{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:11:36Z","timestamp":1773137496700,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62171135"],"award-info":[{"award-number":["62171135"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fujian Key Project","award":["2023XQ004"],"award-info":[{"award-number":["2023XQ004"]}]},{"name":"Fujian Eagle-Scholar and Distinguished Project","award":["2022J06010"],"award-info":[{"award-number":["2022J06010"]}]},{"name":"Fujian Natural Science Fund","award":["2024H6013"],"award-info":[{"award-number":["2024H6013"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3639908","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:43:18Z","timestamp":1764787398000},"page":"1523-1533","source":"Crossref","is-referenced-by-count":0,"title":["HAAP: Vision-Context Hierarchical Attention Autoregressive With Adaptive Permutation for Scene Text Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7127-9665","authenticated-orcid":false,"given":"Honghui","family":"Chen","sequence":"first","affiliation":[{"name":"College of Physics and Information Engineering, Fuzhou University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9706-4013","authenticated-orcid":false,"given":"Yuhang","family":"Qiu","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Monash University, Melbourne, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2243-786X","authenticated-orcid":false,"given":"Jiabao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Physics and Information Engineering, Fuzhou University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2876-653X","authenticated-orcid":false,"given":"Pingping","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Physics and Information Engineering, Fuzhou University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5741-7937","authenticated-orcid":false,"given":"Nam","family":"Ling","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Santa Clara University, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.421"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3233\/ATDE230010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183386"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3260648"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_26"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03728-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3512354"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02676"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298958"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00584"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"ref25","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"Jaderberg","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","first-page":"1","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_21"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00313"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146779"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171108"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3230962"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04241-5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102080"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20245"},{"key":"ref37","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":"ref38","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref40","article-title":"COCO-text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.233"},{"key":"ref42","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":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref48","first-page":"379","article-title":"Open images v5 text annotation and yet another mask text spotter","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Krylov","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3129651"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110244"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0434-y"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11275892.pdf?arnumber=11275892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:59:25Z","timestamp":1773086365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11275892\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3639908","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}