{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T12:45:07Z","timestamp":1782391507066,"version":"3.54.5"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2018YFB1004600"],"award-info":[{"award-number":["2018YFB1004600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61703171"],"award-info":[{"award-number":["61703171"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61573160"],"award-info":[{"award-number":["61573160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2018CFB199"],"award-info":[{"award-number":["2018CFB199"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Program for Support of Top-Notch Young Professionals"},{"name":"Program for HUST Academic Frontier Youth Team"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2878899","type":"journal-article","created":{"date-parts":[[2018,10,31]],"date-time":"2018-10-31T19:04:19Z","timestamp":1541012659000},"page":"66322-66335","source":"Crossref","is-referenced-by-count":67,"title":["Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification"],"prefix":"10.1109","volume":"6","author":[{"given":"Xiang","family":"Bai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6078-6100","authenticated-orcid":false,"given":"Mingkun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengyuan","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7253-3151","authenticated-orcid":false,"given":"Yongchao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846317"},{"key":"ref72","author":"bahdanau","year":"2014","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76888-3_59"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref77","first-page":"77","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"14","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref74","author":"ba","year":"2014","journal-title":"Multiple object recognition with visual attention"},{"key":"ref39","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"2011","journal-title":"Proc IEEE Int Conf Comput Vis (ICCV)"},{"key":"ref75","author":"gregor","year":"2015","journal-title":"Draw A recurrent neural network for image generation"},{"key":"ref38","first-page":"770","article-title":"A method for text localization and recognition in real-world images","author":"neumann","year":"2010","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1109\/TIP.2010.2070803","article-title":"A hybrid approach to detect and localize texts in natural scene images","volume":"20","author":"pan","year":"2011","journal-title":"IEEE Trans Image Process"},{"key":"ref32","first-page":"591","article-title":"Word spotting in the wild","author":"wang","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref30","first-page":"366","article-title":"Detecting and reading text in natural scenes","volume":"2","author":"chen","year":"2004","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref37","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 (CVPR)"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1109\/TPAMI.2013.182","article-title":"Robust text detection in natural scene images","volume":"36","author":"yin","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"2594","DOI":"10.1109\/TIP.2011.2126586","article-title":"Text string detection from natural scenes by structure-based partition and grouping","volume":"20","author":"yi","year":"2011","journal-title":"IEEE Trans Image Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2010.04.002"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref61","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 Neural Inf Process Syst"},{"key":"ref63","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502197"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/s11042-010-0645-5","article-title":"Multimedia data mining: State of the art and challenges","author":"bhatt","year":"2011","journal-title":"Multimedia Tools and Applications"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2015.72"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-6515-6_9"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-014-0225-8"},{"key":"ref29","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1005"},{"key":"ref68","first-page":"1247","article-title":"Deep canonical correlation analysis","volume":"3","author":"andrew","year":"2013","journal-title":"Proc ICML"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2602938"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2375793"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2642781"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248364"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298880"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298995"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2724843"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.118"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.528"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2555080"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2015.12.001"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.04.027"},{"key":"ref53","first-page":"280","article-title":"Aggregating local context for accurate scene text detection","author":"he","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref52","author":"zhong","year":"2016","journal-title":"Deeptext A unified framework for text proposal generation and text detection in natural images"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2353813"},{"key":"ref12","first-page":"834","article-title":"Part-based R-CNNS for fine-grained category detection","author":"zhang","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.110"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2557071"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref16","first-page":"3122","article-title":"Unsupervised template learning for fine-grained object recognition","author":"yang","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref81","author":"mikolov","year":"2013","journal-title":"Efficient Estimation of Word Representations in Vector Space"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.81"},{"key":"ref84","author":"ioffe","year":"2015","journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift"},{"key":"ref18","first-page":"842","article-title":"The application of two-level attention models in deep convolutional neural network for fine-grained image classification","author":"xiao","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1561\/2000000039"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2531289"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2154317"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2520087"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366765"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2443556"},{"key":"ref85","author":"arevalo","year":"2017","journal-title":"Gated multimodal units for information fusion"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2638622"},{"key":"ref86","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/978-1-4615-5529-2_5","article-title":"Multitask learning","author":"caruana","year":"1998","journal-title":"Learning to Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-015-4488-0"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/s10032-015-0237-z","article-title":"Scene text extraction based on edges and support vector regression","volume":"18","author":"lu","year":"2015","journal-title":"Int J Document Anal Recognit"},{"key":"ref87","author":"jaderberg","year":"2014","journal-title":"Synthetic data and artificial neural networks for natural scene text recognition"},{"key":"ref88","article-title":"Torch7: A matlab-like environment for machine learning","author":"collobert","year":"2011","journal-title":"NIPS Workshop BigLearn"},{"key":"ref9","article-title":"TextBoxes: A fast text detector with a single deep neural network","author":"liao","year":"2017","journal-title":"Proc AAAI"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.157"},{"key":"ref47","first-page":"497","article-title":"Robust scene text detection with convolution neural network induced MSER trees","author":"huang","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref42","first-page":"3304","article-title":"End-to-end text recognition with convolutional neural networks","author":"wang","year":"2012","journal-title":"Proc Int Conf Pattern Recognit (ICPR)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.19"},{"key":"ref44","first-page":"512","article-title":"Deep features for text spotting","author":"jaderberg","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.102"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08517130.pdf?arnumber=8517130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T04:49:53Z","timestamp":1643258993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8517130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2878899","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}