{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:22:14Z","timestamp":1771950134120,"version":"3.50.1"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198144","type":"print"},{"value":"9783031198151","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19815-1_16","type":"book-chapter","created":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T23:11:54Z","timestamp":1666221114000},"page":"267-283","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1511-2737","authenticated-orcid":false,"given":"Jeonghun","family":"Baek","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1529-0154","authenticated-orcid":false,"given":"Yusuke","family":"Matsui","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2146-6275","authenticated-orcid":false,"given":"Kiyoharu","family":"Aizawa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,20]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Aizawa, K., et al.: Building a manga dataset manga109 with annotations for multimedia applications. IEEE MultiMedia 2(27), 8\u201318 (2020)","DOI":"10.1109\/MMUL.2020.2987895"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Almaz\u00e1n, J., Gordo, A., Forn\u00e9s, A., Valveny, E.: Word spotting and recognition with embedded attributes. TPAMI 36(12), 2552\u20132566 (2014)","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? dataset and model analysis. In: ICCV, pp. 4715\u20134723 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"16_CR4","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. TACL 5, 135\u2013146 (2017)","DOI":"10.1162\/tacl_a_00051"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Bookstein, F.L.: Principal warps: thin-plate splines and the decomposition of deformations. TPAMI 11(6), 567\u2013585 (1989)","DOI":"10.1109\/34.24792"},{"key":"16_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: ICCV, pp. 5076\u20135084 (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Chng, C.K., et al.: ICDAR 2019 robust reading challenge on arbitrary-shaped text-rrc-art. In: ICDAR, pp. 1571\u20131576 (2019)","DOI":"10.1109\/ICDAR.2019.00252"},{"issue":"1","key":"16_CR9","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10032-019-00334-z","volume":"23","author":"C-K Ch\u2019ng","year":"2019","unstructured":"Ch\u2019ng, C.-K., Chan, C.S., Liu, C.-L.: Total-Text: toward orientation robustness in scene text detection. Int. J. Doc. Anal. Recogn. (IJDAR) 23(1), 31\u201352 (2019). https:\/\/doi.org\/10.1007\/s10032-019-00334-z","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Dai, P., Zhang, S., Zhang, H., Cao, X.: Progressive contour regression for arbitrary-shape scene text detection. In: CVPR, pp. 7393\u20137402 (2021)","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Gu\u00e9rin, C., et al.: ebdtheque: a representative database of comics. In: ICDAR, pp. 1145\u20131149 (2013)","DOI":"10.1109\/ICDAR.2013.232"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Hu, R., Singh, A., Darrell, T., Rohrbach, M.: Iterative answer prediction with pointer-augmented multimodal transformers for textvqa. In: CVPR, pp. 9992\u201310002 (2020)","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Huang, Y., Sun, Z., Jin, L., Luo, C.: EPAN: effective parts attention network for scene text recognition. Neurocomputing 376, 202\u2013213 (2020)","DOI":"10.1016\/j.neucom.2019.10.010"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Iyyer, M., Manjunatha, V., Guha, A., Vyas, Y., Boyd-Graber, J., Daume, H., Davis, L.S.: The amazing mysteries of the gutter: drawing inferences between panels in comic book narratives. In: CVPR, pp. 7186\u20137195 (2017)","DOI":"10.1109\/CVPR.2017.686"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: ICDAR, pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: ICDAR, pp. 1484\u20131493 (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"16_CR18","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: Workshop on Text and Documents in the Deep Learning Era, CVPR, pp. 546\u2013547 (2020)","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"16_CR19","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: AAAI, vol. 33, no. 01, pp. 8610\u20138617 (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"16_CR20","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":"16_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., Jin, L., Zhang, S., Luo, C., Zhang, S.: Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recog. 90, 337\u2013345 (2019)","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Abcnet v2: adaptive bezier-curve network for real-time end-to-end text spotting. TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Yao, C.: Textsnake: a flexible representation for detecting text of arbitrary shapes. In: ECCV, pp. 20\u201336 (2018)","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Lu, N., et al.: Master: multi-aspect non-local network for scene text recognition. Pattern Recogn. 117, 107980 (2021)","DOI":"10.1016\/j.patcog.2021.107980"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Ma, J., et al.: Arbitrary-oriented scene text detection via rotation proposals. TMM 20(11), 3111\u20133122 (2018)","DOI":"10.1109\/TMM.2018.2818020"},{"issue":"20","key":"16_CR26","doi-asserted-by":"publisher","first-page":"21811","DOI":"10.1007\/s11042-016-4020-z","volume":"76","author":"Y Matsui","year":"2016","unstructured":"Matsui, Y., Ito, K., Aramaki, Y., Fujimoto, A., Ogawa, T., Yamasaki, T., Aizawa, K.: Sketch-based manga retrieval using manga109 dataset. Multimedia Tools Appl. 76(20), 21811\u201321838 (2016). https:\/\/doi.org\/10.1007\/s11042-016-4020-z","journal-title":"Multimedia Tools Appl."},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Nayef, N., et al.: ICDAR 2019 robust reading challenge on multi-lingual scene text detection and recognition-rrc-mlt-2019. In: ICDAR, vol. 1, pp. 1454\u20131459 (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Petersen, R.S.: The acoustics of manga. In: Heer, J., Worcester, K., (eds.) A Comics Studies Reader, pp. 163\u2013171. University Press of Mississippi (2009)","DOI":"10.2307\/j.ctt2tvd9s.22"},{"key":"16_CR29","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Risnumawan, A., Shivakumara, P., Chan, C.S., Tan, C.L.: A robust arbitrary text detection system for natural scene images. ESWA 41(18), 8027\u20138048 (2014)","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"16_CR31","doi-asserted-by":"crossref","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. TPAMI 39(11), 2298\u20132304 (2016)","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: CVPR, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: Aster: an attentional scene text recognizer with flexible rectification. TPAMI 41(9), 2035\u20132048 (2018)","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Shi, B., et al.: ICDAR 2017 competition on reading Chinese text in the wild (RCWT-17). In: ICDAR, vol. 1, pp. 1429\u20131434 (2017)","DOI":"10.1109\/ICDAR.2017.233"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards vqa models that can read. In: CVPR, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"16_CR36","doi-asserted-by":"crossref","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: CVPR, pp. 8802\u20138812 (2021)","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: ICDAR2019 competition on large-scale street view text with partial labeling-RRC-LSTV. In: ICDAR, pp. 1557\u20131562 (2019)","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"16_CR38","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NeurIPS 27 (2014)"},{"key":"16_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS 30 (2017)"},{"key":"16_CR40","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: Coco-text: Dataset and benchmark for text detection and recognition in natural images. arXiv:1601.07140 (2016)"},{"key":"16_CR41","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: NeurIPS 28 (2015)"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Wang, H.: All you need is boundary: toward arbitrary-shaped text spotting. In: AAAI, vol. 34, no. 07, 12160\u201312167 (2020)","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Shape robust text detection with progressive scale expansion network. In: CVPR, pp. 9336\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: ICCV, pp. 8440\u20138449 (2019)","DOI":"10.1109\/ICCV.2019.00853"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Zha, Z.J., Xing, M., Fu, Z., Zhang, Y.: Contournet: taking a further step toward accurate arbitrary-shaped scene text detection. In: CVPR, pp. 11753\u201311762 (2020)","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Yang, X., He, D., Zhou, Z., Kifer, D., Giles, C.L.: Learning to read irregular text with attention mechanisms. In: IJCAI, vol. 1, no. 2, p. 3 (2017)","DOI":"10.24963\/ijcai.2017\/458"},{"key":"16_CR47","unstructured":"Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. In: CVPR, pp. 1083\u20131090 (2012)"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: ICDAR 2019 robust reading challenge on reading Chinese text on signboard. In: ICDAR, pp. 1577\u20131581 (2019)","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., et al.: Deep relational reasoning graph network for arbitrary shape text detection. In: CVPR, pp. 9699\u20139708 (2020)","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"16_CR50","unstructured":"Zhang, Y., Gueguen, L., Zharkov, I., Zhang, P., Seifert, K., Kadlec, B.: Uber-text: a large-scale dataset for optical character recognition from street-level imagery. In: Scene Understanding Workshop, CVPR, p. 5 (2017)"},{"key":"16_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Chen, J., Liang, L., Kuang, Z., Jin, L., Zhang, W.: Fourier contour embedding for arbitrary-shaped text detection. In: CVPR, pp. 3123\u20133131 (2021)","DOI":"10.1109\/CVPR46437.2021.00314"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19815-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T05:11:07Z","timestamp":1701234667000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19815-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198144","9783031198151"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19815-1_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"20 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}