{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:21:28Z","timestamp":1771957288046,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031706448","type":"print"},{"value":"9783031706455","type":"electronic"}],"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\/978-3-031-70645-5_11","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"154-167","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Comics Datasets Framework: Mix of\u00a0Comics Datasets for\u00a0Detection Benchmarking"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9971-8738","authenticated-orcid":false,"given":"Emanuele","family":"Vivoli","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4231-1686","authenticated-orcid":false,"given":"Irene","family":"Campaioli","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8528-7890","authenticated-orcid":false,"given":"Mariateresa","family":"Nardoni","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1153-1651","authenticated-orcid":false,"given":"Niccol\u00f2","family":"Biondi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1364-218X","authenticated-orcid":false,"given":"Marco","family":"Bertini","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8762-4454","authenticated-orcid":false,"given":"Dimosthenis","family":"Karatzas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"11_CR1","doi-asserted-by":"publisher","unstructured":"Agrawal, H., Mishra, A., Gupta, M., Mausam: multimodal persona based generation of comic dialogs. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 14150\u201314164. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.791, https:\/\/aclanthology.org\/2023.acl-long.791","DOI":"10.18653\/v1\/2023.acl-long.791"},{"key":"11_CR2","doi-asserted-by":"publisher","unstructured":"Baek, J., Matsui, Y., Aizawa, K.: COO\/ Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2207.04675, http:\/\/arxiv.org\/abs\/2207.04675","DOI":"10.48550\/arXiv.2207.04675"},{"key":"11_CR3","unstructured":"Dubray, D., Laubrock, J.: Deep CNN-based Speech Balloon Detection and Segmentation for Comic Books. arXiv, http:\/\/arxiv.org\/abs\/1902.08137"},{"key":"11_CR4","doi-asserted-by":"publisher","unstructured":"Dunst, A., Hartel, R., Laubrock, J.: The graphic narrative corpus (GNC): design, annotation, and analysis for the digital humanities. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). vol.\u00a003, pp. 15\u201320. https:\/\/doi.org\/10.1109\/ICDAR.2017.286","DOI":"10.1109\/ICDAR.2017.286"},{"key":"11_CR5","doi-asserted-by":"publisher","unstructured":"Dutta, A., Biswas, S., Das, A.K.: BCBId: First Bangla comic dataset and its applications 25(4), 265\u2013279. https:\/\/doi.org\/10.1007\/s10032-022-00412-9","DOI":"10.1007\/s10032-022-00412-9"},{"key":"11_CR6","doi-asserted-by":"publisher","unstructured":"Dutta, A., Biswas, S., Das, A.K.: CNN-based segmentation of speech balloons and narrative text boxes from comic book page images 24(1-2), 49\u201362. https:\/\/doi.org\/10.1007\/s10032-021-00366-4, https:\/\/link.springer.com\/10.1007\/s10032-021-00366-4","DOI":"10.1007\/s10032-021-00366-4"},{"key":"11_CR7","unstructured":"family=Ho, given=HN, g.i., Rigaud, C., Burie, J.C., Ogier, J.M.: Redundant structure detection in attributed adjacency graphs for character detection in comics books. https:\/\/www.semanticscholar.org\/paper\/Redundant-structure-detection-in-attributed-graphs-Verview\/172855949a669fd6d5f8049f1a8ec6f7614cbccd"},{"key":"11_CR8","doi-asserted-by":"publisher","unstructured":"Fujimoto, A., Ogawa, T., Yamamoto, K., Matsui, Y., Yamasaki, T., Aizawa, K.: Manga109 dataset and creation of metadata. In: Proceedings of the 1st International Workshop on coMics ANalysis, Processing and Understanding (Manpu), pp.\u00a01\u20135. https:\/\/doi.org\/10.1145\/3011549.3011551, https:\/\/dl.acm.org\/doi\/10.1145\/3011549.3011551","DOI":"10.1145\/3011549.3011551"},{"key":"11_CR9","doi-asserted-by":"publisher","unstructured":"Gu\u00e9rin, C., et al.: eBDtheque: a representative database of comics. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1145\u20131149. https:\/\/doi.org\/10.1109\/ICDAR.2013.232, https:\/\/www.scopus.com\/inward\/record.uri?eid=2-s2.0-84889595169&doi=10.1109%2fICDAR.2013.232 &partnerID=40 &md5=38719ad5d5966b1a143ef2020aa8ee73","DOI":"10.1109\/ICDAR.2013.232"},{"key":"11_CR10","doi-asserted-by":"publisher","unstructured":"He, Z., Zhou, Y., Wang, Y., Tang, Z.: SReN: shape regression network for comic storyboard extraction. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a031. https:\/\/doi.org\/10.1609\/aaai.v31i1.11074, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/11074","DOI":"10.1609\/aaai.v31i1.11074"},{"key":"11_CR11","doi-asserted-by":"publisher","unstructured":"He, Z., Zhou, Y., Wang, Y., Wang, S., Lu, X., Tang, Z., Cai, L.: An end-to-end quadrilateral regression network for comic panel extraction. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 887\u2013895. MM \u201918, Association for Computing Machinery. https:\/\/doi.org\/10.1145\/3240508.3240555","DOI":"10.1145\/3240508.3240555"},{"key":"11_CR12","doi-asserted-by":"publisher","unstructured":"Iyyer, M., et al.: The amazing mysteries of the gutter: drawing inferences between panels in comic book narratives. In: Proceedings - IEEE Conference on Computer Vision and Pattern Recognition, CVPR. vol. 2017-January, pp. 6478\u20136487. arXiv. https:\/\/doi.org\/10.1109\/CVPR.2017.686, https:\/\/www.scopus.com\/inward\/record.uri?eid=2-s2.0-85044502769&doi=10.1109%2fCVPR.2017.686 &partnerID=40 &md5=53fdaad2abea6dc7342a1e0639ddb132","DOI":"10.1109\/CVPR.2017.686"},{"key":"11_CR13","doi-asserted-by":"publisher","unstructured":"Khan, F.S., Anwer, R.M., van\u00a0de Weijer, J., Bagdanov, A.D., Vanrell, M., Lopez, A.M.: Color attributes for object detection. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3306\u20133313 (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6248068","DOI":"10.1109\/CVPR.2012.6248068"},{"key":"11_CR14","doi-asserted-by":"publisher","unstructured":"Le, T.N., et al.: Subgraph spotting in graph representations of comic book images 112, 118\u2013124. https:\/\/doi.org\/10.1016\/j.patrec.2018.06.017, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167865518302629","DOI":"10.1016\/j.patrec.2018.06.017"},{"key":"11_CR15","doi-asserted-by":"publisher","unstructured":"Li, Y., Aizawa, K., Matsui, Y.: Manga109Dialog A Large-scale Dialogue Dataset for Comics Speaker Detection. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2306.17469, http:\/\/arxiv.org\/abs\/2306.17469","DOI":"10.48550\/arXiv.2306.17469"},{"key":"11_CR16","unstructured":"Liu, S., et al.: Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection, http:\/\/arxiv.org\/abs\/2303.05499"},{"key":"11_CR17","doi-asserted-by":"publisher","unstructured":"Nguyen, N.V., Rigaud, C., Burie, J.C.: Comic characters detection using deep learning. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). vol.\u00a03, pp. 41\u201346. IEEE Computer Society. https:\/\/doi.org\/10.1109\/ICDAR.2017.290, http:\/\/ieeexplore.ieee.org\/document\/8270235\/","DOI":"10.1109\/ICDAR.2017.290"},{"key":"11_CR18","doi-asserted-by":"publisher","unstructured":"Nguyen, N.V., Rigaud, C., Burie, J.C.: Digital Comics Image Indexing Based on Deep Learning 4(7), \u00a089. https:\/\/doi.org\/10.3390\/jimaging4070089, https:\/\/www.mdpi.com\/2313-433X\/4\/7\/89","DOI":"10.3390\/jimaging4070089"},{"key":"11_CR19","doi-asserted-by":"publisher","unstructured":"Nguyen, N.V., Rigaud, C., Revel, A., Burie, J.C.: A learning approach with incomplete pixel-level labels for deep neural networks 130, 111\u2013125. https:\/\/doi.org\/10.1016\/j.neunet.2020.06.025, https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608020302409","DOI":"10.1016\/j.neunet.2020.06.025"},{"key":"11_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1007\/978-3-030-86337-1_51","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"N-V Nguyen","year":"2021","unstructured":"Nguyen, N.-V., Vu, X.-S., Rigaud, C., Jiang, L., Burie, J.-C.: ICDAR 2021 competition on multimodal emotion recognition on comics scenes. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12824, pp. 767\u2013782. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_51"},{"key":"11_CR21","doi-asserted-by":"publisher","unstructured":"Ogawa, T., Otsubo, A., Narita, R., Matsui, Y., Yamasaki, T., Aizawa, K.: Object Detection for Comics using Manga109 Annotations. arXiv.https:\/\/doi.org\/10.48550\/arXiv.1803.08670, http:\/\/arxiv.org\/abs\/1803.08670","DOI":"10.48550\/arXiv.1803.08670"},{"key":"11_CR22","doi-asserted-by":"publisher","unstructured":"Padilla, R., Passos, W.L., Dias, T.L.B., Netto, S.L., family=Silva, given=Eduardo A.\u00a0B., p.u.: A Comparative Analysis of Object Detection Metrics with a Companion Open-Source Toolkit 10(3), \u00a0279. https:\/\/doi.org\/10.3390\/electronics10030279, https:\/\/www.mdpi.com\/2079-9292\/10\/3\/279","DOI":"10.3390\/electronics10030279"},{"key":"11_CR23","doi-asserted-by":"publisher","unstructured":"Qin, X., Zhou, Y., He, Z., Wang, Y., Tang, Z.: A Faster R-CNN Based Method for Comic Characters Face Detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). vol.\u00a001, pp. 1074\u20131080. https:\/\/doi.org\/10.1109\/ICDAR.2017.178","DOI":"10.1109\/ICDAR.2017.178"},{"key":"11_CR24","doi-asserted-by":"publisher","unstructured":"Rigaud, C.: Segmentation and indexation of complex objects in comic book 14(3). https:\/\/doi.org\/10.5565\/rev\/elcvia.833, http:\/\/elcvia.cvc.uab.es\/article\/view\/v14-n3-rigaud","DOI":"10.5565\/rev\/elcvia.833"},{"key":"11_CR25","unstructured":"Sachdeva, R., Zisserman, A.: The Manga Whisperer: Automatically Generating Transcriptions for Comics, http:\/\/arxiv.org\/abs\/2401.10224"},{"key":"11_CR26","unstructured":"Shit, S., et al.: Relationformer: A Unified Framework for Image-to-Graph Generation, http:\/\/arxiv.org\/abs\/2203.10202"},{"key":"11_CR27","doi-asserted-by":"publisher","unstructured":"Sun, W., Burie, J.C., Ogier, J.M., Kise, K.: Specific comic character detection using local feature matching. In: 2013 12th International Conference on Document Analysis and Recognition. pp. 275\u2013279. https:\/\/doi.org\/10.1109\/ICDAR.2013.62, http:\/\/ieeexplore.ieee.org\/document\/6628627\/","DOI":"10.1109\/ICDAR.2013.62"},{"key":"11_CR28","unstructured":"Topal, B.B., Yuret, D., Sezgin, T.M.: DASS-Detector: Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings, http:\/\/arxiv.org\/abs\/2211.10641"},{"key":"11_CR29","unstructured":"Vivoli, E., Baeza, J.L., Llobet, E.V., Karatzas, D.: Multimodal Transformer for Comics Text-Cloze, http:\/\/arxiv.org\/abs\/2403.03719"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70645-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:10:19Z","timestamp":1725941419000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70645-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031706448","9783031706455"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70645-5_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"11 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"}}]}}