{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T04:02:22Z","timestamp":1745812942862,"version":"3.40.4"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031784972"},{"type":"electronic","value":"9783031784989"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78498-9_8","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T09:28:33Z","timestamp":1733218113000},"page":"103-117","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Contour-Guided Context Learning for\u00a0Scene Text Recognition"],"prefix":"10.1007","author":[{"given":"Wei-Chun","family":"Hsieh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2631-0448","authenticated-orcid":false,"given":"Gee-Sern","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun-Yi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moi Hoon","family":"Yap","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zi-Chun","family":"Chao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Atienza, R.: Vision transformer for fast and efficient scene text recognition. In: International Conference on Document Analysis and Recognition, pp. 319\u2013334. Springer (2021)","DOI":"10.1007\/978-3-030-86549-8_21"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? Dataset and model analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4715\u20134723 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"8_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/978-3-031-19815-1_11","volume-title":"Computer Vision \u2013 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.) ECCV 2022. LNCS, vol. 13688, pp. 178\u2013196. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_11"},{"key":"8_CR4","unstructured":"Bojanowski, P., Joulin, A., Lopez-Paz, D., Szlam, A.: Optimizing the latent space of generative networks (2019). arXiv:1707.05776"},{"key":"8_CR5","unstructured":"Cup, A.: Moe AI competition and labeled data acquisition project. https:\/\/www.aicup.tw\/"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Da, C., Wang, P., Yao, C.: Levenshtein OCR. In: ECCV 2022, Part XXVIII, pp. 322\u2013338. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_19"},{"key":"8_CR7","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"8_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"8_CR9","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7098\u20137107 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"8_CR10","doi-asserted-by":"publisher","unstructured":"Goh, G., et al.: Multimodal neurons in artificial neural networks. Distill (2021). https:\/\/doi.org\/10.23915\/distill.00030","DOI":"10.23915\/distill.00030"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F.J., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: Self-supervised implicit glyph attention for text recognition. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01467"},{"key":"8_CR13","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":"8_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., Qiao, Y., Loy, C.C., Tang, X.: Reading scene text in deep convolutional sequences. In: AAAI (2016)","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"8_CR16","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. In: Workshop on Deep Learning, NIPS (2014)"},{"key":"8_CR17","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et\u00a0al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Lee, J., Park, S., Baek, J., Oh, S.J., Kim, S., Lee, H.: On recognizing texts of arbitrary shapes with 2D self-attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 546\u2013547 (2020)","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"8_CR21","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843 (2016)"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: BMVC-British machine vision conference. BMVA (2012)","DOI":"10.5244\/C.26.127"},{"key":"8_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, Part XXVIII, pp. 446\u2013463. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_26"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Phan, T.Q., Shivakumara, P., Tian, S., Tan, C.L.: Recognizing text with perspective distortion in natural scenes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 569\u2013576 (2013)","DOI":"10.1109\/ICCV.2013.76"},{"key":"8_CR25","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"issue":"18","key":"8_CR26","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":"8_CR27","doi-asserted-by":"publisher","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: ACL (2016). https:\/\/doi.org\/10.18653\/v1\/p16-1162","DOI":"10.18653\/v1\/p16-1162"},{"key":"8_CR28","unstructured":"Shen, S., et al.: How much can CLIP benefit vision-and-language tasks? In: ICLR (2022)"},{"issue":"11","key":"8_CR29","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":"8_CR30","doi-asserted-by":"crossref","unstructured":"Shi, H., Peng, L., Yan, R., Yao, G., Han, S., Wang, S.: Mask scene text recognizer. In: International Conference on Document Analysis and Recognition, pp. 33\u201348. Springer (2021)","DOI":"10.1007\/978-3-030-86337-1_3"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Cardoso, M.J.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. CoRR arXiv:1707.03237 (2017)","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"8_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"8_CR33","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: 2011 International Conference on Computer Vision, pp. 1457\u20131464. IEEE (2011)"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 12216\u201312224 (2020)","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Wu, L., et al.: Editing text in the wild. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1500\u20131508 (2019)","DOI":"10.1145\/3343031.3350929"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Xu, X., Zhang, Z., Wang, Z., Price, B., Wang, Z., Shi, H.: Rethinking text segmentation: a novel dataset and a text-specific refinement approach. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12045\u201312055 (2021)","DOI":"10.1109\/CVPR46437.2021.01187"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Yu, D., Li, X., Zhang, C., Liu, T., Han, J., Liu, J., Ding, E.: Towards accurate scene text recognition with semantic reasoning networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12113\u201312122 (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Yue, X., Kuang, Z., Lin, C., Sun, H., Zhang, W.: RobustScanner: dynamically enhancing positional clues for robust text recognition. In: European Conference on Computer Vision, pp. 135\u2013151. Springer (2020)","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhu, B., Yao, X., Sun, Q., Li, R., Yu, B.: Context-based contrastive learning for scene text recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 3353\u20133361 (2022)","DOI":"10.1609\/aaai.v36i3.20245"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78498-9_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,27]],"date-time":"2025-04-27T14:15:00Z","timestamp":1745763300000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78498-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031784972","9783031784989"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78498-9_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}