{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T13:08:36Z","timestamp":1752671316536,"version":"3.28.0"},"reference-count":49,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/bigdata.2018.8622129","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T22:07:18Z","timestamp":1548367638000},"page":"2373-2382","source":"Crossref","is-referenced-by-count":10,"title":["A unified scheme of text localization and structured data extraction for joint OCR and data mining"],"prefix":"10.1109","author":[{"given":"Yibin","family":"Ye","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenggao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yezhang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dandan","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lanjun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Spatial transformer modules","year":"2016","author":"jaderberg","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.87"},{"key":"ref30","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":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"ref34","first-page":"56","article-title":"Detecting text in natural image with connectionist text proposal network","author":"tian","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.19"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.157"},{"key":"ref29","first-page":"512","article-title":"Deep features for text spotting","author":"jaderberg","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1147\/JRD.2012.2184356","article-title":"Introduction to ”this is watson","volume":"56","author":"ferrucci","year":"2012","journal-title":"IBM Journal of Research and Development"},{"key":"ref1","first-page":"3","article-title":"Toward an architecture for never-ending language learning","volume":"5","author":"carlson","year":"2010","journal-title":"AAAI"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872799"},{"key":"ref22","first-page":"82","article-title":"New indices for text: Pat trees and pat arrays","volume":"66","author":"gonnet","year":"1992","journal-title":"Information Retrieval Data Structures & Algorithms"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CIMCA.2005.1631550"},{"key":"ref24","first-page":"109","article-title":"Roadrunner: Towards automatic data extraction from large web sites","volume":"1","author":"crescenzi","year":"2001","journal-title":"VLDB"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372182"},{"key":"ref26","article-title":"Focal loss for dense object detection","author":"lin","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1007\/3-540-45728-3_14","article-title":"Discovery of frequent word sequences in text","author":"ahonen-myka","year":"2002","journal-title":"Pattern Detection and Discovery"},{"key":"ref10","first-page":"497","article-title":"Robust scene text detection with convolution neural network induced mser trees","author":"huang","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388210"},{"key":"ref40","first-page":"35","article-title":"Accurate scene text recognition based on recurrent neural network","author":"su","year":"2014","journal-title":"Asian Conference on Computer Vision"},{"key":"ref12","first-page":"1206","article-title":"Fastext: Efficient unconstrained scene text detector","author":"busta","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366765"},{"key":"ref14","first-page":"886","article-title":"Histograms of oriented gradients for human detection","volume":"1","author":"dalal","year":"2005","journal-title":"Computer Vision and Pattern Recognition 2005 CVPR 2005 IEEE Computer Society Conference on"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.01.009"},{"key":"ref16","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"liu","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.9790\/0661-16351821"},{"key":"ref19","first-page":"262","article-title":"Overview of predictive and descriptive data mining techniques","volume":"5","author":"sondwale","year":"2015","journal-title":"International Journal of Advanced Research in Computer Science and Software Engineering"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.451"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700826"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.528"},{"article-title":"Accurate text localization in natural image with cascaded convolutional text network","year":"2016","author":"he","key":"ref8"},{"key":"ref7","first-page":"3501","article-title":"Reading scene text in deep convolutional sequences","volume":"16","author":"he","year":"2016","journal-title":"AAAI"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.143"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref46","first-page":"1453","article-title":"Online incremental feature learning with denoising autoencoders","author":"zhou","year":"2012","journal-title":"Artificial Intelligence and Statistics"},{"article-title":"Efficient estimation of word representations in vector space","year":"2013","author":"mikolov","key":"ref45"},{"key":"ref48","first-page":"4161","article-title":"Textboxes: A fast text detector with a single deep neural network","author":"liao","year":"2017","journal-title":"AAAI"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1111\/j.1756-8765.2010.01109.x"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WiSPNET.2016.7566241"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1220835.1220874"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390256"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333766"}],"event":{"name":"2018 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2018,12,10]]},"location":"Seattle, WA, USA","end":{"date-parts":[[2018,12,13]]}},"container-title":["2018 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8610059\/8621858\/08622129.pdf?arnumber=8622129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T18:35:03Z","timestamp":1643222103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8622129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/bigdata.2018.8622129","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}