{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T18:37:52Z","timestamp":1767983872149,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB3104700"],"award-info":[{"award-number":["2022YFB3104700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62121002, 62232006, 62102384"],"award-info":[{"award-number":["62121002, 62232006, 62102384"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612370","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"2006-2015","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Masked Text Modeling: A Self-Supervised Pre-training Method for Scene Text Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6807-5207","authenticated-orcid":false,"given":"Keran","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-5315","authenticated-orcid":false,"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0228-6220","authenticated-orcid":false,"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1237-7177","authenticated-orcid":false,"given":"Dongming","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Communication Content Cognition, People's Daily Online, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0265-5011","authenticated-orcid":false,"given":"Yadong","family":"Qu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0587-4167","authenticated-orcid":false,"given":"Zuan","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"e_1_3_2_1_2_1","volume-title":"Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254","author":"Bao Hangbo","year":"2021","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2021. Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_8_1","volume-title":"Abinet: Autonomous, bidirectional and iterative language modeling for scene text spotting","author":"Fang Shancheng","year":"2022","unstructured":"Shancheng Fang, Zhendong Mao, Hongtao Xie, Yuxin Wang, Chenggang Yan, and Yongdong Zhang. 2022. Abinet: Autonomous, bidirectional and iterative language modeling for scene text spotting. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240571"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00870"},{"key":"e_1_3_2_1_15_1","volume-title":"Milan: Masked image pretraining on language assisted representation. arXiv preprint arXiv:2208.06049","author":"Hou Zejiang","year":"2022","unstructured":"Zejiang Hou, Fei Sun, Yen-Kuang Chen, Yuan Xie, and Sun-Yuan Kung. 2022. Milan: Masked image pretraining on language assisted representation. arXiv preprint arXiv:2208.06049 (2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"ICDAR 2015 competition on robust reading. In 2015 13th international conference on document analysis and recognition (ICDAR). IEEE, 1156--1160","author":"Karatzas Dimosthenis","year":"2015","unstructured":"Dimosthenis Karatzas, Lluis Gomez-Bigorda, Anguelos Nicolaou, Suman Ghosh, Andrew Bagdanov, Masakazu Iwamura, Jiri Matas, Lukas Neumann, Vijay Ramaseshan Chandrasekhar, Shijian Lu, et al. 2015. ICDAR 2015 competition on robust reading. In 2015 13th international conference on document analysis and recognition (ICDAR). IEEE, 1156--1160."},{"key":"e_1_3_2_1_17_1","volume-title":"Textboxes: A single-shot oriented scene text detector","author":"Liao Minghui","year":"2018","unstructured":"Minghui Liao, Baoguang Shi, and Xiang Bai. 2018. Textboxes: A single-shot oriented scene text detector. IEEE transactions on image processing, Vol. 27, 8 (2018), 3676--3690."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3155612"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00788"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818020"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_12"},{"key":"e_1_3_2_1_25_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_26_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2910412"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01523"},{"key":"e_1_3_2_1_31_1","volume-title":"Seglink: Detecting dense and arbitrary-shaped scene text by instance-aware component grouping. Pattern recognition","author":"Tang Jun","year":"2019","unstructured":"Jun Tang, Zhibo Yang, Yongpan Wang, Qi Zheng, Yongchao Xu, and Xiang Bai. 2019. Seglink: Detecting dense and arbitrary-shaped scene text by instance-aware component grouping. Pattern recognition, Vol. 96 (2019), 106954."},{"key":"e_1_3_2_1_32_1","volume-title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling. arXiv preprint arXiv:2301.03580","author":"Tian Keyu","year":"2023","unstructured":"Keyu Tian, Yi Jiang, Qishuai Diao, Chen Lin, Liwei Wang, and Zehuan Yuan. 2023. Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling. arXiv preprint arXiv:2301.03580 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Coco-text: Dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140","author":"Veit Andreas","year":"2016","unstructured":"Andreas Veit, Tomas Matera, Lukas Neumann, Jiri Matas, and Serge Belongie. 2016. Coco-text: Dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140 (2016)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00592"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00956"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00853"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00661"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3197981"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_7"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3231737"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2900589"},{"key":"e_1_3_2_1_45_1","volume-title":"MSR: multi-scale shape regression for scene text detection. arXiv preprint arXiv:1901.02596","author":"Xue Chuhui","year":"2019","unstructured":"Chuhui Xue, Shijian Lu, and Wei Zhang. 2019. MSR: multi-scale shape regression for scene text detection. arXiv preprint arXiv:1901.02596 (2019)."},{"key":"e_1_3_2_1_46_1","volume-title":"Tel Aviv","author":"Xue Chuhui","year":"2022","unstructured":"Chuhui Xue, Wenqing Zhang, Yu Hao, Shijian Lu, Philip HS Torr, and Song Bai. 2022. Language matters: A weakly supervised vision-language pre-training approach for scene text detection and spotting. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXVIII. Springer, 284--302."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2353813"},{"key":"e_1_3_2_1_48_1","volume-title":"2012 IEEE conference on computer vision and pattern recognition. IEEE, 1083--1090","author":"Yao Cong","year":"2012","unstructured":"Cong Yao, Xiang Bai, Wenyu Liu, Yi Ma, and Zhuowen Tu. 2012. Detecting texts of arbitrary orientations in natural images. In 2012 IEEE conference on computer vision and pattern recognition. IEEE, 1083--1090."},{"key":"e_1_3_2_1_49_1","volume-title":"Large batch optimization for deep learning: Training bert in 76 minutes. arXiv preprint arXiv:1904.00962","author":"You Yang","year":"2019","unstructured":"Yang You, Jing Li, Sashank Reddi, Jonathan Hseu, Sanjiv Kumar, Srinadh Bhojanapalli, Xiaodan Song, James Demmel, Kurt Keutzer, and Cho-Jui Hsieh. 2019. Large batch optimization for deep learning: Training bert in 76 minutes. arXiv preprint arXiv:1904.00962 (2019)."},{"key":"e_1_3_2_1_50_1","volume-title":"Detecting curve text in the wild: New dataset and new solution. arXiv preprint arXiv:1712.02170","author":"Yuliang Liu","year":"2017","unstructured":"Liu Yuliang, Jin Lianwen, Zhang Shuaitao, and Zhang Sheng. 2017. Detecting curve text in the wild: New dataset and new solution. arXiv preprint arXiv:1712.02170 (2017)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01080"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00134"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"e_1_3_2_1_55_1","volume-title":"In Proceedings of the 28th ACM international conference on multimedia. 2571--2580","author":"Zhou Yu","year":"2020","unstructured":"Yu Zhou, Hongtao Xie, Shancheng Fang, Yan Li, and Yongdong Zhang. 2020. In Proceedings of the 28th ACM international conference on multimedia. 2571--2580."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612370","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:54:50Z","timestamp":1755820490000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612370"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":55,"alternative-id":["10.1145\/3581783.3612370","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612370","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}