{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:04:29Z","timestamp":1761897869934,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":40,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62277011"],"award-info":[{"award-number":["62277011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0108003"],"award-info":[{"award-number":["2020AAA0108003"]}],"id":[{"id":"10.13039\/501100012166","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\/3581783.3612174","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"4546-4554","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Self-Supervised Cross-Language Scene Text Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7252-4207","authenticated-orcid":false,"given":"Fuxiang","family":"Yang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8869-1664","authenticated-orcid":false,"given":"Tonghua","family":"Su","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology & Chongqing Research Institute of Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1594-5173","authenticated-orcid":false,"given":"Xiang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2270-3378","authenticated-orcid":false,"given":"Donglin","family":"Di","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9084-7373","authenticated-orcid":false,"given":"Zhongjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7892-8242","authenticated-orcid":false,"given":"Songze","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"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\/ICDAR.2019.00083"},{"key":"e_1_3_2_1_2_1","first-page":"4479","article-title":"Fast Fourier Convolution","volume":"33","author":"Chi Lu","year":"2020","unstructured":"Lu Chi, Borui Jiang, and Yadong Mu. 2020. Fast Fourier Convolution. In Advances in Neural Information Processing Systems, Vol. 33. 4479--4488.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","volume-title":"ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT. In International Conference on Document Analysis and Recognition. 1571--1576","author":"Chng Chee Kheng","year":"2019","unstructured":"Chee Kheng Chng, Yuliang Liu, Yipeng Sun, et al. 2019. ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT. In International Conference on Document Analysis and Recognition. 1571--1576."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00438"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550070"},{"key":"e_1_3_2_1_6_1","volume-title":"ICDAR2017 robust reading challenge on COCO-Text. In International Conference on Document Analysis and Recognition","volume":"1","author":"Gomez Raul","year":"2017","unstructured":"Raul Gomez, Baoguang Shi, Lluis Gomez, Lukas Numann, Andreas Veit, Jiri Matas, Serge Belongie, and Dimosthenis Karatzas. 2017. ICDAR2017 robust reading challenge on COCO-Text. In International Conference on Document Analysis and Recognition, Vol. 1. 1435--1443."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_8_1","unstructured":"Martin Heusel Hubert Ramsauer Thomas Unterthiner Bernhard Nessler and Sepp Hochreiter. 2017. GANs trained by a two time-scale update rule converge to a local nash equilibrium. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_9_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In Advances in Neural Information Processing Systems, Vol. 33. 6840--6851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_2_1_12_1","volume-title":"Content and style aware generation of text-line images for handwriting recognition","author":"Kang Lei","year":"2021","unstructured":"Lei Kang, Pau Riba, Marcal Rusinol, Alicia Forn\u00e9s, and Mauricio Villegas. 2021. Content and style aware generation of text-line images for handwriting recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_17"},{"key":"e_1_3_2_1_14_1","volume-title":"ICDAR 2015 competition on robust reading. In International Conference on Document Analysis and Recognition. 1156--1160","author":"Karatzas Dimosthenis","year":"2015","unstructured":"Dimosthenis Karatzas, Lluis Gomez-Bigorda, Anguelos Nicolaou, et al. 2015. ICDAR 2015 competition on robust reading. In International Conference on Document Analysis and Recognition. 1156--1160."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_16_1","volume-title":"Textstylebrush: Transfer of text aesthetics from a single example","author":"Krishnan Praveen","year":"2023","unstructured":"Praveen Krishnan, Rama Kovvuri, Guan Pang, Boris Vassilev, and Tal Hassner. 2023. Textstylebrush: Transfer of text aesthetics from a single example. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Hyeonsu Lee and Chankyu Choi. 2022. The Surprisingly Straightforward Scene Text Removal Method with Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis. In European Conference on Computer Vision. 457--472.","DOI":"10.1007\/978-3-031-19787-1_26"},{"key":"e_1_3_2_1_18_1","volume-title":"RewriteNet: Realistic Scene Text Image Generation via Editing Text in Real-world Image. arXiv preprint arXiv:2107.11041","author":"Lee Junyeop","year":"2021","unstructured":"Junyeop Lee, Yoonsik Kim, Seonghyeon Kim, Moonbin Yim, Seung Shin, Gayoung Lee, and Sungrae Park. 2021. RewriteNet: Realistic Scene Text Image Generation via Editing Text in Real-world Image. arXiv preprint arXiv:2107.11041 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00048"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70139-4"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3018859"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.181"},{"key":"e_1_3_2_1_23_1","volume-title":"Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"e_1_3_2_1_25_1","volume-title":"ICDAR2017 Robust Reading Challenge on Multi-Lingual Scene Text Detection and Script Identification - RRC-MLT. 1454--1459","author":"Nayef Nibal","year":"2017","unstructured":"Nibal Nayef, Fei Yin, Imen Bizid, Hyunsoo Choi, Yuan Feng, Dimosthenis Karatzas, Zhenbo Luo, Umapada Pal, Christophe Rigaud, Joseph Chazalon, Wafa Khlif, Muhammad Muzzamil Luqman, Jean-Christophe Burie, Cheng-lin Liu, and Jean-Marc Ogier. 2017. ICDAR2017 Robust Reading Challenge on Multi-Lingual Scene Text Detection and Script Identification - RRC-MLT. 1454--1459."},{"key":"e_1_3_2_1_26_1","volume-title":"International Conference on Machine Learning. 8162--8171","author":"Nichol Alexander Quinn","year":"2021","unstructured":"Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In International Conference on Machine Learning. 8162--8171."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25305"},{"key":"e_1_3_2_1_29_1","volume-title":"Palette: Image-to-Image Diffusion Models. In ACM SIGGRAPH 2022 Conference Proceedings. 1--10","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Huiwen Chang, Chris Lee, Jonathan Ho, Tim Salimans, David Fleet, and Mohammad Norouzi. 2022. Palette: Image-to-Image Diffusion Models. In ACM SIGGRAPH 2022 Conference Proceedings. 1--10."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations.","author":"Simonyan K.","key":"e_1_3_2_1_31_1","unstructured":"K. Simonyan and A. Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Machine Learning. 2256--2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning. 2256--2265."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00016"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350929"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00509"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01471"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.02.045"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301801"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612174","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:06:19Z","timestamp":1755821179000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612174"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":40,"alternative-id":["10.1145\/3581783.3612174","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612174","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"}}]}}