{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T11:38:58Z","timestamp":1763811538650,"version":"3.41.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705519"},{"type":"electronic","value":"9783031705526"}],"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\/978-3-031-70552-6_8","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"128-145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multimodal Transformer for\u00a0Comics Text-Cloze"],"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\/0009-0007-9736-9048","authenticated-orcid":false,"given":"Joan","family":"Lafuente Baeza","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0368-9697","authenticated-orcid":false,"given":"Ernest","family":"Valveny Llobet","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":"8_CR1","doi-asserted-by":"publisher","unstructured":"Baek, J., Matsui, Y., Aizawa, K.: COO\/comic onomatopoeia dataset for recognizing arbitrary or truncated texts. arXiv (2022). https:\/\/doi.org\/10.48550\/arXiv.2207.04675","DOI":"10.48550\/arXiv.2207.04675"},{"key":"8_CR2","doi-asserted-by":"publisher","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9357\u20139366. IEEE, Long Beach, CA, USA (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00959","DOI":"10.1109\/CVPR.2019.00959"},{"key":"8_CR3","unstructured":"Chen, J., et al.: MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning (2023)"},{"key":"8_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations (2020)"},{"key":"8_CR5","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna"},{"key":"8_CR6","doi-asserted-by":"publisher","unstructured":"Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation (2021). https:\/\/doi.org\/10.48550\/arXiv.2102.02779","DOI":"10.48550\/arXiv.2102.02779"},{"key":"8_CR7","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., et al.: ViT: an image is worth 16x16 words: transformers for image recognition at scale (2021). https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"8_CR8","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 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.286","DOI":"10.1109\/ICDAR.2017.286"},{"issue":"4","key":"8_CR9","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/s10032-022-00412-9","volume":"25","author":"A Dutta","year":"2022","unstructured":"Dutta, A., Biswas, S., Das, A.K.: BCBId: first bangla comic dataset and its applications. Int. J. Doc. Anal. Recogn. (IJDAR) 25(4), 265\u2013279 (2022). https:\/\/doi.org\/10.1007\/s10032-022-00412-9","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"8_CR10","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 (2016). https:\/\/doi.org\/10.1145\/3011549.3011551","DOI":"10.1145\/3011549.3011551"},{"key":"8_CR11","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 (2013). https:\/\/doi.org\/10.1109\/ICDAR.2013.232","DOI":"10.1109\/ICDAR.2013.232"},{"key":"8_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 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.686","DOI":"10.1109\/CVPR.2017.686"},{"key":"8_CR13","doi-asserted-by":"publisher","unstructured":"Kirillov, A., et al.: SAM: segment anything (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.02643","DOI":"10.48550\/arXiv.2304.02643"},{"key":"8_CR14","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models (2023)"},{"key":"8_CR15","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":"8_CR16","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":"2023","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. LNCS, vol. 13644, pp. 48\u201360. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-37742-6_4"},{"issue":"1","key":"8_CR17","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/TPC.1998.661632","volume":"41","author":"S McCloud","year":"1998","unstructured":"McCloud, S.: Understanding comics: the invisible art. IEEE Trans. Prof. Commun. 41(1), 66\u201369 (1998). https:\/\/doi.org\/10.1109\/TPC.1998.661632","journal-title":"IEEE Trans. Prof. Commun."},{"key":"8_CR18","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"key":"8_CR19","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"8_CR20","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer (2020)"},{"key":"8_CR21","doi-asserted-by":"publisher","unstructured":"Raisi, Z., Naiel, M.A., Fieguth, P., Wardell, S., Zelek, J.: Text detection and recognition in the wild: a review (2020). https:\/\/doi.org\/10.48550\/arXiv.2006.04305","DOI":"10.48550\/arXiv.2006.04305"},{"key":"8_CR22","doi-asserted-by":"publisher","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks (2016). https:\/\/doi.org\/10.48550\/arXiv.1506.01497","DOI":"10.48550\/arXiv.1506.01497"},{"key":"8_CR23","doi-asserted-by":"publisher","unstructured":"Soykan, G., Yuret, D., Sezgin, T.M.: A comprehensive gold standard and benchmark for comics text detection and recognition (2022). https:\/\/doi.org\/10.48550\/ARXIV.2212.14674","DOI":"10.48550\/ARXIV.2212.14674"},{"key":"8_CR24","doi-asserted-by":"publisher","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models (2023). https:\/\/doi.org\/10.48550\/arXiv.2302.13971","DOI":"10.48550\/arXiv.2302.13971"},{"key":"8_CR25","doi-asserted-by":"publisher","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models (2023). https:\/\/doi.org\/10.48550\/arXiv.2307.09288","DOI":"10.48550\/arXiv.2307.09288"},{"key":"8_CR26","doi-asserted-by":"publisher","unstructured":"Vaswani, A., et al.: Attention is all you need (2017). https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"8_CR27","unstructured":"Wang, J., et al.: GIT: a generative image-to-text transformer for vision and language (2022)"},{"key":"8_CR28","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"8_CR29","unstructured":"Yang, Z., et al.: Crossing the format boundary of text and boxes: towards unified vision-language modeling. arXiv (2021)"},{"key":"8_CR30","doi-asserted-by":"publisher","unstructured":"Ye, F., Long, Y., Feng, F., Wang, X.: Whether you can locate or not? Interactive referring expression generation. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 4697\u20134706 (2023). https:\/\/doi.org\/10.1145\/3581783.3612214","DOI":"10.1145\/3581783.3612214"},{"issue":"7","key":"8_CR31","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2015","unstructured":"Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1480\u20131500 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2014.2366765","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR32","doi-asserted-by":"publisher","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.10592","DOI":"10.48550\/arXiv.2304.10592"},{"issue":"1","key":"8_CR33","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu, Y., Yao, C., Bai, X.: Scene text detection and recognition: recent advances and future trends. Front. Comput. Sci. 10(1), 19\u201336 (2016). https:\/\/doi.org\/10.1007\/s11704-015-4488-0","journal-title":"Front. Comput. Sci."}],"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\/978-3-031-70552-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:07:12Z","timestamp":1749996432000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70552-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705519","9783031705526"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70552-6_8","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":"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"}}]}}