{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T21:07:18Z","timestamp":1773436038977,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2017,3,1]],"date-time":"2017-03-01T00:00:00Z","timestamp":1488326400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2017,3,1]],"date-time":"2017-03-01T00:00:00Z","timestamp":1488326400000},"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":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7952435","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T17:35:36Z","timestamp":1497980136000},"page":"1642-1646","source":"Crossref","is-referenced-by-count":0,"title":["Deep salience map guided arbitrary direction scene text recognition"],"prefix":"10.1109","author":[{"given":"Xinhao","family":"Liu","sequence":"first","affiliation":[{"name":"NTT Corporation, Kanagawa, Japan 243-0198"}]},{"given":"Takahito","family":"Kawanishi","sequence":"additional","affiliation":[{"name":"NTT Corporation, Kanagawa, Japan 243-0198"}]},{"given":"Xiaomeng","family":"Wu","sequence":"additional","affiliation":[{"name":"NTT Corporation, Kanagawa, Japan 243-0198"}]},{"given":"Kaoru","family":"Hiramatsu","sequence":"additional","affiliation":[{"name":"NTT Corporation, Kanagawa, Japan 243-0198"}]},{"given":"Kunio","family":"Kashino","sequence":"additional","affiliation":[{"name":"NTT Corporation, Kanagawa, Japan 243-0198"}]}],"member":"263","reference":[{"key":"ref10","first-page":"512","article-title":"Deep features for text spotting","author":"jaderberg","year":"2014","journal-title":"ECCV"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471891"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10465","article-title":"Reading scene text in deep convolutional sequences","author":"he","year":"2016","journal-title":"AAAI"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref14","first-page":"181","article-title":"Perspective scene text recognition with feature compression and ranking","author":"zhou","year":"2014","journal-title":"ACCV"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref18","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.451"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.515"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.186"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298914"},{"key":"ref8","article-title":"End-to-end text recognition with hybrid HMM maxout models","author":"alsharif","year":"2014","journal-title":"ICLRE"},{"key":"ref7","first-page":"3304","article-title":"End-to-end text recognition with convolutional neural networks","author":"wang","year":"2012","journal-title":"ICPR"},{"key":"ref2","first-page":"591","article-title":"Word spotting in the wild","author":"wang","year":"2010","journal-title":"ECCV"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.102"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/s10032-004-0134-3","article-title":"ICDAR 2003 robust reading competitions: entries, results, and future directions","volume":"7","author":"lucas","year":"2005","journal-title":"International Journal of Document Analysis and Recognition (IJDAR)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"2011","journal-title":"ICCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.381"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref26","first-page":"1083","article-title":"Detecting texts of arbitrary orientations in natural images","author":"yao","year":"2012","journal-title":"CVPR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"}],"event":{"name":"ICASSP 2017 - 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"New Orleans, LA, USA","start":{"date-parts":[[2017,3,5]]},"end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07952435.pdf?arnumber=7952435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T19:51:51Z","timestamp":1773431511000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7952435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7952435","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}