{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:19:10Z","timestamp":1780463950459,"version":"3.54.1"},"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_15","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"231-256","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Spatially Augmented Speech Bubble to\u00a0Character Association via\u00a0Comic Multi-task Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8695-7860","authenticated-orcid":false,"given":"G\u00fcrkan","family":"Soykan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7039-0046","authenticated-orcid":false,"given":"Deniz","family":"Yuret","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1524-1646","authenticated-orcid":false,"given":"Tevfik Metin","family":"Sezgin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"15_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":"15_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":"1","key":"15_CR3","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1147\/sj.41.0025","volume":"4","author":"JE Bresenham","year":"1965","unstructured":"Bresenham, J.E.: Algorithm for computer control of a digital plotter. IBM Syst. J. 4(1), 25\u201330 (1965)","journal-title":"IBM Syst. J."},{"issue":"2","key":"15_CR4","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":"15_CR5","unstructured":"Cohn, N.: The Visual Language of Comics: Introduction to the Structure and Cognition of Sequential Images. A &C Black (2013)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale (2020). arXiv preprint arXiv:2010.11929"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"issue":"1","key":"15_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":"15_CR10","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"issue":"1","key":"15_CR11","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":"15_CR12","unstructured":"Li, Y., Xie, S., Chen, X., Doll\u00e1r, P., He, K., Girshick, R.B.: Benchmarking detection transfer learning with vision transformers (2021). CoRR abs\/2111.11429, https:\/\/arxiv.org\/abs\/2111.11429"},{"key":"15_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"15_CR14","unstructured":"Loshchilov, I., Hutter, F.: SGDR: Stochastic gradient descent with warm restarts (2016). arXiv preprint arXiv:1608.03983"},{"key":"15_CR15","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2017). arXiv preprint arXiv:1711.05101"},{"key":"15_CR16","doi-asserted-by":"publisher","unstructured":"Nguyen, N.V., Rigaud, C., Burie, J.C.: Digital comics image indexing based on deep learning. J. Imaging 4(7), 89 (2018). https:\/\/doi.org\/10.3390\/jimaging4070089, http:\/\/www.mdpi.com\/2313-433X\/4\/7\/89","DOI":"10.3390\/jimaging4070089"},{"key":"15_CR17","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":"15_CR18","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":"15_CR19","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 (2015)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Rigaud, C., Le\u00a0Thanh, N., Burie, J.C., Ogier, J.M., Iwata, M., Imazu, E., Kise, K.: Speech balloon and speaker association for comics and manga understanding. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 351\u2013355. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333782"},{"key":"15_CR21","doi-asserted-by":"publisher","unstructured":"Sachdeva, R., Zisserman, A.: The manga whisperer: Automatically generating transcriptions for comics (2024). CoRR abs\/2401.10224. https:\/\/doi.org\/10.48550\/ARXIV.2401.10224","DOI":"10.48550\/ARXIV.2401.10224"},{"key":"15_CR22","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"15_CR23","unstructured":"Soykan, G., Yuret, D., Sezgin, T.M.: A comprehensive gold standard and benchmark for comics text detection and recognition (2022)"},{"key":"15_CR24","unstructured":"Soykan, G., Yuret, D., Sezgin, T.M.: Identity-aware semi-supervised learning for comic character re-identification (2023)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., Liu, W.: Learning to compose dynamic tree structures for visual contexts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern recognition, pp. 6619\u20136628 (2019)","DOI":"10.1109\/CVPR.2019.00678"},{"key":"15_CR26","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"}],"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_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:10:54Z","timestamp":1725941454000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70645-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031706448","9783031706455"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70645-5_15","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"}}]}}