{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:21:21Z","timestamp":1772907681706,"version":"3.50.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Joint Laboratory of CAS-HK"},{"name":"Shenzhen Research Program","award":["JSGG20191129141212311"],"award-info":[{"award-number":["JSGG20191129141212311"]}]},{"name":"Shenzhen Research Program","award":["RCJC20200714114557087"],"award-info":[{"award-number":["RCJC20200714114557087"]}]},{"name":"Shanghai Committee of Science and Technology","award":["21DZ1100100"],"award-info":[{"award-number":["21DZ1100100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3171108","type":"journal-article","created":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T20:20:31Z","timestamp":1651177231000},"page":"4094-4107","source":"Crossref","is-referenced-by-count":9,"title":["Dual Relation Network for Scene Text Recognition"],"prefix":"10.1109","volume":"25","author":[{"given":"Ming","family":"Li","sequence":"first","affiliation":[{"name":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1526-8654","authenticated-orcid":false,"given":"Bin","family":"Fu","sequence":"additional","affiliation":[{"name":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1813-1784","authenticated-orcid":false,"given":"Junjun","family":"He","sequence":"additional","affiliation":[{"name":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2567","authenticated-orcid":false,"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3015037"},{"key":"ref57","first-page":"1","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"jaderberg","year":"2014","journal-title":"Proc Workshop Deep Learn NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2978630"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/34.24792"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2625259"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2802644"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3045602"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref10","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representation"},{"key":"ref54","article-title":"Longformer: The long-document transformer","author":"beltagy","year":"2020","journal-title":"arXiv 2004 05150"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2353813"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941777"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3073575"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00685"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00254"},{"key":"ref46","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref47","first-page":"833","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2707805"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.11591\/ijece.v7i5.pp2496-2501"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2710-7"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3066903"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00035"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.543"},{"key":"ref37","first-page":"1251","article-title":"Xception: Deep learning with depthwise separable convolutions","author":"fran\u00e7ois","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref36","first-page":"1492","article-title":"Aggregated residual transformations for deep neural networks","author":"saining","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12252"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00163"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00730"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_27"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819223"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027724"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref38","article-title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","author":"howard","year":"2017"},{"key":"ref71","first-page":"2231","author":"lee","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12246"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/458"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00216"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.515"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12242"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"ref26","article-title":"Spatial Transformer Networks","volume":"28","author":"jaderberg","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00924"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298914"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3013376"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00481"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01369-0"},{"key":"ref65","article-title":"Adadelta: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3025696"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2952978"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00584"},{"key":"ref60","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09765383.pdf?arnumber=9765383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T19:45:59Z","timestamp":1699299959000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9765383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3171108","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}