{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:48:16Z","timestamp":1743022096255,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705427"},{"type":"electronic","value":"9783031705434"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70543-4_9","type":"book-chapter","created":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T09:02:15Z","timestamp":1725786135000},"page":"145-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Recognition and\u00a0Link Prediction of\u00a0Onomatopoeia Texts with\u00a0Arbitrary Shapes"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1262-6530","authenticated-orcid":false,"given":"Jingtao","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2570-4544","authenticated-orcid":false,"given":"Hongxi","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9994-3691","authenticated-orcid":false,"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,9]]},"reference":[{"issue":"12","key":"9_CR1","doi-asserted-by":"publisher","first-page":"2552","DOI":"10.1109\/TPAMI.2014.2339814","volume":"36","author":"J Almaz\u00e1n","year":"2014","unstructured":"Almaz\u00e1n, J., Gordo, A., Forn\u00e9s, A., Valveny, E.: Word spotting and recognition with embedded attributes. IEEE Trans. Pattern Anal. Mach. Intell. 36(12), 2552\u20132566 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_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 International Conference on Computer Vision, pp. 4715\u20134723. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"9_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/978-3-031-19815-1_16","volume-title":"Computer Vision \u2013 ECCV 2022","author":"J Baek","year":"2022","unstructured":"Baek, J., Matsui, Y., Aizawa, K.: Coo: Comic onomatopoeia dataset for recognizing arbitrary or truncated texts. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 267\u2013283. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_16"},{"key":"9_CR4","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"9_CR5","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"BOOKSTEIN, F.L.: Principal warps: thin-plate splines and the decomposition of deformations. IEEE Trans. Pattern Anal. Mach. Intell. 11(6), 567\u2013585 (1989)","DOI":"10.1109\/34.24792"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S.: Focusing attention: towards accurate text recognition in natural images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5076\u20135084. IEEE (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"9_CR8","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Du, Y., et la.: SVTR: scene text recognition with a single visual model. arXiv preprint arXiv:2205.00159 (2022)","DOI":"10.24963\/ijcai.2022\/124"},{"key":"9_CR10","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 Conference on Computer Vision and Pattern Recognition, pp. 7098\u20137107. IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"9_CR11","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. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Hu, R., Singh, A., Darrell, T., Rohrbach, M.: Iterative answer prediction with pointer-augmented multimodal transformers for TextVQA. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9992\u201310002. IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"9_CR13","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1016\/j.neucom.2019.10.010","volume":"376","author":"Y Huang","year":"2020","unstructured":"Huang, Y., Sun, Z., Jin, L., Luo, C.: EPAN: effective parts attention network for scene text recognition. Neurocomputing 376, 202\u2013213 (2020)","journal-title":"Neurocomputing"},{"key":"9_CR14","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, vol. 28, pp. 2017\u20132025 (2015)"},{"key":"9_CR15","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 Conference on Computer Vision and Pattern Recognition Workshops, pp. 546\u2013547 (2020)","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"9_CR16","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 AAAI Conference on Artificial Intelligence, pp. 8610\u20138617. AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"9_CR17","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":"9_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988. IEEE (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"9_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-031-41498-5_13","volume-title":"Document Analysis and Recognition - ICDAR 2023 Workshops","author":"JB Louis","year":"2023","unstructured":"Louis, J.B., Burie, J.C.: Detection of buried complex text. Case of onomatopoeia in comics books. In: Coustaty, M., Forn\u00e9s, A. (eds.) ICDAR 2023. LNCS, vol. 14193, pp. 177\u2013191. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41498-5_13"},{"key":"9_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1007\/978-3-031-37742-6_4","volume-title":"Pattern Recognition, Computer Vision, and Image Processing - ICPR 2022 International Workshops and Challenges","author":"JB Louis","year":"2022","unstructured":"Louis, J.B., Burie, J.C., Revel, A.: Can deep learning approaches detect complex text? Case of onomatopoeia in comics albums. In: Rousseau, J.J., Kapralos, B. (eds.) ICPR 2022. Lecture Notes in Computer Science, vol. 13644, pp. 48\u201360. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-37742-6_4"},{"key":"9_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107980","volume":"117","author":"N Lu","year":"2021","unstructured":"Lu, N., et al.: Master: multi-aspect non-local network for scene text recognition. Pattern Recogn. 117, 107980 (2021)","journal-title":"Pattern Recogn."},{"key":"9_CR22","doi-asserted-by":"publisher","first-page":"21811","DOI":"10.1007\/s11042-016-4020-z","volume":"76","author":"Y Matsui","year":"2017","unstructured":"Matsui, Y., et al.: Sketch-based manga retrieval using manga109 dataset. Multimedia Tools Appl. 76, 21811\u201321838 (2017)","journal-title":"Multimedia Tools Appl."},{"key":"9_CR23","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28, pp. 91\u201399 (2015)"},{"issue":"11","key":"9_CR24","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":"9_CR25","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4168\u20134176. IEEE (2016)","DOI":"10.1109\/CVPR.2016.452"},{"issue":"9","key":"9_CR26","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., Lyu, P., Yao, C., Bai, X.: 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":"9_CR27","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, vol. 27, pp. 3104\u20133112 (2014)"},{"key":"9_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30, pp. 5998\u20136008 (2017)"},{"key":"9_CR29","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Advances in Neural Information Processing Systems, vol. 28, pp. 2692\u20132700 (2015)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70543-4_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T14:06:39Z","timestamp":1739887599000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70543-4_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705427","9783031705434"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70543-4_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"9 September 2024","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":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}