{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:53:11Z","timestamp":1740102791142,"version":"3.37.3"},"reference-count":23,"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"}]},{"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"}]},{"DOI":"10.13039\/501100010450","name":"Nova","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010450","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\/icassp48485.2024.10446176","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"2720-2724","source":"Crossref","is-referenced-by-count":0,"title":["Read, Spell and Repeat: Scene Text Recognition with Vision-Language Circular Refinement"],"prefix":"10.1109","author":[{"given":"Taiwei","family":"Zhang","sequence":"first","affiliation":[{"name":"Beihang University,Hangzhou Innovation Institute,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenghui","family":"Hu","sequence":"additional","affiliation":[{"name":"Beihang University,Hangzhou Innovation Institute,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixin","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University,Hangzhou Innovation Institute,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingjie","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University,Hangzhou Innovation Institute,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University,Hangzhou Innovation Institute,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20245"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/124"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_20"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054269"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054135"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00035"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19971"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_19"},{"article-title":"Synthetic data and artificial neural networks for natural scene text recognition","year":"2014","author":"Jaderberg","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2011.6126402"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"}],"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\/10446176.pdf?arnumber=10446176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:05:42Z","timestamp":1722575142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446176","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}