{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:14:52Z","timestamp":1755839692391,"version":"3.37.3"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446874","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"4245-4249","source":"Crossref","is-referenced-by-count":2,"title":["Maskstr: Guide Scene Text Recognition Models with Masking"],"prefix":"10.1109","author":[{"given":"Baole","family":"Wei","sequence":"first","affiliation":[{"name":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghang","family":"He","sequence":"additional","affiliation":[{"name":"ByteDance Inc,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangcai","family":"Gao","sequence":"additional","affiliation":[{"name":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duoyou","family":"Zhou","sequence":"additional","affiliation":[{"name":"ByteDance Inc,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Tang","sequence":"additional","affiliation":[{"name":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Maskocr: Text recognition with masked encoder-decoder pretraining","year":"2022","author":"Lyu","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547784"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref16","first-page":"5","article-title":"Uber-text: A large-scale dataset for optical character recognition from street-level imagery","volume-title":"SUNw: Scene Understanding Workshop-CVPR","volume":"2017","author":"Zhang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446874.pdf?arnumber=10446874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:26:52Z","timestamp":1722576412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446874\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446874","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}