{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:20:47Z","timestamp":1759332047861},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096434","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"source":"Crossref","is-referenced-by-count":8,"title":["A3S: Adversarial Learning of Semantic Representations for Scene-Text Spotting"],"prefix":"10.1109","author":[{"given":"Masato","family":"Fujitake","sequence":"first","affiliation":[{"name":"Fast Accounting Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"5676","article-title":"Fots: Fast oriented text spotting with a unified network","author":"liu","year":"2018","journal-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414739"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_15"},{"key":"ref14","first-page":"4593","article-title":"Swintextspotter: Scene text spotting via better synergy between text detection and text recognition","author":"huang","year":"2022","journal-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16348"},{"key":"ref1","first-page":"9519","article-title":"Text spotting transformers","author":"zhang","year":"2022","journal-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref17","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of NAACL-HLT"},{"key":"ref16","article-title":"Decoupling visual-semantic feature learning for robust scene text recognition","author":"cheng","year":"2021","journal-title":"arXiv preprint arXiv 2111 12372"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref18","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proceedings of International Conference on Neural Information Processing Systems"},{"key":"ref24","first-page":"936","article-title":"Feature pyramid networks for object detection","author":"lin","year":"2017","journal-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00334-z"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref25","first-page":"1582","article-title":"Ic-dar2019 robust reading challenge on multi-lingual scene text detection and recognition—rrc-mlt-2019","author":"nayef","year":"2019","journal-title":"Proc of the International Conference on Document Analysis and Recognition"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16383"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref8","first-page":"2642","article-title":"East: an efficient and accurate scene text detector","author":"zhou","year":"2017","journal-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref7","first-page":"1","article-title":"Label embedding for text recognition","author":"rodriguez-serrano","year":"2013","journal-title":"Proceedings of British Machine Vision Conference"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SMC52423.2021.9658799"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00917"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107437"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096434.pdf?arnumber=10096434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:59Z","timestamp":1700507279000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096434\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096434","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}