{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T04:35:09Z","timestamp":1758083709731,"version":"3.44.0"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032046260"},{"type":"electronic","value":"9783032046277"}],"license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-04627-7_21","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:09:25Z","timestamp":1757988565000},"page":"362-381","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["E-FCOS: Enhanced Historical Text Detection with\u00a0Fast Fourier Transform Denoising and\u00a0Adaptive Multi-scale Fusion"],"prefix":"10.1007","author":[{"given":"Menghui","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanghui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingfeng","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"21_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109458","volume":"139","author":"M Bermudez-Gonzalez","year":"2025","unstructured":"Bermudez-Gonzalez, M., Jalali, A., Lee, M.: Dynamically adaptive deformable feature fusion for multi-scale character detection in ancient documents. Eng. Appl. Artif. Intell. 139, 109458 (2025). https:\/\/doi.org\/10.1016\/j.engappai.2024.109458","journal-title":"Eng. Appl. Artif. Intell."},{"key":"21_CR2","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-3-031-21648-0_30","volume-title":"ICFHR 2022","author":"H Cheng","year":"2022","unstructured":"Cheng, H., Jian, C., Wu, S., Jin, L.: SCUT-CAB: a new benchmark dataset of ancient Chinese books with complex layouts for document layout analysis. In: Porwal, U., Forn\u00e9s, A., Shafait, F. (eds.) ICFHR 2022. LNCS, vol. 13639, pp. 436\u2013451. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-21648-0_30"},{"key":"21_CR3","doi-asserted-by":"publisher","unstructured":"Chi, L., Jiang, B., Mu, Y.: Fast Fourier convolution. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 4479\u20134488 (2020). https:\/\/doi.org\/10.5555\/3495724.3496100","DOI":"10.5555\/3495724.3496100"},{"key":"21_CR4","doi-asserted-by":"publisher","unstructured":"Clanuwat, T., Lamb, A., Kitamoto, A.: Kuronet: pre-modern Japanese Kuzushiji character recognition with deep learning. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 607\u2013614 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00103","DOI":"10.1109\/ICDAR.2019.00103"},{"key":"21_CR5","doi-asserted-by":"publisher","unstructured":"Ding, X., Wen, D., Peng, L., Liu, C.: Document digitization technology and its application for digital library in China, pp. 46\u201353 (2004). https:\/\/doi.org\/10.1109\/DIAL.2004.1263236","DOI":"10.1109\/DIAL.2004.1263236"},{"issue":"3","key":"21_CR6","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1109\/18.382009","volume":"41","author":"DL Donoho","year":"2002","unstructured":"Donoho, D.L.: De-noising by soft-thresholding. IEEE Trans. Inf. Theory 41(3), 613\u2013627 (2002). https:\/\/doi.org\/10.1109\/18.382009","journal-title":"IEEE Trans. Inf. Theory"},{"key":"21_CR7","doi-asserted-by":"publisher","unstructured":"Du, Y., et\u00a0al.: PP-OCR: a practical ultra lightweight OCR system. arXiv preprint arXiv:2009.09941 (2020). https:\/\/doi.org\/10.48550\/arXiv.2009.09941","DOI":"10.48550\/arXiv.2009.09941"},{"key":"21_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/978-3-030-86159-9_4","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021 Workshops","author":"R Feng","year":"2021","unstructured":"Feng, R., Zhao, F., Chen, S., Zhang, S., Wang, D.: A handwritten text detection model based on cascade feature fusion network improved by FCOS. In: Barney Smith, E.H., Pal, U. (eds.) ICDAR 2021. LNCS, vol. 12917, pp. 51\u201365. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86159-9_4"},{"key":"21_CR9","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.patrec.2023.06.013","volume":"172","author":"R Feng","year":"2023","unstructured":"Feng, R., Zhao, F., Chen, S., Zhang, S., Zhu, S.: A handwritten ancient text detector based on improved feature pyramid network. Pattern Recogn. Lett. 172, 195\u2013202 (2023). https:\/\/doi.org\/10.1016\/j.patrec.2023.06.013","journal-title":"Pattern Recogn. Lett."},{"key":"21_CR10","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"21_CR11","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580\u2013587 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"21_CR12","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"21_CR13","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR14","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-031-70543-4_23","volume-title":"ICDAR 2024","author":"X Hu","year":"2024","unstructured":"Hu, X., Wei, B., Gao, L., Wang, J.: SegHist: a general segmentation-based framework for Chinese historical document text line detection. In: Barney Smith, E.H., Liwicki, M., Peng, L. (eds.) ICDAR 2024. LNCS, vol. 14806, pp. 391\u2013410. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-70543-4_23"},{"key":"21_CR15","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1016\/j.neunet.2022.12.023","volume":"160","author":"A Jalali","year":"2023","unstructured":"Jalali, A., Lee, M.: Adversarial Lagrangian integrated contrastive embedding for limited size datasets. Neural Netw. 160, 122\u2013131 (2023). https:\/\/doi.org\/10.1016\/j.neunet.2022.12.023","journal-title":"Neural Netw."},{"key":"21_CR16","doi-asserted-by":"publisher","unstructured":"Kuang, Z., et al.: MMOCR: a comprehensive toolbox for text detection, recognition and understanding. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3791\u20133794 (2021). https:\/\/doi.org\/10.1145\/3474085.3478328","DOI":"10.1145\/3474085.3478328"},{"key":"21_CR17","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/978-3-031-41676-7_22","volume-title":"ICDAR 2023","author":"H Li","year":"2023","unstructured":"Li, H., Liu, C., Wang, J., Huang, M., Zhou, W., Jin, L.: DTDT: highly accurate dense text line detection in historical documents via dynamic transformer. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14187, pp. 381\u2013396. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41676-7_22"},{"key":"21_CR18","doi-asserted-by":"publisher","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol.\u00a034, pp. 11474\u201311481 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6812","DOI":"10.1609\/aaai.v34i07.6812"},{"issue":"1","key":"21_CR19","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1109\/TPAMI.2022.3155612","volume":"45","author":"M Liao","year":"2022","unstructured":"Liao, M., Zou, Z., Wan, Z., Yao, C., Bai, X.: Real-time scene text detection with differentiable binarization and adaptive scale fusion. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 919\u2013931 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2022.3155612","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR20","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"21_CR21","doi-asserted-by":"publisher","unstructured":"Liu, J.J., Hou, Q., Cheng, M.M., Wang, C., Feng, J.: Improving convolutional networks with self-calibrated convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10096\u201310105 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01011","DOI":"10.1109\/CVPR42600.2020.01011"},{"key":"21_CR22","doi-asserted-by":"publisher","unstructured":"Liu, J., Ma, X., Wang, L., Pei, L.: How can generative artificial intelligence techniques facilitate intelligent research into ancient books? 17(4) (2024). https:\/\/doi.org\/10.1145\/3690391","DOI":"10.1145\/3690391"},{"key":"21_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-030-58601-0_6","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Liu","year":"2020","unstructured":"Liu, L., et al.: Wavelet-based dual-branch network for image demoir\u00e9ing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 86\u2013102. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_6"},{"key":"21_CR24","doi-asserted-by":"publisher","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8759\u20138768 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00913","DOI":"10.1109\/CVPR.2018.00913"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10012\u201310022 (2021). https:\/\/doi.org\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"21_CR26","doi-asserted-by":"publisher","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 3431\u20133440 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2016.2572683","DOI":"10.1109\/TPAMI.2016.2572683"},{"issue":"3","key":"21_CR27","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1007\/s10462-024-11095-5","volume":"58","author":"H Qi","year":"2025","unstructured":"Qi, H., Yang, H., Wang, Z., Ye, J., Xin, Q., Zhang, C., Lang, Q.: Ancientglyphnet: an advanced deep learning framework for detecting ancient Chinese characters in complex scene. Artif. Intell. Rev. 58(3), 88 (2025). https:\/\/doi.org\/10.1007\/s10462-024-11095-5","journal-title":"Artif. Intell. Rev."},{"issue":"6","key":"21_CR28","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-86549-8_28","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"A Scius-Bertrand","year":"2021","unstructured":"Scius-Bertrand, A., Jungo, M., Wolf, B., Fischer, A., Bui, M.: Annotation-free character detection in historical Vietnamese stele images. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 432\u2013447. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_28"},{"key":"21_CR30","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/978-3-031-41685-9_13","volume-title":"ICDAR 2023","author":"G Sfikas","year":"2023","unstructured":"Sfikas, G., Retsinas, G., Dimitrakopoulos, P., Gatos, B., Nikou, C.: Shared-operation hypercomplex networks for handwritten text recognition. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14190, pp. 200\u2013216. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41685-9_13"},{"key":"21_CR31","doi-asserted-by":"publisher","unstructured":"Shen, H., Zhao, Z.Q., Zhang, W.: Adaptive dynamic filtering network for image denoising. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol.\u00a037, pp. 2227\u20132235 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i2.25317","DOI":"10.1609\/aaai.v37i2.25317"},{"key":"21_CR32","doi-asserted-by":"publisher","first-page":"6767","DOI":"10.1609\/aaai.v37i2.25317","volume":"25","author":"Z Sheng","year":"2022","unstructured":"Sheng, Z., Liu, X., Cao, S.Y., Shen, H.L., Zhang, H.: Frequency-domain deep guided image denoising. IEEE Trans. Multimed. 25, 6767\u20136781 (2022). https:\/\/doi.org\/10.1609\/aaai.v37i2.25317","journal-title":"IEEE Trans. Multimed."},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Sundararajan, D.: The Discrete Fourier Transform: Theory, Algorithms and Applications. World Scientific (2001). https:\/\/doi.org\/ThediscreteFouriertransform:theory,algorithmsandapplications","DOI":"10.1142\/9789812810298"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10781\u201310790 (2020). https:\/\/doi.org\/CVPR42600.2020.01079","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"21_CR35","doi-asserted-by":"publisher","unstructured":"Tang, C.W., Liu, C.L., Chiu, P.S.: Hrcenternet: an anchorless approach to Chinese character segmentation in historical documents. In: 2020 IEEE International Conference on Big Data (Big Data), pp. 1924\u20131930. IEEE (2020). https:\/\/doi.org\/10.1109\/BigData50022.2020.9378051","DOI":"10.1109\/BigData50022.2020.9378051"},{"key":"21_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-86337-1_1","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"C-W Tang","year":"2021","unstructured":"Tang, C.-W., Liu, C.-L., Chiu, P.-S.: HRRegionNet: Chinese character segmentation in historical documents with regional awareness. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12824, pp. 3\u201317. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_1"},{"key":"21_CR37","doi-asserted-by":"publisher","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9626\u20139635 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00972","DOI":"10.1109\/ICCV.2019.00972"},{"key":"21_CR38","doi-asserted-by":"publisher","unstructured":"Varghese, R., Sambath, M.: YOLOv8: a novel object detection algorithm with enhanced performance and robustness. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), pp.\u00a01\u20136. IEEE (2024). https:\/\/doi.org\/10.1109\/ADICS58448.2024.10533619","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"21_CR39","doi-asserted-by":"publisher","unstructured":"Wang, P., Hu, Y., Peng, S., Zhou, L.: Emanet: an ancient text detection method based on enhanced-efficientnet and multi-dimensional scale fusion. IEEE Internet Things J. (2024). https:\/\/doi.org\/10.1109\/JIOT.2024.3423667","DOI":"10.1109\/JIOT.2024.3423667"},{"key":"21_CR40","doi-asserted-by":"publisher","unstructured":"Wang, W., Xie, E., Li, X., Hou, W., Lu, T., Yu, G., Shao, S.: Shape robust text detection with progressive scale expansion network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9336\u20139345 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00956","DOI":"10.1109\/CVPR.2019.00956"},{"key":"21_CR41","doi-asserted-by":"publisher","unstructured":"Wang, W., et al.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8439\u20138448 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00853","DOI":"10.1109\/ICCV.2019.00853"},{"key":"21_CR42","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.neucom.2019.04.001","volume":"350","author":"Z Xie","year":"2019","unstructured":"Xie, Z., et al.: Weakly supervised precise segmentation for historical document images. Neurocomputing 350, 271\u2013281 (2019). https:\/\/doi.org\/10.1016\/j.neucom.2019.04.001","journal-title":"Neurocomputing"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Xu, K., Qin, M., Sun, F., Wang, Y., Chen, Y.K., Ren, F.: Learning in the frequency domain. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1740\u20131749 (2020). https:\/\/doi.org\/CVPR42600.2020.00181","DOI":"10.1109\/CVPR42600.2020.00181"},{"key":"21_CR44","doi-asserted-by":"publisher","unstructured":"Yang, G., Lei, J., Zhu, Z., Cheng, S., Feng, Z., Liang, R.: AFPN: asymptotic feature pyramid network for object detection. In: 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2184\u20132189. IEEE (2023). https:\/\/doi.org\/10.1109\/TCSVT.2024.3376773","DOI":"10.1109\/TCSVT.2024.3376773"},{"key":"21_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlaseng.2022.107406","volume":"162","author":"J Yao","year":"2023","unstructured":"Yao, J., Jiang, Z., Lv, X., Peng, Q., Zhao, X., Song, L.: Adaptive Fourier single-pixel imaging based on directional energy continuity in high frequencies. Opt. Lasers Eng. 162, 107406 (2023). https:\/\/doi.org\/10.1016\/j.optlaseng.2022.107406","journal-title":"Opt. Lasers Eng."},{"key":"21_CR46","doi-asserted-by":"publisher","unstructured":"Ye, M., Zhang, J., Zhao, S., Liu, J., Du, B., Tao, D.: Dptext-detr: towards better scene text detection with dynamic points in transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 3241\u20133249 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i3.25430","DOI":"10.1609\/aaai.v37i3.25430"},{"issue":"14","key":"21_CR47","doi-asserted-by":"publisher","first-page":"25088","DOI":"10.1109\/JIOT.2024.3390943","volume":"11","author":"Z Yuan","year":"2024","unstructured":"Yuan, Z., Shi, C.: MGN-net: multigranularity graph fusion network in multimodal for scene text spotting. IEEE Internet Things J. 11(14), 25088\u201325098 (2024). https:\/\/doi.org\/10.1109\/JIOT.2024.3390943","journal-title":"IEEE Internet Things J."},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process. 26(7), 3142\u20133155 (2017). https:\/\/doi.org\/TIP.2017.2662206","DOI":"10.1109\/TIP.2017.2662206"},{"key":"21_CR49","doi-asserted-by":"publisher","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5551\u20135560 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.283","DOI":"10.1109\/CVPR.2017.283"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04627-7_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:09:33Z","timestamp":1757988573000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04627-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032046260","9783032046277"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04627-7_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"16 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}