{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:51:42Z","timestamp":1742935902540,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620630"},{"type":"electronic","value":"9789819620647"}],"license":[{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-2064-7_30","type":"book-chapter","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T19:24:06Z","timestamp":1735327446000},"page":"410-424","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SCLSTE: Semi-supervised Contrastive Learning-Guided Scene Text Editing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2272-1481","authenticated-orcid":false,"given":"Min","family":"Yin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7604-1410","authenticated-orcid":false,"given":"Liang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5906-1380","authenticated-orcid":false,"given":"HaoRan","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0870-8524","authenticated-orcid":false,"given":"Xing","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4495-8686","authenticated-orcid":false,"given":"Ben","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2077-9608","authenticated-orcid":false,"given":"RongHua","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? dataset and model analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4715\u20134723 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"issue":"9","key":"30_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3557999","volume":"55","author":"J Cao","year":"2023","unstructured":"Cao, J., Lam, K.Y., Lee, L.H., Liu, X., Hui, P., Su, X.: Mobile augmented reality: user interfaces, frameworks, and intelligence. ACM Comput. Surv. 55(9), 1\u201336 (2023)","journal-title":"ACM Comput. Surv."},{"key":"30_CR3","first-page":"26561","volume":"34","author":"H Chen","year":"2021","unstructured":"Chen, H., et al.: Artistic style transfer with internal-external learning and contrastive learning. Adv. Neural. Inf. Process. Syst. 34, 26561\u201326573 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Fragoso, V., Gauglitz, S., Zamora, S., Kleban, J., Turk, M.: Translatar: a mobile augmented reality translator. In: 2011 IEEE Workshop on Applications of Computer Vision (WACV), pp. 497\u2013502. IEEE (2011)","DOI":"10.1109\/WACV.2011.5711545"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Han, J., Shoeiby, M., Petersson, L., Armin, M.A.: Dual contrastive learning for unsupervised image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 746\u2013755 (2021)","DOI":"10.1109\/CVPRW53098.2021.00084"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"30_CR8","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"30_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Krishnan, P., Kovvuri, R., Pang, G., Vassilev, B., Hassner, T.: Textstylebrush: transfer of text aesthetics from a single example. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3239736"},{"key":"30_CR14","unstructured":"Lee, J., et al.: Rewritenet: reliable scene text editing with implicit decomposition of text contents and styles. arXiv preprint arXiv:2107.11041 (2021)"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Lin, Y., Zhang, S., Chen, T., Lu, Y., Li, G., Shi, Y.: Exploring negatives in contrastive learning for unpaired image-to-image translation. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1186\u20131194 (2022)","DOI":"10.1145\/3503161.3547802"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Nayef, N., et\u00a0al.: Icdar2017 robust reading challenge on multi-lingual scene text detection and script identification-rrc-mlt. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol.\u00a01, pp. 1454\u20131459. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.237"},{"key":"30_CR17","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"30_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-030-58545-7_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Park","year":"2020","unstructured":"Park, T., Efros, A.A., Zhang, R., Zhu, J.-Y.: Contrastive learning for unpaired image-to-image translation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 319\u2013345. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_19"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Qin, X., et al.: Mask is all you need: rethinking mask r-cnn for dense and arbitrary-shaped scene text detection. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 414\u2013423 (2021)","DOI":"10.1145\/3474085.3475178"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Qu, Y., Tan, Q., Xie, H., Xu, J., Wang, Y., Zhang, Y.: Exploring stroke-level modifications for scene text editing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2119\u20132127 (2023)","DOI":"10.1609\/aaai.v37i2.25305"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Roy, P., Bhattacharya, S., Ghosh, S., Pal, U.: Stefann: scene text editor using font adaptive neural network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13228\u201313237 (2020)","DOI":"10.1109\/CVPR42600.2020.01324"},{"key":"30_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-030-58621-8_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 776\u2013794. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_45"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Microast: towards super-fast ultra-resolution arbitrary style transfer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2742\u20132750 (2023)","DOI":"10.1609\/aaai.v37i3.25374"},{"key":"30_CR24","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Contrastive learning for compact single image dehazing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10551\u201310560 (2021)","DOI":"10.1109\/CVPR46437.2021.01041"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Wu, L., Zhang, C., Liu, J., Han, J., Liu, J., Ding, E., Bai, X.: Editing text in the wild. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1500\u20131508 (2019)","DOI":"10.1145\/3343031.3350929"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Xie, Y., Chen, X., Sun, L., Lu, Y.: Dg-font: Deformable generative networks for unsupervised font generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5130\u20135140 (2021)","DOI":"10.1109\/CVPR46437.2021.00509"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Yang, Q., Huang, J., Lin, W.: Swaptext: image based texts transfer in scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14700\u201314709 (2020)","DOI":"10.1109\/CVPR42600.2020.01471"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Yang, S., Liu, J., Wang, W., Guo, Z.: Tet-gan: text effects transfer via stylization and destylization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 1238\u20131245 (2019)","DOI":"10.1609\/aaai.v33i01.33011238"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Yang, S., Wang, Z., Wang, Z., Xu, N., Liu, J., Guo, Z.: Controllable artistic text style transfer via shape-matching gan. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4442\u20134451 (2019)","DOI":"10.1109\/ICCV.2019.00454"},{"key":"30_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/978-3-030-01237-3_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"F Zhan","year":"2018","unstructured":"Zhan, F., Lu, S., Xue, C.: Verisimilar image synthesis for accurate detection and recognition of texts in scenes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 257\u2013273. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_16"},{"key":"30_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Domain enhanced arbitrary image style transfer via contrastive learning. In: ACM SIGGRAPH 2022 Conference Proceedings, pp.\u00a01\u20138 (2022)","DOI":"10.1145\/3528233.3530736"},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: More deformable, better results. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9308\u20139316 (2019)","DOI":"10.1109\/CVPR.2019.00953"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2064-7_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T20:05:36Z","timestamp":1735329936000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2064-7_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,28]]},"ISBN":["9789819620630","9789819620647"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2064-7_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,28]]},"assertion":[{"value":"28 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}