{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:19:51Z","timestamp":1775578791142,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R and D Program of China","award":["2020YFB1406704"],"award-info":[{"award-number":["2020YFB1406704"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025604"],"award-info":[{"award-number":["62025604"]}],"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":["61733007"],"award-info":[{"award-number":["61733007"]}],"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":["62072454"],"award-info":[{"award-number":["62072454"]}],"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":["U1936208"],"award-info":[{"award-number":["U1936208"]}],"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":["U1736219"],"award-info":[{"award-number":["U1736219"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["QYZDB-SSW-JSC003"],"award-info":[{"award-number":["QYZDB-SSW-JSC003"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4202084"],"award-info":[{"award-number":["4202084"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Peng Cheng Laboratory Project of Guangdong Province","award":["PCL2018KP004"],"award-info":[{"award-number":["PCL2018KP004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3073575","type":"journal-article","created":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T02:30:47Z","timestamp":1618540247000},"page":"1883-1895","source":"Crossref","is-referenced-by-count":40,"title":["Accurate Scene Text Detection Via Scale-Aware Data Augmentation and Shape Similarity Constraint"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6262-982X","authenticated-orcid":false,"given":"Pengwen","family":"Dai","sequence":"first","affiliation":[{"name":"State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"Algorithmics group at Delft University of Technology, Delft, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7627-4142","authenticated-orcid":false,"given":"Hua","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Jingzhi","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7141-708X","authenticated-orcid":false,"given":"Xiaochun","family":"Cao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref39","first-page":"6773","article-title":"PixelLink: Detecting scene text via instance segmentation","volume":"32","author":"deng","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01369-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019038"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947475"},{"key":"ref31","first-page":"1","article-title":"AB-LSTM: Atention-based bidirectional lstm model for scene text detection","volume":"15","author":"liu","year":"2019","journal-title":"ACM Trans Multimedia Comput Commun Appl"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350988"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01080"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2937086"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2952978"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2954218"},{"key":"ref60","article-title":"OpenImages: A public dataset for large-scale multi-label and multi-class image classification","author":"krasin","year":"2017"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref63","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","volume":"abs 1512 1274","author":"chen","year":"2015","journal-title":"CoRR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2900589"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00766"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/139"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2638622"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.331"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.87"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00661"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.529"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref51","first-page":"9333","article-title":"SNIPER: Efficient multi-scale training","author":"singh","year":"2018","journal-title":"” NeurIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.234"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref57","first-page":"1429","author":"shi","year":"0","journal-title":"Proc Int Conf Document Anal Recognit"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref55","first-page":"935","article-title":"Total-text: A. comprehensive dataset for scene text detection and recognition","volume":"1","author":"ch\u2019ngand","year":"0","journal-title":"Proc Int Conf Document Anal Recognit"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/280811.281026"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546066"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00436"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref13","first-page":"2612","article-title":"Feature enhancement network: A refined scene text detector","author":"zhang","year":"0","journal-title":"Proc Conf Artif Intell AAAI"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2625259"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2802644"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00619"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00788"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825107"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00150"},{"key":"ref4","first-page":"4161","article-title":"TextBoxes: A fast text detector with a single deep neural network","author":"liao","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00295"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00956"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00377"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_16"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00920"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00853"},{"key":"ref44","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"jaderberg","year":"0","journal-title":"Deep Learning Workshop"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00077"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09405411.pdf?arnumber=9405411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,9]],"date-time":"2022-05-09T19:58:52Z","timestamp":1652126332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9405411\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3073575","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}