{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:21:11Z","timestamp":1750220471023,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Nature Science Foundation of China","award":["62022076 U1936210"],"award-info":[{"award-number":["62022076 U1936210"]}]},{"name":"the Fundamental Research Funds for the Central Universities under Grant","award":["WK3480000011"],"award-info":[{"award-number":["WK3480000011"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475423","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T04:52:26Z","timestamp":1634532746000},"page":"2510-2518","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["TDI TextSpotter: Taking Data Imbalance into Account in Scene Text Spotting"],"prefix":"10.1145","author":[{"given":"Yu","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Shancheng","family":"Fang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Cloud & AI, Shenzhen, China"}]},{"given":"Zhengjun","family":"Zha","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"volume-title":"Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework. In IEEE International Conference on Computer Vision.","year":"2017","author":"Busta Michal","key":"e_1_3_2_2_1_1"},{"volume-title":"E2E-MLT-an unconstrained end-to-end method for multi-language scene text. arXiv preprint arXiv:1801.09919","year":"2018","author":"Michal Buvs","key":"e_1_3_2_2_2_1"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00334-z"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240571"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00917"},{"volume-title":"Convolutional sequence to sequence learning. arXiv preprint arXiv:1705.03122","year":"2017","author":"Gehring Jonas","key":"e_1_3_2_2_7_1"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"volume-title":"Synthetic Data for Text Localisation in Natural Images. In IEEE Conference on Computer Vision & Pattern Recognition.","year":"2016","author":"Gupta Ankush","key":"e_1_3_2_2_10_1"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"volume-title":"Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes","year":"2019","author":"Liao Minghui","key":"e_1_3_2_2_18_1"},{"volume-title":"Proceedings, Part XI 16","year":"2020","author":"Liao Minghui","key":"e_1_3_2_2_19_1"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825107"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298172"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00595"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2496234"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00480"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969250"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"volume-title":"Asian Conference on Computer Vision. Springer, 83--99","year":"2018","author":"Sun Yipeng","key":"e_1_3_2_2_30_1"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"volume-title":"2020 b. R-Net: A Relationship Network for Efficient and Accurate Scene Text Detection","year":"2020","author":"Wang Yuxin","key":"e_1_3_2_2_33_1"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3231737"},{"volume-title":"GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition. In The IEEE International Conference on Computer Vision (ICCV).","year":"2019","author":"Zhan Fangneng","key":"e_1_3_2_2_35_1"},{"volume-title":"Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes. arXiv preprint arXiv:1904.06535","year":"2019","author":"Zhang Chengquan","key":"e_1_3_2_2_36_1"},{"volume-title":"Deeptext: A unified framework for text proposal generation and text detection in natural images. arXiv preprint arXiv:1605.07314","year":"2016","author":"Zhong Zhuoyao","key":"e_1_3_2_2_37_1"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413565"}],"event":{"name":"MM '21: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Virtual Event China","acronym":"MM '21"},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475423","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:32Z","timestamp":1750193312000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475423"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":38,"alternative-id":["10.1145\/3474085.3475423","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475423","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}