{"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":1758083709127,"version":"3.44.0"},"publisher-location":"Cham","reference-count":53,"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_10","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:09:43Z","timestamp":1757988583000},"page":"172-190","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PerturbCTC: Improving Alignment in\u00a0Scene Text Recognition with\u00a0Feature Perturbation Based CTC"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7075-1869","authenticated-orcid":false,"given":"Zeng","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2016-0901","authenticated-orcid":false,"given":"Jin","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6135-7958","authenticated-orcid":false,"given":"Zhijie","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8830-8250","authenticated-orcid":false,"given":"Yaqiang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2696-8549","authenticated-orcid":false,"given":"Gangyan","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8628-411X","authenticated-orcid":false,"given":"Dongbao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8942-5907","authenticated-orcid":false,"given":"Zhi","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4188-9953","authenticated-orcid":false,"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., et\u00a0al.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML 2006, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Ehsan Variani, Tom Bagby, Kamel Lahouel, et\u00a0al., \u201cSampled connectionist temporal classification,\u201d in ICASSP, 2018, pp. 4959\u20134963","DOI":"10.1109\/ICASSP.2018.8461929"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Baoguang Shi, Xiang Bai, and Cong Yao, \u201cAn end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition,\u201d TPAMI, pp. 2298\u20132304, 2016","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Du, Y., Chen, Z., Jia, C., et\u00a0al.: Svtr: scene text recognition with a single visual model (2022)","DOI":"10.24963\/ijcai.2022\/124"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Hu, W., Cai, X., Hou, J., et\u00a0al.: Gtc: guided training of ctc towards efficient and accurate scene text recognition. In: AAAI 2020, pp. 11005\u201311012 (2020)","DOI":"10.1609\/aaai.v34i07.6735"},{"key":"10_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1007\/978-3-030-58604-1_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Chao","year":"2020","unstructured":"Chao, L., Chen, J., Chu, W.: Variational connectionist temporal classification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 460\u2013476. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_28"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, W.: Reinterpreting ctc training as iterative fitting PR 107392 (2020)","DOI":"10.1016\/j.patcog.2020.107392"},{"key":"10_CR8","unstructured":"Liu, H., Jin, S., Zhang, C.: Connectionist temporal classification with maximum entropy regularization. In: NIPS (2018)"},{"key":"10_CR9","unstructured":"Du, Y., Chen, Z., Xie, H., Jia, C., Jiang, Y.G.: Svtrv2: Ctc beats encoder-decoder models in scene text recognition. CoRR arxiv:2411.15858 (2024)"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Qin, X., Zhou, Y., Yang, F., Wang, W.: Gaussian constrained attention network for scene text recognition. In: 2020 25th International Conference on Pattern Recognition (ICPR), p. 3328\u20133335 (2021)","DOI":"10.1109\/ICPR48806.2021.9412806"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Zhou, Y., Yang, D., et\u00a0al.: Seed: semantics enhanced encoder-decoder framework for scene text recognition. In: CVPR 2020, pp. 13528\u201313537 (2020)","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Zhou, Y., Wei, J., et\u00a0al.: Pimnet: a parallel, iterative and mimicking network for scene text recognition. In: ACMMM 2021, pp. 2046\u20132055 (2021)","DOI":"10.1145\/3474085.3475238"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Li, M., Lv, T., Chen, J., et\u00a0al.: Trocr: transformer-based optical character recognition with pre-trained models. In: AAAI 2023, pp. 13094\u201313102 (2003)","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"10_CR14","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1109\/LSP.2024.3381893","volume":"31","author":"X Yang","year":"2024","unstructured":"Yang, X., Qiao, Z., Wei, J., Yang, D., Zhou, Yu.: Masked and permuted implicit context learning for scene text recognition. IEEE Signal Process. Lett. 31, 964\u2013968 (2024)","journal-title":"IEEE Signal Process. Lett."},{"key":"10_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-025-02443-1","volume":"133","author":"X Yang","year":"2025","unstructured":"Yang, X., Qiao, Z., Zhou, Y.: IPAD: iterative, parallel, and diffusion-based network for scene text recognition. Int. J. Comput. Vision 133, 1\u201321 (2025)","journal-title":"Int. J. Comput. Vision"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Linguistics-aware masked image modeling for self-supervised scene text recognition. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 9318\u20139328 (2025)","DOI":"10.1109\/CVPR52734.2025.00870"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, Y., Jin, L., et\u00a0al.: Decoupled attention network for text recognition. In: AAAI 2020, pp. 12216\u201312224 (2020)","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Yu, D., Li, X., Zhang, C., et\u00a0al.: Towards accurate scene text recognition with semantic reasoning networks. In: CVPR 2020, pp. 12113\u201312122 (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Wan, Z., He, M., Chen, H., et\u00a0al.: Textscanner: reading characters in order for robust scene text recognition. In: AAAI 2020, pp. 12120\u201312127 (2020)","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"10_CR20","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: CVPR 2021, pp. 7098\u20137107 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Fang, S., et\u00a0al.: From two to one: a new scene text recognizer with visual language modeling network. In: ICCV 2021, pp. 14194\u201314203 (2021)","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Wang, P., Da, C., Yao, C.: Multi-granularity prediction for scene text recognition. In ECCV 2022, pp. 339\u2013355 (2022)","DOI":"10.1007\/978-3-031-19815-1_20"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Na, B., Kim, Y., Park, S.: Multi-modal text recognition networks: Interactive enhancements between visual and semantic features. In: ECCV 2022, pp. 446\u2013463 (2022)","DOI":"10.1007\/978-3-031-19815-1_26"},{"issue":"1","key":"10_CR24","doi-asserted-by":"publisher","first-page":"9345861","DOI":"10.1155\/2019\/9345861","volume":"2019","author":"X Feng","year":"2019","unstructured":"Feng, X., Yao, H., Zhang, S.: Focal CTC loss for Chinese optical character recognition on unbalanced datasets. Complexity 2019(1), 9345861 (2019)","journal-title":"Complexity"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Lu, N., Liao, M., et\u00a0al.: Self-distillation regularized connectionist temporal classification loss for text recognition: a simple yet effective approach (2023)","DOI":"10.1609\/aaai.v38i7.28575"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., et\u00a0al.: Icdar 2013 robust reading competition. In: ICDAR 2013, pp. 1484\u20131493 (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., et\u00a0al.: Icdar 2015 competition on robust reading. In: ICDAR 2015, pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: BMVC (2012)","DOI":"10.5244\/C.26.127"},{"key":"10_CR29","unstructured":"Wang, K., Babenko, B., Belongie, S: End-to-end scene text recognition. In: ICCV 2011, pp. 1457\u20131464 (2011)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Phan, T.Q., Shivakumara, P., Tian, S., et\u00a0al.: Recognizing text with perspective distortion in natural scenes. In: ICCV 2013, pp. 569\u2013576 (2013)","DOI":"10.1109\/ICCV.2013.76"},{"issue":"18","key":"10_CR31","doi-asserted-by":"publisher","first-page":"8027","DOI":"10.1016\/j.eswa.2014.07.008","volume":"41","author":"A Risnumawan","year":"2014","unstructured":"Risnumawan, A., Shivakumara, P., Chan, C.S., Tan, C.L.: A robust arbitrary text detection system for natural scene images. Expert Syst. Appl. 41(18), 8027\u20138048 (2014)","journal-title":"Expert Syst. Appl."},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, Q., Wang, J., Peng, D., Liu, C., Jin, L.: Revisiting scene text recognition: a data perspective. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01878"},{"key":"10_CR33","unstructured":"Yu, H., Chen, J., Li, B., et\u00a0al.: Benchmarking Chinese text recognition: datasets, baselines, and an empirical study. arXiv preprint arXiv:2112.15093 (2021)"},{"key":"10_CR34","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. TPAMI 41, 2035\u20132048 (2018)","journal-title":"TPAMI"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Sheng, F., Chen, Z., Xu, B.: NRTR: a no-recurrence sequence-to-sequence model for scene text recognition. CoRR arxiv:1806.00926 (2018)","DOI":"10.1109\/ICDAR.2019.00130"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Luo, C., Jin, L., Sun, Z.: Moran: a multi-object rectified attention network for scene text recognition. PR 109\u2013118 (2019)","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C., Zhang, G.: Show, attend and read: a simple and strong baseline for irregular text recognition. In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence. AAAI\u201919\/IAAI\u201919\/EAAI\u201919, AAAI Press (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"10_CR38","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition. In: AAAI Conference on Artificial Intelligence (2019)"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Deli, Yu., Li, X., Zhang, C., Liu, T., Han, J., Liu, J., Ding, E.: Towards accurate scene text recognition with semantic reasoning networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020, pp. 12110\u201312119 (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, H., Yao, Q., Yang, M., Xu, Y., Bai, X.: Autostr: efficient backbone search for scene text recognition. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58586-0_44"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Yue, X., Kuang, Z., Lin, C., Sun, H., Zhang, W.: Robustscanner: dynamically enhancing positional clues for robust text recognition. ArXiv arxiv:2007.07542 (2020)","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"10_CR42","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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021, pp. 7094\u20137103 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Fang, S., Wang, J., Zhu, S., Zhang, Y.: From two to one: a new scene text recognizer with visual language modeling network. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 14174\u201314183 (2021)","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Na, B., Kim, Y., Park, S.: Multi-modal text recognition networks: interactive enhancements between visual and semantic features. In: Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part XXVIII, pp. 446\u2013463. Springer, Heidelberg (2022)","DOI":"10.1007\/978-3-031-19815-1_26"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Wang, P., Da, C., Yao, C.: Multi-granularity prediction for scene text recognition. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19815-1_20"},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Du, Y., Chen, Z., Jia, C., Yin, X., Li, C., Du, Y., Jiang, Y.G.: Context perception parallel decoder for scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3545453"},{"key":"10_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xie, H., Wang, Y., Xu, J., Zhang, Y.: Linguistic more: taking a further step toward efficient and accurate scene text recognition. In: International Joint Conference on Artificial Intelligence (2023)","DOI":"10.24963\/ijcai.2023\/189"},{"key":"10_CR49","doi-asserted-by":"crossref","unstructured":"Cheng, C., Wang, P., Da, C., et\u00a0al.: Lister: neighbor decoding for length-insensitive scene text recognition. In: ICCV 2023, pp. 19541\u201319551 (2003)","DOI":"10.1109\/ICCV51070.2023.01790"},{"issue":"2","key":"10_CR50","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/s11263-023-01880-0","volume":"132","author":"T Zheng","year":"2023","unstructured":"Zheng, T., Chen, Z., Fang, S., Xie, H., Jiang, Y.-G.: Cdistnet: perceiving multi-domain character distance for robust text recognition. Int. J. Comput. Vision 132(2), 300\u2013318 (2023)","journal-title":"Int. J. Comput. Vision"},{"key":"10_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110244","volume":"149","author":"M Yang","year":"2024","unstructured":"Yang, M., Yang, B., Liao, M., Zhu, Y., Bai, X.: Class-aware mask-guided feature refinement for scene text recognition. Pattern Recogn. 149, 110244 (2024)","journal-title":"Pattern Recogn."},{"key":"10_CR52","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Image as a language: revisiting scene text recognition via balanced, unified and synchronized vision-language reasoning network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 5885\u20135893 (2024)","DOI":"10.1609\/aaai.v38i6.28402"},{"key":"10_CR53","doi-asserted-by":"crossref","unstructured":"Jianjun, X., Wang, Y., Xie, H., Zhang, Y.: Ote: exploring accurate scene text recognition using one token. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, pp. 28327\u201328336 (2024)","DOI":"10.1109\/CVPR52733.2024.02676"}],"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_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:10:01Z","timestamp":1757988601000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04627-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032046260","9783032046277"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04627-7_10","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"}}]}}