{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T22:39:19Z","timestamp":1782859159124,"version":"3.54.5"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62172256"],"award-info":[{"award-number":["62172256"]}],"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":["62202278"],"award-info":[{"award-number":["62202278"]}],"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":["62202272"],"award-info":[{"award-number":["62202272"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2019ZD06"],"award-info":[{"award-number":["ZR2019ZD06"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2020QF036"],"award-info":[{"award-number":["ZR2020QF036"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3350916","type":"journal-article","created":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T19:53:27Z","timestamp":1704743607000},"page":"6437-6448","source":"Crossref","is-referenced-by-count":6,"title":["VOLTER: Visual Collaboration and Dual-Stream Fusion for Scene Text Recognition"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7660-5724","authenticated-orcid":false,"given":"Jia-Nan","family":"Li","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2187-8598","authenticated-orcid":false,"given":"Xiao-Qian","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6901-5476","authenticated-orcid":false,"given":"Xin","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9972-7370","authenticated-orcid":false,"given":"Xin-Shun","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956029"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_26"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00481"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01467"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3440756"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-3005-5_43"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463639"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_18"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.1994.323794"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01411-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2364976"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2515997"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2863602"},{"key":"ref23","article-title":"TextSR: Content-aware text super-resolution guided by recognition","author":"Wang","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref25","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Jaderberg","year":"2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/34.24792"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00216"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3129651"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146779"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00584"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/124"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475238"},{"key":"ref34","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref35","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"Jaderberg","year":"2014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00313"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_10"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00035"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_19"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_20"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03728-5"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/189"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_28"},{"key":"ref47","first-page":"555","article-title":"Masked vision-language transformers for scene text recognition","author":"Wu","year":"2022","journal-title":"Proc. Brit. Mach. Vis. Conf."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref52","article-title":"COCO-Text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.233"},{"key":"ref54","first-page":"5","article-title":"Uber-text: A large-scale dataset for optical character recognition from street-level imagery","volume-title":"Proc. SUNw: Scene Understanding Workshop-CVPR","volume":"2017","author":"Zhang","year":"2017"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/icdar.2019.00254"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10382654.pdf?arnumber=10382654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T19:06:55Z","timestamp":1712862415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10382654\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3350916","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}