{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T22:26:04Z","timestamp":1743546364371,"version":"3.28.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9411951","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"3130-3137","source":"Crossref","is-referenced-by-count":3,"title":["Stratified Multi-Task Learning for Robust Spotting of Scene Texts"],"prefix":"10.1109","author":[{"given":"Kinjal","family":"Dasgupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sudip","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ujjwal","family":"Bhattacharya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"67","article-title":"Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes","author":"lyu","year":"2018","journal-title":"ECCV"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00186"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00142"},{"key":"ref37","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","author":"chen","year":"2017","journal-title":"ArXiv"},{"key":"ref36","article-title":"Cluenet: A deep framework for occluded pedestrian pose estimation","author":"kishore","year":"2019","journal-title":"BMVC"},{"key":"ref35","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1631","DOI":"10.1109\/TPAMI.2003.1251157","article-title":"Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithm","volume":"25","author":"kim","year":"2003","journal-title":"TPAMI"},{"key":"ref40","first-page":"83","article-title":"Textnet: Irregular text reading from images with an end-to-end trainable network","author":"sun","year":"2018","journal-title":"ACCV"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref12","first-page":"1206","article-title":"FASText: Efficient unconstrained scene text detector","author":"busta","year":"2015","journal-title":"ICCV"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.19"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref15","article-title":"COCO-Text: Dataset and benchmark for text detection and recognition in natural images","author":"veit","year":"2016","journal-title":"ArXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.87"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019038"},{"key":"ref19","first-page":"20","article-title":"TextSnake: A flexible representation for detecting text of arbitrary shapes","author":"long","year":"2018","journal-title":"ECCV"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00924"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00480"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191102"},{"key":"ref29","first-page":"4161","article-title":"Textboxes: A fast text detector with a single deep neural network","author":"liao","year":"2017","journal-title":"AAAI"},{"key":"ref5","article-title":"A survey on multi-task learning","author":"zhang","year":"2017","journal-title":"ArXiv"},{"key":"ref8","first-page":"512","article-title":"Deep features for text spotting","author":"aderberg","year":"2014","journal-title":"ECCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-015-4488-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00595"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.74"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00661"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref22","article-title":"Multi-digit number recognition from street view imagery using deep convolutional neural networks","author":"goodfellow","year":"2013","journal-title":"ArXiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.516"},{"key":"ref42","first-page":"1083","article-title":"Detecting texts of arbitrary orientations in natural images","author":"yao","year":"2012","journal-title":"CVPR"},{"key":"ref24","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"aderberg","year":"2014","journal-title":"ArXiv"},{"key":"ref41","first-page":"1454","article-title":"ICDAR 2017 robust reading challenge on multi-lingual scene text detection and script identification-rrc-mlt","volume":"1","author":"nayef","year":"2017","journal-title":"ICDAR"},{"key":"ref23","first-page":"35","article-title":"Accurate scene text recognition based on recurrent neural network","author":"su","year":"2014","journal-title":"ACCV"},{"key":"ref44","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ArXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00788"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00216"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09411951.pdf?arnumber=9411951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:55Z","timestamp":1652197255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9411951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9411951","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}