{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T10:26:59Z","timestamp":1761388019231,"version":"build-2065373602"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62170110"],"award-info":[{"award-number":["62170110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China under Grant","award":["62476088"],"award-info":[{"award-number":["62476088"]}]},{"DOI":"10.13039\/100018915","name":"Shanghai Automotive Industry Science and Technology Development Foundation","doi-asserted-by":"publisher","award":["2304"],"award-info":[{"award-number":["2304"]}],"id":[{"id":"10.13039\/100018915","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s00530-025-01910-6","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T11:05:16Z","timestamp":1755774316000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual attention transformer with adaptive frequency enhancement for real-world Chinese\u2013English scene text image super-resolution"],"prefix":"10.1007","volume":"31","author":[{"given":"Yanbin","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziming","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofeng","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"key":"1910_CR1","unstructured":"Dong, C., Zhu, X., Deng, Y., et\u00a0al.: Boosting optical character recognition: a super-resolution approach. arXiv preprint arXiv:1506.02211 (2015)"},{"key":"1910_CR2","unstructured":"Wang, W., Xie, E., Sun, P., et\u00a0al.: Textsr: content-aware text super-resolution guided by recognition. arXiv preprint arXiv:1909.07113 (2019)"},{"key":"1910_CR3","doi-asserted-by":"crossref","unstructured":"Mou, Y., Tan, L., Yang, H., et\u00a0al.: Plugnet: Degradation aware scene text recognition supervised by a pluggable super-resolution unit. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XV 16, Springer, pp 158\u2013174, (2020)","DOI":"10.1007\/978-3-030-58555-6_10"},{"key":"1910_CR4","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Liu, X., et\u00a0al.: Scene text image super-resolution in the wild. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part X 16, Springer, pp 650\u2013666, (2020)","DOI":"10.1007\/978-3-030-58607-2_38"},{"key":"1910_CR5","doi-asserted-by":"crossref","unstructured":"Ma, J., Liang, Z., Xiang, W., et\u00a0al.: A benchmark for chinese-english scene text image super-resolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 19452\u201319461 (2023)","DOI":"10.1109\/ICCV51070.2023.01782"},{"key":"1910_CR6","doi-asserted-by":"crossref","unstructured":"Dong, C., Loy, C.C., He, K., et\u00a0al.: Learning a deep convolutional network for image super-resolution. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV 13, Springer, pp 184\u2013199, (2014)","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"1910_CR7","doi-asserted-by":"crossref","unstructured":"Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14, Springer, pp 391\u2013407, (2016)","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"1910_CR8","doi-asserted-by":"crossref","unstructured":"Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1646\u20131654 (2016)","DOI":"10.1109\/CVPR.2016.182"},{"key":"1910_CR9","doi-asserted-by":"crossref","unstructured":"Zhou, C., Li, Q., Li, C., et\u00a0al.: A comprehensive survey on pretrained foundation models: A history from bert to chatgpt. arXiv preprint arXiv:2302.09419 (2023)","DOI":"10.1007\/s13042-024-02443-6"},{"key":"1910_CR10","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, (2017)"},{"key":"1910_CR11","doi-asserted-by":"crossref","unstructured":"Li, A., Zhang, L., Liu, Y., et\u00a0al.: Feature modulation transformer: Cross-refinement of global representation via high-frequency prior for image super-resolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 12514\u201312524, (2023)","DOI":"10.1109\/ICCV51070.2023.01150"},{"key":"1910_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, Y., Gu, J., et\u00a0al.: Dual aggregation transformer for image super-resolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12312\u201312321, (2023)","DOI":"10.1109\/ICCV51070.2023.01131"},{"key":"1910_CR13","unstructured":"Liu, Y., Zhang, Y., Wang, Y., et\u00a0al.: A survey of visual transformers. IEEE Trans. Neural Netw. Learn. Syst. (2023)"},{"key":"1910_CR14","doi-asserted-by":"crossref","unstructured":"Ray, A., Kumar, G., Kolekar, M.H.: Cfat: Unleashing triangular windows for image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 26120\u201326129, (2024)","DOI":"10.1109\/CVPR52733.2024.02468"},{"key":"1910_CR15","doi-asserted-by":"crossref","unstructured":"Liang, J., Cao, J., Sun, G., et\u00a0al.: Swinir: image restoration using Swin transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 1833\u20131844, (2021)","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"1910_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, K., Li, K., et\u00a0al.: Image super-resolution using very deep residual channel attention networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 286\u2013301, (2018)","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"1910_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109606","volume":"139","author":"S Moorthy","year":"2025","unstructured":"Moorthy, S., Sachin Sakthi, K.S., Arthanari, S., et al.: Hybrid multi-attention transformer for robust video object detection. Eng. Appl. Artif. Intell. 139, 109606 (2025)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"14","key":"1910_CR18","doi-asserted-by":"publisher","first-page":"2279","DOI":"10.3390\/math12142279","volume":"12","author":"SS Kuppusami Sakthivel","year":"2024","unstructured":"Kuppusami Sakthivel, S.S., Moorthy, S., Arthanari, S., et al.: Learning a context-aware environmental residual correlation filter via deep convolution features for visual object tracking. Mathematics 12(14), 2279 (2024)","journal-title":"Mathematics"},{"key":"1910_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2025.117305","volume":"136","author":"S Arthanari","year":"2025","unstructured":"Arthanari, S., Moorthy, S., Jeong, J.H., et al.: Adaptive spatially regularized target attribute-aware background suppressed deep correlation filter for object tracking. Signal Process. Image Commun. 136, 117305 (2025)","journal-title":"Signal Process. Image Commun."},{"key":"1910_CR20","doi-asserted-by":"crossref","unstructured":"Zhao, C., Feng, S., Zhao, B.N., et\u00a0al.: Scene text image super-resolution via parallelly contextual attention network. In: Proceedings of the 29th ACM International Conference on Multimedia, pp 2908\u20132917, (2021)","DOI":"10.1145\/3474085.3475469"},{"key":"1910_CR21","doi-asserted-by":"crossref","unstructured":"Chen, J., Li, B., Xue, X.: Scene text telescope: text-focused scene image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 12026\u201312035, (2021)","DOI":"10.1109\/CVPR46437.2021.01185"},{"key":"1910_CR22","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TIP.2023.3237002","volume":"32","author":"J Ma","year":"2023","unstructured":"Ma, J., Guo, S., Zhang, L.: Text prior guided scene text image super-resolution. IEEE Trans. Image Process. 32, 1341\u20131353 (2023)","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"1910_CR23","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1910_CR24","doi-asserted-by":"crossref","unstructured":"Ma, J., Liang, Z., Zhang, L.: A text attention network for spatial deformation robust scene text image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5911\u20135920, (2022)","DOI":"10.1109\/CVPR52688.2022.00582"},{"key":"1910_CR25","doi-asserted-by":"crossref","unstructured":"Li, X., Zuo, W., Loy, C.C.: Learning generative structure prior for blind text image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10103\u201310113, (2023)","DOI":"10.1109\/CVPR52729.2023.00974"},{"key":"1910_CR26","doi-asserted-by":"crossref","unstructured":"Liu, B., Yang, Z., Wang, P., et\u00a0al.: Textdiff: mask-guided residual diffusion models for scene text image super-resolution. arXiv preprint arXiv:2308.06743 (2023)","DOI":"10.2139\/ssrn.4818933"},{"key":"1910_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, J., Li, H., et\u00a0al.: Diffusion-based blind text image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 25827\u201325836, (2024)","DOI":"10.1109\/CVPR52733.2024.02440"},{"issue":"9","key":"1910_CR28","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., et al.: Aster: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2035\u20132048 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1910_CR29","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et\u00a0al.: Spatial transformer networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"1910_CR30","doi-asserted-by":"crossref","unstructured":"Fang, S., Xie, H., Wang, Y., et\u00a0al.: Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7098\u20137107, (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"1910_CR31","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, X., Li, B., et\u00a0al.: Chinese text recognition with a pre-trained clip-like model through image-ids aligning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 11943\u201311952, (2023)","DOI":"10.1109\/ICCV51070.2023.01097"},{"key":"1910_CR32","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, PMLR, pp. 8748\u20138763 (2021)"},{"key":"1910_CR33","doi-asserted-by":"crossref","unstructured":"Huang, J., Peng, D., Li, H., et\u00a0al.: Segctc: offline handwritten Chinese text recognition via better fusion between explicit and implicit segmentation. In: International Conference on Document Analysis and Recognition, Springer, pp. 332\u2013349, (2023)","DOI":"10.1007\/978-3-031-41685-9_21"},{"key":"1910_CR34","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"6","author":"J Canny","year":"1986","unstructured":"Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 6, 679\u2013698 (1986)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1910_CR35","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"1910_CR36","doi-asserted-by":"crossref","unstructured":"Timofte, R., Agustsson, E., Van\u00a0Gool, L., et\u00a0al.: Ntire 2017 challenge on single image super-resolution: Methods and results. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 114\u2013125, (2017)","DOI":"10.1109\/CVPRW.2017.150"},{"key":"1910_CR37","doi-asserted-by":"crossref","unstructured":"Lim, B., Son, S., Kim, H., et\u00a0al.: Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 136\u2013144 (2017)","DOI":"10.1109\/CVPRW.2017.151"},{"key":"1910_CR38","doi-asserted-by":"crossref","unstructured":"Bevilacqua, M., Roumy, A., Guillemot, C., et\u00a0al.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding (2012)","DOI":"10.5244\/C.26.135"},{"key":"1910_CR39","doi-asserted-by":"crossref","unstructured":"Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Curves and Surfaces: 7th International Conference, Avignon, France, June 24-30, 2010, Revised Selected Papers 7, Springer, pp 711\u2013730 (2012)","DOI":"10.1007\/978-3-642-27413-8_47"},{"key":"1910_CR40","doi-asserted-by":"crossref","unstructured":"Martin, D., Fowlkes, C., Tal, D., et\u00a0al.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, IEEE, pp. 416\u2013423, (2001)","DOI":"10.1109\/ICCV.2001.937655"},{"key":"1910_CR41","doi-asserted-by":"crossref","unstructured":"Huang, J.B., Singh, A., Ahuja, N.: Single image super-resolution from transformed self-exemplars. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5197\u20135206, (2015)","DOI":"10.1109\/CVPR.2015.7299156"},{"key":"1910_CR42","doi-asserted-by":"publisher","first-page":"21811","DOI":"10.1007\/s11042-016-4020-z","volume":"76","author":"Y Matsui","year":"2017","unstructured":"Matsui, Y., Ito, K., Aramaki, Y., et al.: Sketch-based manga retrieval using manga109 dataset. Multimedia Tools Appl. 76, 21811\u201321838 (2017)","journal-title":"Multimedia Tools Appl."},{"key":"1910_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, K., Wu, S., et\u00a0al.: Esrgan: enhanced super-resolution generative adversarial networks. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops, pp 0\u20130, (2018)","DOI":"10.1007\/978-3-030-11021-5_5"},{"key":"1910_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zeng, H., Guo, S., et\u00a0al.: Efficient long-range attention network for image super-resolution. In: European Conference on Computer Vision, Springer, pp 649\u2013667, (2022)","DOI":"10.1007\/978-3-031-19790-1_39"},{"key":"1910_CR45","doi-asserted-by":"crossref","unstructured":"Guo, H., Li, J., Dai, T., et\u00a0al.: Mambair: A simple baseline for image restoration with state-space model. In: European Conference on Computer Vision, Springer, pp 222\u2013241, (2025)","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"1910_CR46","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Husz\u00e1r, F., et\u00a0al.: Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4681\u20134690, (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"1910_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Li, Z., Guo, C.L., et\u00a0al.: Srformer: Permuted self-attention for single image super-resolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 12780\u201312791 (2023)","DOI":"10.1109\/ICCV51070.2023.01174"},{"key":"1910_CR48","doi-asserted-by":"crossref","unstructured":"Zheng, M., Sun, L., Dong, J., et\u00a0al.: Smfanet: a lightweight self-modulation feature aggregation network for efficient image super-resolution. In: European Conference on Computer Vision, Springer, pp 359\u2013375, (2024)","DOI":"10.1007\/978-3-031-72973-7_21"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01910-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01910-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01910-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T10:24:59Z","timestamp":1761387899000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01910-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":48,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["1910"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01910-6","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"assertion":[{"value":"1 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"This work does not involve experimental procedures with human subjects or animals.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent"}}],"article-number":"333"}}