{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:50:54Z","timestamp":1777657854984,"version":"3.51.4"},"publisher-location":"Cham","reference-count":26,"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_16","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"257-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ComicBERT: A Transformer Model and\u00a0Pre-training Strategy for\u00a0Contextual Understanding in\u00a0Comics"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8695-7860","authenticated-orcid":false,"given":"G\u00fcrkan","family":"Soykan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7039-0046","authenticated-orcid":false,"given":"Deniz","family":"Yuret","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1524-1646","authenticated-orcid":false,"given":"Tevfik Metin","family":"Sezgin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, H., Mishra, A., Gupta, M., et\u00a0al.: Multimodal persona based generation of comic dialogs. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 14150\u201314164 (2023)","DOI":"10.18653\/v1\/2023.acl-long.791"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Augereau, O., Iwata, M., Kise, K.: An overview of comics research in computer science. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). vol.\u00a03, pp. 54\u201359. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.292"},{"issue":"2","key":"16_CR3","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1080\/21504857.2010.528638","volume":"1","author":"C Brienza","year":"2010","unstructured":"Brienza, C.: Producing comics culture: a sociological approach to the study of comics. J. Graph. Novels Comics 1(2), 105\u2013119 (2010)","journal-title":"J. Graph. Novels Comics"},{"key":"16_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations (2020). arXiv preprint arXiv:2002.05709"},{"key":"16_CR5","unstructured":"Cohn, N.: The Visual Language of Comics: Introduction to the Structure and Cognition of Sequential Images. A &C Black (2013)"},{"key":"16_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding (2019)"},{"key":"16_CR7","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":"16_CR8","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs) (2016). arXiv preprint arXiv:1606.08415"},{"issue":"1","key":"16_CR9","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/s11858-010-0290-5","volume":"43","author":"P Herbst","year":"2011","unstructured":"Herbst, P., Chazan, D., Chen, C.L., Chieu, V.M., Weiss, M.: Using comics-based representations of teaching, and technology, to bring practice to teacher education courses. ZDM 43(1), 91\u2013103 (2011)","journal-title":"ZDM"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Iyyer, M., et al.: The amazing mysteries of the gutter: Drawing inferences between panels in comic book narratives (2017)","DOI":"10.1109\/CVPR.2017.686"},{"issue":"1","key":"16_CR11","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3390\/technologies9010002","volume":"9","author":"A Jaiswal","year":"2020","unstructured":"Jaiswal, A., Babu, A.R., Zadeh, M.Z., Banerjee, D., Makedon, F.: A survey on contrastive self-supervised learning. Technologies 9(1), 2 (2020)","journal-title":"Technologies"},{"issue":"1","key":"16_CR12","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1111\/tops.12476","volume":"12","author":"J Laubrock","year":"2020","unstructured":"Laubrock, J., Dunst, A.: Computational approaches to comics analysis. Top. Cogn. Sci. 12(1), 274\u2013310 (2020)","journal-title":"Top. Cogn. Sci."},{"key":"16_CR13","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2017). arXiv preprint arXiv:1711.05101"},{"key":"16_CR14","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/s10032-019-00330-3","volume":"22","author":"NV Nguyen","year":"2019","unstructured":"Nguyen, N.V., Rigaud, C., Burie, J.C.: Comic MTL: optimized multi-task learning for comic book image analysis. Int. J. Doc. Anal. Recogn. (IJDAR) 22, 265\u2013284 (2019)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"16_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1007\/978-3-030-86331-9_27","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"N-V Nguyen","year":"2021","unstructured":"Nguyen, N.-V., Rigaud, C., Revel, A., Burie, J.-C.: Manga-MMTL: multimodal multitask transfer learning for manga character analysis. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 410\u2013425. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_27"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (2019). https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"16_CR17","doi-asserted-by":"publisher","unstructured":"Sachdeva, R., Zisserman, A.: The manga whisperer: Automatically generating transcriptions for comics. CoRR abs\/2401.10224 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2401.10224","DOI":"10.48550\/ARXIV.2401.10224"},{"key":"16_CR18","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter (2019). ArXiv abs\/1910.01108"},{"key":"16_CR19","unstructured":"Soykan, G., Yuret, D., Sezgin, T.M.: A comprehensive gold standard and benchmark for comics text detection and recognition (2022)"},{"key":"16_CR20","unstructured":"Soykan, G., Yuret, D., Sezgin, T.M.: Identity-aware semi-supervised learning for comic character re-identification (2023)"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Su, Y., et al.: TaCL: Improving BERT pre-training with token-aware contrastive learning (2021). arXiv preprint arXiv:2111.04198","DOI":"10.18653\/v1\/2022.findings-naacl.191"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Sunder, V., Fosler-Lussier, E., Thomas, S., Kuo, H.K.J., Kingsbury, B.: Tokenwise contrastive pretraining for finer speech-to-BERT alignment in end-to-end speech-to-intent systems (2022). arXiv preprint arXiv:2204.05188","DOI":"10.21437\/Interspeech.2022-239"},{"key":"16_CR23","unstructured":"Tan, M., Le, Q.: EfficientNet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"16_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"16_CR25","unstructured":"Wolf, T., et\u00a0al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345 (2020)"},{"issue":"10","key":"16_CR26","doi-asserted-by":"publisher","first-page":"12113","DOI":"10.1109\/TPAMI.2023.3275156","volume":"45","author":"P Xu","year":"2023","unstructured":"Xu, P., Zhu, X., Clifton, D.A.: Multimodal learning with transformers: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(10), 12113\u201312132 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3275156","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"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_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:11:06Z","timestamp":1725941466000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70645-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031706448","9783031706455"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70645-5_16","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":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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"}}]}}