{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:41:53Z","timestamp":1758123713141,"version":"3.37.3"},"reference-count":55,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076100","61976094","62276072"],"award-info":[{"award-number":["62076100","61976094","62276072"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangxi Natural Science Foundation","award":["2022GXNSFAA035627"],"award-info":[{"award-number":["2022GXNSFAA035627"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005015","name":"South China University of Technology","doi-asserted-by":"publisher","award":["D2210010","D2200150","D2201300"],"award-info":[{"award-number":["D2210010","D2200150","D2201300"]}],"id":[{"id":"10.13039\/501100005015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2020B0101100002"],"award-info":[{"award-number":["2020B0101100002"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3219642","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T21:19:44Z","timestamp":1667596784000},"page":"7208-7221","source":"Crossref","is-referenced-by-count":8,"title":["Scene-Text Oriented Referring Expression Comprehension"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2158-8750","authenticated-orcid":false,"given":"Yuqi","family":"Bu","sequence":"first","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liuwu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-7879","authenticated-orcid":false,"given":"Jiayuan","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6410-615X","authenticated-orcid":false,"given":"Qiong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-789X","authenticated-orcid":false,"given":"Yi","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7691-347X","authenticated-orcid":false,"given":"Qingbao","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Institute of Artificial Intelligence, Guangxi University, Nanning, Guangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"103","article-title":"Generating racing game commentary from vision, language, and structured data","author":"ishigaki","year":"0","journal-title":"Proc 14th Int Conf Natural Lang Gener"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33885-4_46"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/S0926-907X(05)80003-0","article-title":"Eye movements and cognitive processes in reading, visual search, and scene perception","volume":"6","author":"rayner","year":"1995","journal-title":"Studies in Visual Information Processing"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8279.1969.tb02040.x"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2638622"},{"article-title":"PP-OCR: A practical ultra lightweight OCR system","year":"2020","author":"du","key":"ref55"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412077"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_43"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2299799"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01117"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59006-2_8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248048"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00537"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539981"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2123"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919897133"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460699"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120194"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01276"},{"article-title":"Coco-text: Dataset and benchmark for text detection and recognition in natural images","year":"2016","author":"veit","key":"ref40"},{"article-title":"Yolov3: An incremental improvement","year":"2018","author":"redmon","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3018491"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1109\/TPAMI.2007.1078","article-title":"A normalized levenshtein distance metric","volume":"29","author":"li","year":"2007","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref36","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00227"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2930176"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.349"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19309-5_55"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475629"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01245"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2811621"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00136"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00453"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09939075.pdf?arnumber=9939075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T20:19:26Z","timestamp":1702325966000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9939075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3219642","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2023]]}}}