{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T13:03:15Z","timestamp":1783688595394,"version":"3.55.0"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032046161","type":"print"},{"value":"9783032046178","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"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\/978-3-032-04617-8_15","type":"book-chapter","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T11:46:14Z","timestamp":1757936774000},"page":"253-272","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Lightweight Context-Driven Training-Free Network for\u00a0Scene Text Segmentation and\u00a0Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3597-3703","authenticated-orcid":false,"given":"Ritabrata","family":"Chakraborty","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9026-4613","authenticated-orcid":false,"given":"Palaiahnakote","family":"Shivakumara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5426-2618","authenticated-orcid":false,"given":"Umapada","family":"Pal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6743-4175","authenticated-orcid":false,"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,15]]},"reference":[{"key":"15_CR1","doi-asserted-by":"publisher","unstructured":"Atienza, R.: Vision transformer for fast and efficient scene text recognition. In: Document Analysis and Recognition \u2013 ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part I, pp. 319\u2013334. Springer, Heidelberg (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_21","DOI":"10.1007\/978-3-030-86549-8_21"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"15_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1007\/978-3-030-58526-6_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Baek","year":"2020","unstructured":"Baek, Y., Shin, S., Baek, J., Park, S., Lee, J., Nam, D., Lee, H.: Character region attention for text spotting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 504\u2013521. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58526-6_30"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Banerjee, A., Palaiahnakote, S., Pal, U., Antonacopoulos, A., Lu, T., Canet, J.L.: Tts: Hilbert transform-based generative adversarial network for tattoo and scene text spotting. IEEE Trans. Multimed. (2024)","DOI":"10.1109\/TMM.2024.3378458"},{"key":"15_CR5","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/978-3-031-19815-1_11","volume-title":"Computer Vision - ECCV 2022","author":"D Bautista","year":"2022","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, pp. 178\u2013196. Springer, Cham (2022)"},{"issue":"13","key":"15_CR6","doi-asserted-by":"publisher","first-page":"3426","DOI":"10.1049\/ipr2.12574","volume":"16","author":"P Blanco-Medina","year":"2022","unstructured":"Blanco-Medina, P., Fidalgo, E., Alegre, E., Gonz\u00e1lez-Castro, V.: A survey on methods, datasets and implementations for scene text spotting. IET Image Proc. 16(13), 3426\u20133445 (2022). https:\/\/doi.org\/10.1049\/ipr2.12574","journal-title":"IET Image Proc."},{"key":"15_CR7","unstructured":"Bonechi, S., Andreini, P., Bianchini, M., Scarselli, F.: Coco_ts dataset: Pixel-level annotations based on weak supervision for scene text segmentation. CoRR abs\/1904.00818 (2019). http:\/\/arxiv.org\/abs\/1904.00818"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Busta, M., Neumann, L., Matas, J.: Deep textspotter: An end-to-end trainable scene text localization and recognition framework. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2204\u20132212 (2017)","DOI":"10.1109\/ICCV.2017.242"},{"key":"15_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"15_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"15_CR11","doi-asserted-by":"publisher","unstructured":"Chen, X., Jin, L., Zhu, Y., Luo, C., Wang, T.: Text recognition in the wild: a survey. ACM Comput. Surv. 54(2), March 2021. https:\/\/doi.org\/10.1145\/3440756","DOI":"10.1145\/3440756"},{"key":"15_CR12","doi-asserted-by":"publisher","unstructured":"Ch\u2019ng, C.K., Chan, C.S.: Total-text: A comprehensive dataset for scene text detection and recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a001, pp. 935\u2013942 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.157","DOI":"10.1109\/ICDAR.2017.157"},{"issue":"2","key":"15_CR13","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1109\/34.982903","volume":"24","author":"G Desouza","year":"2002","unstructured":"Desouza, G., Kak, A.: Vision for mobile robot navigation: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 24(2), 237\u2013267 (2002). https:\/\/doi.org\/10.1109\/34.982903","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR14","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv abs\/2010.11929 (2020). https:\/\/api.semanticscholar.org\/CorpusID:225039882"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Fang, S., Xie, H., Wang, Y., Mao, Z., Zhang, Y.: Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7094\u20137103 (2021). https:\/\/api.semanticscholar.org\/CorpusID:232185272","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Feng, W., He, W., Yin, F., Zhang, X.Y., Liu, C.L.: Textdragon: an end-to-end framework for arbitrary shaped text spotting. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9075\u20139084 (2019), https:\/\/api.semanticscholar.org\/CorpusID:207978383","DOI":"10.1109\/ICCV.2019.00917"},{"key":"15_CR17","unstructured":"Google Cloud: Cloud Vision API Documentation (2025). https:\/\/cloud.google.com\/vision\/docs. Accessed 12 Mar 2025"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"15_CR19","doi-asserted-by":"publisher","unstructured":"Hao, W., et al.: All you need is boundary: Toward arbitrary-shaped text spotting. In: Proceedings of the AAAI Conference on Artificial Intelligence 34, 12160\u201312167 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6896","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn (2018). https:\/\/arxiv.org\/abs\/1703.06870","DOI":"10.1109\/ICCV.2017.322"},{"key":"15_CR21","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015). https:\/\/arxiv.org\/abs\/1512.03385"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Huang, M., et al.: Swintextspotter: scene text spotting via better synergy between text detection and text recognition. arXiv preprint arXiv:2203.10209 (2022)","DOI":"10.1109\/CVPR52688.2022.00455"},{"key":"15_CR23","unstructured":"Huang, M., et al.: Swintextspotter v2: towards better synergy for scene text spotting (2024). https:\/\/arxiv.org\/abs\/2401.07641"},{"key":"15_CR24","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37, pp. 448\u2013456. ICML\u201915, JMLR.org (2015)"},{"key":"15_CR25","doi-asserted-by":"publisher","unstructured":"Jadon, S.: A survey of loss functions for semantic segmentation. In: 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), pp.\u00a01\u20137 (2020). https:\/\/doi.org\/10.1109\/CIBCB48159.2020.9277638","DOI":"10.1109\/CIBCB48159.2020.9277638"},{"key":"15_CR26","doi-asserted-by":"publisher","unstructured":"Karatzas, D., et al.: Icdar 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160 (2015). https:\/\/doi.org\/10.1109\/ICDAR.2015.7333942","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"15_CR27","doi-asserted-by":"publisher","unstructured":"Karatzas, D., et al.: Icdar 2013 robust reading competition. In: Proceedings of the 2013 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493. ICDAR \u201913, IEEE Computer Society, USA (2013). https:\/\/doi.org\/10.1109\/ICDAR.2013.221, https:\/\/doi.org\/10.1109\/ICDAR.2013.221","DOI":"10.1109\/ICDAR.2013.221"},{"key":"15_CR28","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR abs\/1412.6980 (2014). https:\/\/api.semanticscholar.org\/CorpusID:6628106"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Kittenplon, Y., Lavi, I., Fogel, S., Bar, Y., Manmatha, R., Perona, P.: Towards weakly-supervised text spotting using a multi-task transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4604\u20134613 (2022)","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"15_CR30","doi-asserted-by":"publisher","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436\u201344 (2015). https:\/\/doi.org\/10.1038\/nature14539","DOI":"10.1038\/nature14539"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C.: Towards end-to-end text spotting with convolutional recurrent neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5238\u20135246 (2017)","DOI":"10.1109\/ICCV.2017.560"},{"key":"15_CR32","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of the 40th International Conference on Machine Learning, ICML\u201923, JMLR.org (2023)"},{"key":"15_CR33","doi-asserted-by":"publisher","unstructured":"Liao, M., Lyu, P., He, M., Yao, C., Wu, W., Bai, X.: Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes. IEEE Trans. Pattern Anal. Mach. Intell., 11 (2019).https:\/\/doi.org\/10.1109\/TPAMI.2019.2937086","DOI":"10.1109\/TPAMI.2019.2937086"},{"key":"15_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1007\/978-3-030-58621-8_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Liao","year":"2020","unstructured":"Liao, M., Pang, G., Huang, J., Hassner, T., Bai, X.: Mask TextSpotter v3: segmentation proposal network for robust scene text spotting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 706\u2013722. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_41"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., Yan, J.: Fots: Fast oriented text spotting with a unified network (2018). https:\/\/arxiv.org\/abs\/1801.01671","DOI":"10.1109\/CVPR.2018.00595"},{"key":"15_CR36","doi-asserted-by":"publisher","unstructured":"Liu, Y., Chen, H., Shen, C., He, T., Jin, L., Wang, L.: Abcnet: Real-time scene text spotting with adaptive bezier-curve network. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 9806\u20139815 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00983","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"15_CR37","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.patcog.2019.02.002","volume":"90","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Jin, L., Zhang, S., Luo, C., Zhang, S.: Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recogn. 90, 337\u2013345 (2019)","journal-title":"Pattern Recogn."},{"issue":"11","key":"15_CR38","doi-asserted-by":"publisher","first-page":"8048","DOI":"10.1109\/TPAMI.2021.3107437","volume":"44","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Shen, C., Jin, L., He, T., Chen, P., Liu, C., Chen, H.: Abcnet v2: Adaptive bezier-curve network for real-time end-to-end text spotting. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 8048\u20138064 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3107437","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR39","doi-asserted-by":"publisher","unstructured":"Long, S., He, X., Ya, C.: Scene text detection and recognition: The deep learning era, November 2018. https:\/\/doi.org\/10.48550\/arXiv.1811.04256","DOI":"10.48550\/arXiv.1811.04256"},{"key":"15_CR40","unstructured":"Lyu, J., Wei, J., Zeng, G., Li, Z., Xie, E., Wang, W., ZHOU, Y.: Textblockv2: Towards precise-detection-free scene text spotting with pre-trained language model. ArXiv abs\/2403.10047 (2024), https:\/\/api.semanticscholar.org\/CorpusID:268510467"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Lyu, P., Liao, M., Yao, C., Wu, W., Bai, X.: Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes (2018). https:\/\/arxiv.org\/abs\/1807.02242","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Nayef, N., et\u00a0al.: Icdar2019 robust reading challenge on multi-lingual scene text detection and recognition-rrc-mlt-2019. In: 2019 International conference on document analysis and recognition (ICDAR), pp. 1582\u20131587. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"15_CR43","doi-asserted-by":"publisher","unstructured":"Nayef, N., et al.: 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.\u00a001, pp. 1454\u20131459 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.237","DOI":"10.1109\/ICDAR.2017.237"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Pak, I., Teh, P.L.: Text segmentation techniques: a critical review. Innovative Computing, Optimization and Its Applications: Modelling and Simulations, pp. 167\u2013181 (2018)","DOI":"10.1007\/978-3-319-66984-7_10"},{"key":"15_CR45","doi-asserted-by":"publisher","unstructured":"Peng, D., et al.: Spts: Single-point text spotting. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4272\u20134281. MM \u201922. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3503161.3547942","DOI":"10.1145\/3503161.3547942"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Prasad, S., Kong, A.W.K.: Using object information for spotting text. In: Proceedings of the European Conference on Computer Vision (ECCV), September 2018","DOI":"10.1007\/978-3-030-01270-0_33"},{"key":"15_CR47","doi-asserted-by":"publisher","unstructured":"Qiao, L., Chen, Y., Cheng, Z., Xu, Y., Niu, Y., Pu, S., Wu, F.: Mango: a mask attention guided one-stage scene text spotter. In: Proceedings of the AAAI Conference on Artificial Intelligence 35, pp. 2467\u20132476, May 2021. https:\/\/doi.org\/10.1609\/aaai.v35i3.16348","DOI":"10.1609\/aaai.v35i3.16348"},{"key":"15_CR48","doi-asserted-by":"publisher","unstructured":"Qiao, L., Tang, S., Cheng, Z., Xu, Y., Niu, Y., Pu, S., Wu, F.: Text perceptron: towards end-to-end arbitrary-shaped text spotting. In: Proceedings of the AAAI Conference on Artificial Intelligence 34, 11899\u201311907, April 2020. https:\/\/doi.org\/10.1609\/aaai.v34i07.6864","DOI":"10.1609\/aaai.v34i07.6864"},{"key":"15_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2014 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"15_CR50","doi-asserted-by":"publisher","unstructured":"Sarkar, S., Das, D., Pakray, P., Gelbukh, A.: JUNITMZ at SemEval-2016 task 1: Identifying semantic similarity using Levenshtein ratio. In: Bethard, S., Carpuat, M., Cer, D., Jurgens, D., Nakov, P., Zesch, T. (eds.) Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 702\u2013705. Association for Computational Linguistics, San Diego, California, June 2016. https:\/\/doi.org\/10.18653\/v1\/S16-1108, https:\/\/aclanthology.org\/S16-1108\/","DOI":"10.18653\/v1\/S16-1108"},{"issue":"11","key":"15_CR51","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","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 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2646371","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification (2016). https:\/\/arxiv.org\/abs\/1603.03915","DOI":"10.1109\/CVPR.2016.452"},{"key":"15_CR53","doi-asserted-by":"publisher","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: Aster: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. PP, 1 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2018.2848939","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"15_CR54","doi-asserted-by":"publisher","unstructured":"Singh, A., Pang, G., Toh, M., Huang, J., Galuba, W., Hassner, T.: Textocr: towards large-scale end-to-end reasoning for arbitrary-shaped scene text. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8798\u20138808 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00869","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"15_CR55","unstructured":"Song, K., Tan, X., Qin, T., Lu, J., Liu, T.Y.: Mpnet: masked and permuted pre-training for language understanding. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. NIPS \u201920. Curran Associates Inc., Red Hook, NY, USA (2020)"},{"key":"15_CR56","doi-asserted-by":"crossref","unstructured":"Tian, Z., Huang, W., He, T., He, P., Qiao, Y.: Detecting text in natural image with connectionist text proposal network (2016). https:\/\/arxiv.org\/abs\/1609.03605","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"15_CR57","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"15_CR58","doi-asserted-by":"publisher","unstructured":"Wang, L., Wang, Y., Shan, S., Su, F.: Scene text detection and tracking in video with background cues. In: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval. p. 160\u2013168. ICMR \u201918. Association for Computing Machinery, New York (2018). https:\/\/doi.org\/10.1145\/3206025.3206051, https:\/\/doi.org\/10.1145\/3206025.3206051","DOI":"10.1145\/3206025.3206051"},{"key":"15_CR59","doi-asserted-by":"publisher","unstructured":"Wang, P., et al.: Pgnet: Real-time arbitrarily-shaped text spotting with point gathering network. In: Proceedings of the AAAI Conference on Artificial Intelligence 35, pp. 2782\u20132790, May 2021. https:\/\/doi.org\/10.1609\/aaai.v35i4.16383","DOI":"10.1609\/aaai.v35i4.16383"},{"issue":"9","key":"15_CR60","doi-asserted-by":"publisher","first-page":"5349","DOI":"10.1109\/TPAMI.2021.3077555","volume":"44","author":"W Wang","year":"2022","unstructured":"Wang, W., Xie, E., Li, X., Liu, X., Liang, D., Yang, Z., Lu, T., Shen, C.: Pan++: towards efficient and accurate end-to-end spotting of arbitrarily-shaped text. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5349\u20135367 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3077555","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR61","doi-asserted-by":"publisher","unstructured":"Wang, X., Wu, C., Yu, H., Li, B., Xue, X.: Textformer: component-aware text segmentation with transformer. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 1877\u20131882 (2023).https:\/\/doi.org\/10.1109\/ICME55011.2023.00322","DOI":"10.1109\/ICME55011.2023.00322"},{"key":"15_CR62","doi-asserted-by":"crossref","unstructured":"Wu, D., Wang, R., Tian, X., Liang, D., Cao, X.: The keywords spotting with context for multi -oriented chinese scene text. In: 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM), pp.\u00a01\u20135 (2018), https:\/\/api.semanticscholar.org\/CorpusID:53043043","DOI":"10.1109\/BigMM.2018.8499433"},{"key":"15_CR63","unstructured":"Xing, L., Tian, Z., Huang, W., Scott, M.R.: Convolutional character networks (2019). https:\/\/arxiv.org\/abs\/1910.07954"},{"key":"15_CR64","doi-asserted-by":"publisher","unstructured":"Ye, J., Chen, Z., Liu, J., Du, B.: Textfusenet: Scene text detection with richer fused features. In: Bessiere, C. (ed.) Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20. pp. 516\u2013522. International Joint Conferences on Artificial Intelligence Organization (7 2020https:\/\/doi.org\/10.24963\/ijcai.2020\/72, main track","DOI":"10.24963\/ijcai.2020\/72"},{"key":"15_CR65","doi-asserted-by":"publisher","unstructured":"Ye, M., Zhang, J., Zhao, S., Liu, J., Liu, T., Du, B., Tao, D.: Deepsolo: Let transformer decoder with explicit points solo for text spotting, November 2022. https:\/\/doi.org\/10.48550\/arXiv.2211.10772","DOI":"10.48550\/arXiv.2211.10772"},{"key":"15_CR66","doi-asserted-by":"publisher","unstructured":"Ye, M., Zhang, J., Zhao, S., Liu, J., Liu, T., Du, B., Tao, D.: Deepsolo++: Let transformer decoder with explicit points solo for text spotting (05 2023). https:\/\/doi.org\/10.48550\/arXiv.2305.19957","DOI":"10.48550\/arXiv.2305.19957"},{"key":"15_CR67","doi-asserted-by":"publisher","unstructured":"Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37, June 2015. https:\/\/doi.org\/10.1109\/TPAMI.2014.2366765","DOI":"10.1109\/TPAMI.2014.2366765"},{"key":"15_CR68","doi-asserted-by":"publisher","unstructured":"Zhang, C., Yuefeng, T., Du, K., Ding, W., Wang, B., Liu, J., Wang, W.: Character-level street view text spotting based on deep multi-segmentation network for smarter autonomous driving. IEEE Trans. Artif. Intell. PP, 1 (2021). https:\/\/doi.org\/10.1109\/TAI.2021.3116216","DOI":"10.1109\/TAI.2021.3116216"},{"key":"15_CR69","doi-asserted-by":"publisher","unstructured":"Zhang, Q., Xu, Y., Zhang, J., Tao, D.: Vitaev2: Vision transformer advanced by exploring inductive bias for image recognition and beyond, February 2022. https:\/\/doi.org\/10.48550\/arXiv.2202.10108","DOI":"10.48550\/arXiv.2202.10108"},{"key":"15_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, X., Su, Y., Tripathi, S., Tu, Z.: Text spotting transformers. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9509\u20139518 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247957876","DOI":"10.1109\/CVPR52688.2022.00930"},{"key":"15_CR71","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123771","volume":"249","author":"D Zhong","year":"2024","unstructured":"Zhong, D., Zhan, H., Lyu, S., Liu, C., Yin, B., Shivakumara, P., Pal, U., Lu, Y.: Ndorder: exploring a novel decoding order for scene text recognition. Expert Syst. Appl. 249, 123771 (2024). https:\/\/doi.org\/10.1016\/j.eswa.2024.123771","journal-title":"Expert Syst. Appl."}],"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\/978-3-032-04617-8_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T11:46:32Z","timestamp":1757936792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04617-8_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,15]]},"ISBN":["9783032046161","9783032046178"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04617-8_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,15]]},"assertion":[{"value":"15 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"}}]}}