{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:47:12Z","timestamp":1766083632867,"version":"3.48.0"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB3104700"],"award-info":[{"award-number":["2022YFB3104700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425114"],"award-info":[{"award-number":["62425114"]}],"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":["62121002"],"award-info":[{"award-number":["62121002"]}],"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":["U23B2028"],"award-info":[{"award-number":["U23B2028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ambient Intelligence and Trusted Services Key Laboratory of Sichuan Province","award":["WTP-KF-WDTXKMT"],"award-info":[{"award-number":["WTP-KF-WDTXKMT"]}]},{"name":"Supercomputiong Center of the USTC"},{"name":"GPU cluster built by MCC Lab of Information Science and Technology Institution, USTC"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3613181","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:25:57Z","timestamp":1758648357000},"page":"9429-9443","source":"Crossref","is-referenced-by-count":0,"title":["Masked Text Pre-Training for Scene Text Detection"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-5315","authenticated-orcid":false,"given":"Hongtao","family":"Xie","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6807-5207","authenticated-orcid":false,"given":"Keran","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1087-1784","authenticated-orcid":false,"given":"Bangbang","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0228-6220","authenticated-orcid":false,"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"given":"Weigang","family":"Qi","sequence":"additional","affiliation":[{"name":"Ambient Intelligence and Trusted Services Key Laboratory of Sichuan Province, Chengdu, China"}]},{"given":"Jie","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0265-5011","authenticated-orcid":false,"given":"Yadong","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"given":"Zuan","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1237-7177","authenticated-orcid":false,"given":"Dongming","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Communication Content Cognition, People's Daily Online, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5052-2582","authenticated-orcid":false,"given":"Yizhi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3216729"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2978630"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3286657"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3186431"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3197981"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223908"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3093727"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3172547"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995290"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00956"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859590"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240571"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3231737"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312285"},{"article-title":"Detecting curve text in the wild: New dataset and new solution","year":"2017","author":"Yuliang","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00592"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01523"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_17"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00870"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413565"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3155612"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref31","first-page":"385","article-title":"Designing Bert for convolutional networks: Sparse and hierarchical masked modeling","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Tian","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612370"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825107"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01080"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00134"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00314"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00853"},{"key":"ref43","first-page":"16433","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1163\/2589-7993_eeco_sim_00002236"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref48","first-page":"19460","article-title":"Architecture-agnostic masked image modelingfrom ViT back to CNN","volume-title":"Proc. Mach. Learn. Res.","author":"Li","year":"2023"},{"article-title":"Contrastive learning rivals masked image modeling in fine-tuning via feature distillation","year":"2022","author":"Wei","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16865"},{"key":"ref51","first-page":"33781","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Bangalath","year":"2022"},{"article-title":"Hierarchical text-conditional image generation with CLIP latents","year":"2022","author":"Ramesh","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611769"},{"key":"ref54","first-page":"7720","article-title":"Understanding and improving lexical choice in non-autoregressive translation","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Ding","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321480"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3236837"},{"key":"ref57","first-page":"1","article-title":"Can linguistic knowledge improve multimodal alignment in vision-language pretraining?","volume-title":"ACM Trans. Multimedia Comput., Commun. Appl.","volume":"20","author":"Wang","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681403"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247787"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00788"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2353813"},{"article-title":"COCO-text: Dataset and benchmark for text detection and recognition in natural images","year":"2016","author":"Veit","key":"ref68"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref71","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref72","article-title":"Large batch optimization for deep learning: Training BERT in 76 minutes","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"You","year":"2020"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3077555"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25430"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00731"},{"article-title":"MixNet: Toward accurate detection of challenging scene text in the wild","year":"2023","author":"Zeng","key":"ref77"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285096"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00569"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2900589"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/139"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00661"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02022-w"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3299087"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28302"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11175522.pdf?arnumber=11175522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:34:43Z","timestamp":1766082883000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11175522\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3613181","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}