"A bilingual, openworld video text dataset and end-to-end video text spotter with transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Wu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02063-1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/206"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00283"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3327962"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36802-9_16"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69535-4_18"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412558"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00285"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00920"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01474"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.87"},{"key":"ref53","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00914"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01342"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00772"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref60","first-page":"1","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref67","article-title":"Epic-kitchens-100 unsupervised domain adaptation challenge for action recognition 2021: Team m3em technical report","author":"Yang","year":"2021"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412541"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref75","article-title":"Segment and track anything","author":"Cheng","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547882"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25430"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/icdar.2017.237"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2068553"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.182"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3941-x"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206051"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.03.018"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2443556"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107791"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00174"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00661"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3155612"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110177"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref96","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref98","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref100","article-title":"MPLUG-OWL2: Revolutionizing multi-modal large language model with modality collaboration","author":"Ye","year":"2023"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref102","article-title":"Textmonkey: An OCR-free large multimodal model for understanding document","author":"Liu","year":"2024"},{"key":"ref103","article-title":"InternLM-XComposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024"},{"key":"ref104","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref105","article-title":"Exploring OCR capabilities of GPT-4V (ISION): A quantitative and in-depth evaluation","author":"Shi","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10916529\/10840310.pdf?arnumber=10840310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:38:58Z","timestamp":1741372738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10840310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":105,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3528950","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":[[2025,4]]}}}