{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:14:18Z","timestamp":1784301258201,"version":"3.55.0"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62427819,32341012,62172103"],"award-info":[{"award-number":["62427819,32341012,62172103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01874","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20147-20156","source":"Crossref","is-referenced-by-count":9,"title":["SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition"],"prefix":"10.1109","author":[{"given":"Yongkun","family":"Du","sequence":"first","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhineng","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caiyan","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00481"},{"key":"ref3","article-title":"BEiT: BERT pretraining of image transformers","author":"Bao","year":"2022","journal-title":"ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01185"},{"key":"ref6","article-title":"Benchmarking chinese text recognition: Datasets, baselines, and an empirical study","author":"Chen","year":"2021","journal-title":"CoRR, abs\/2112.15093"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3440756"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01790"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_19"},{"key":"ref10","article-title":"An image is worth $16\\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/124"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32285"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3545453"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3525526"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223908"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01467"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01784"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6735"},{"key":"ref24","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"Jaderberg","year":"2014","journal-title":"CoRR, abs\/1406.2227"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01878"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref27","first-page":"14841493","article-title":"ICDAR 2013 robust reading competition","author":"KaratzasAU","year":"2013","journal-title":"ICDAR"},{"key":"ref28","article-title":"PP-OCRv3: More attempts for the improvement of ultra lightweight ocr system","author":"Li","year":"2022","journal-title":"CoRR, abs\/2206.03001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"ref30","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107980"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_26"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01479"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00130"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2017","journal-title":"ICLR"},{"key":"ref43","article-title":"2d-ctc for scene text recognition","author":"Wan","year":"2019","journal-title":"CoRR, abs\/1907.09705"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2011.6126402"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_20"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3197981"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28402"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_18"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02676"},{"key":"ref53","first-page":"4203","article-title":"Focal modulation networks","author":"Yang","year":"2022","journal-title":"NeurIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110244"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01097"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/189"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_44"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28575"},{"key":"ref61","first-page":"5191","article-title":"Decoder pretraining with only text for scene text recognition","author":"Zhao","year":"2024","journal-title":"ACM M M"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3512354"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01474"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/197"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01880-0"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681271"},{"key":"ref67","first-page":"1762","article-title":"Focus on the whole character: Discriminative character modeling for scene text recognition","author":"Zhou","year":"2024","journal-title":"IJCAI"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445475.pdf?arnumber=11445475","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:24:04Z","timestamp":1777613044000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445475\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01874","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}