{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:19:48Z","timestamp":1775578788790,"version":"3.50.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956488","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T14:34:13Z","timestamp":1669732453000},"page":"3238-3245","source":"Crossref","is-referenced-by-count":13,"title":["Arbitrary Shape Text Detection using Transformers"],"prefix":"10.1109","author":[{"given":"Zobeir","family":"Raisi","sequence":"first","affiliation":[{"name":"University of Waterloo,Waterloo,ON,Canada,N2L 3G1"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georges","family":"Younes","sequence":"additional","affiliation":[{"name":"University of Waterloo,Waterloo,ON,Canada,N2L 3G1"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Zelek","sequence":"additional","affiliation":[{"name":"University of Waterloo,Waterloo,ON,Canada,N2L 3G1"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"lorentz","year":"2013","journal-title":"Bernstein Polynomials"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/72"},{"key":"ref32","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00353"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref37","first-page":"770","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"Proc IEEE Comp Vision Pattern Recogn Conf (CVPR)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref28","article-title":"Are convolutional neural networks or transformers more like human vision?","author":"tuli","year":"2021","journal-title":"arXiv preprint arXiv 2105 07197"},{"key":"ref27","article-title":"Transformers are graph neural networks","author":"joshi","year":"2020","journal-title":"The Gra-dient"},{"key":"ref29","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"arXiv preprint arXiv 2005 12840"},{"key":"ref2","article-title":"Text detection and recognition in the wild: A review","author":"raisi","year":"2020","journal-title":"arXiv preprint arXiv 2006 04989"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01369-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"ref22","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref21","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv in Neural Info Process Sys"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref23","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Eur Conf on Comp Vision"},{"key":"ref26","article-title":"A survey on visual transformer","author":"han","year":"2020","journal-title":"2012 arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref10","first-page":"20","article-title":"Textsnake: A flexible representation for detecting text of arbitrary shapes","author":"long","year":"2018","journal-title":"Proc Eur Conf on Comp Vision (ECCV)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00853"},{"key":"ref40","article-title":"Generalized intersection over union","author":"rezatofighi","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00956"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01080"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2900589"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413819"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00314"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825107"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/s21030888"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2948405"},{"key":"ref49","first-page":"1083","article-title":"Detecting texts of arbitrary orientations in natural images","author":"yao","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00095"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00917"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"ref48","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv preprint arXiv 1711 05847"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"ref42","article-title":"Detecting curve text in the wild: New dataset and new solution","author":"yuliang","year":"2017","journal-title":"arXiv preprint arXiv 1712 02170"},{"key":"ref41","first-page":"935","article-title":"Total-text: A comprehensive dataset for scene text detection and recognition","volume":"1","author":"ch\u2019ng","year":"2017","journal-title":"Proc IAPR Int Conf on Document Anal and Recognit (ICDAR)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.236"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956488.pdf?arnumber=9956488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T15:06:09Z","timestamp":1671462369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956488\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956488","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}