{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:50:25Z","timestamp":1777657825756,"version":"3.51.4"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,7,17]],"date-time":"2019-07-17T00:00:00Z","timestamp":1563321600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,17]],"date-time":"2019-07-17T00:00:00Z","timestamp":1563321600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10032-019-00330-3","type":"journal-article","created":{"date-parts":[[2019,7,17]],"date-time":"2019-07-17T08:03:36Z","timestamp":1563350616000},"page":"265-284","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Comic MTL: optimized multi-task learning for comic book image analysis"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2271-6918","authenticated-orcid":false,"given":"Nhu-Van","family":"Nguyen","sequence":"first","affiliation":[]},{"given":"Christophe","family":"Rigaud","sequence":"additional","affiliation":[]},{"given":"Jean-Christophe","family":"Burie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,17]]},"reference":[{"key":"330_CR1","doi-asserted-by":"crossref","unstructured":"Arai, K., Tolle, H.: Method for automatic e-comic scene frame extraction for reading comic on mobile devices. In: 7th International Conference on Information Technology: New Generations, ITNG, pp. 370\u2013375. IEEE Computer Society, Washington DC, USA (2010)","DOI":"10.1109\/ITNG.2010.22"},{"issue":"6","key":"330_CR2","first-page":"669","volume":"4","author":"K Arai","year":"2011","unstructured":"Arai, K., Tolle, H.: Method for real time text extraction of digital manga comic. Int. J. Image Process. 4(6), 669\u2013676 (2011)","journal-title":"Int. J. Image Process."},{"key":"330_CR3","doi-asserted-by":"crossref","unstructured":"Aramaki, Y., Matsui, Y., Yamasaki, T., Aizawa, K.: Text detection in manga by combining connected-component-based and region-based classifications. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 2901\u20132905 (2016)","DOI":"10.1109\/ICIP.2016.7532890"},{"key":"330_CR4","doi-asserted-by":"publisher","first-page":"87","DOI":"10.3390\/jimaging4070087","volume":"4","author":"O Augereau","year":"2018","unstructured":"Augereau, O., Iwata, M., Kise, K.: A survey of comics research in computer science. J. Imaging 4, 87 (2018)","journal-title":"J. Imaging"},{"key":"330_CR5","unstructured":"Baxter, J.: A model of inductive bias learning. J. Artif. Int. Res. 12(1), 149\u2013198 (2000). http:\/\/dl.acm.org\/citation.cfm?id=1622248.1622254"},{"key":"330_CR6","doi-asserted-by":"crossref","unstructured":"Bingel, J., Sogaard, A.: Identifying beneficial task relations for multi-task learning in deep neural networks. In: EACL (2017)","DOI":"10.18653\/v1\/E17-2026"},{"issue":"1","key":"330_CR7","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R.: Multitask learning. Mach. Learn. 28(1), 41\u201375 (1997). https:\/\/doi.org\/10.1023\/A:1007379606734","journal-title":"Mach. Learn."},{"key":"330_CR8","doi-asserted-by":"crossref","unstructured":"Chu, W.T., Cheng, W.C.: Manga-specific features and latent style model for manga style analysis. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1332\u20131336 (2016)","DOI":"10.1109\/ICASSP.2016.7471893"},{"key":"330_CR9","doi-asserted-by":"crossref","unstructured":"Chu, W.T., Li, W.W.: Manga facenet: Face detection in manga based on deep neural network. In: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, pp. 412\u2013415. ACM (2017)","DOI":"10.1145\/3078971.3079031"},{"key":"330_CR10","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: CVPR09 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"1","key":"330_CR11","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.M., Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"330_CR12","doi-asserted-by":"crossref","unstructured":"Fujino, S., Mori, N., Matsumoto, K.: Recognizing the order of four-scene comics by evolutionary deep learning. In: Distributed Computing and Artificial Intelligence, pp. 136\u2013144 (2015)","DOI":"10.1007\/978-3-319-94649-8_17"},{"key":"330_CR13","doi-asserted-by":"crossref","unstructured":"Gu\u00e9rin, C., Rigaud, C., Mercier, A., Ammar-Boudjelal, F., Bertet, K., Bouju, A., Burie, J.C., Louis, G., Ogier, J.M., Revel, A.: eBDtheque: A representative database of comics. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1145\u20131149 (2013)","DOI":"10.1109\/ICDAR.2013.232"},{"key":"330_CR14","doi-asserted-by":"crossref","unstructured":"Hashimoto, K., Xiong, C., Tsuruoka, Y., Socher, R.: A joint many-task model: Growing a neural network for multiple nlp tasks. In: EMNLP (2017)","DOI":"10.18653\/v1\/D17-1206"},{"key":"330_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. CoRR abs\/1703.06870 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"330_CR16","unstructured":"He, Z., Zhou, Y., Wang, Y., Tang, Z.: Sren: Shape regression network for comic storyboard extraction. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4\u20139, 2017, San Francisco, California, pp. 4937\u20134938 (2017)"},{"key":"330_CR17","doi-asserted-by":"crossref","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: ACM Multimedia (2018)","DOI":"10.1145\/3240508.3240555"},{"key":"330_CR18","doi-asserted-by":"crossref","unstructured":"Ho, A.K.N., Burie, J.C., Ogier, J.M.: Panel and Speech Balloon Extraction from Comic Books. 2012 10th IAPR International Workshop on Document Analysis Systems pp. 424\u2013428 (2012)","DOI":"10.1109\/DAS.2012.66"},{"key":"330_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Z., Li, J., Siniscalchi, S.M., Chen, I.F., Wu, J., Lee, C.H.: Rapid adaptation for deep neural networks through multi-task learning. In: INTERSPEECH (2015)","DOI":"10.21437\/Interspeech.2015-719"},{"issue":"2","key":"330_CR20","first-page":"216","volume":"5","author":"Y In","year":"2011","unstructured":"In, Y., Oie, T., Higuchi, M., Kawasaki, S., Koike, A., Murakami, H.: Fast frame decomposition and sorting by contour tracing for mobile phone comic images. Int. J. Syst. Appl. Eng. Dev. 5(2), 216\u2013223 (2011)","journal-title":"Int. J. Syst. Appl. Eng. Dev."},{"key":"330_CR21","unstructured":"Kaiser, L., Gomez, A.N., Shazeer, N., Vaswani, A., Parmar, N., Jones, L., Uszkoreit, J.: One model to learn them all. CoRR abs\/1706.05137 (2017)"},{"key":"330_CR22","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 7482\u20137491 (2018)"},{"key":"330_CR23","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)"},{"issue":"1","key":"330_CR24","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s11042-012-1241-7","volume":"69","author":"L Li","year":"2014","unstructured":"Li, L., Wang, Y., Tang, Z., Gao, L.: Automatic comic page segmentation based on polygon detection. Multimed. Tools Appl. 69(1), 171\u2013197 (2014)","journal-title":"Multimed. Tools Appl."},{"issue":"4","key":"330_CR25","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/s00371-015-1084-0","volume":"32","author":"X Liu","year":"2016","unstructured":"Liu, X., Li, C., Zhu, H., Wong, T.T., Xu, X.: Text-aware balloon extraction from manga. Vis. Comput. 32(4), 501\u2013511 (2016)","journal-title":"Vis. Comput."},{"key":"330_CR26","doi-asserted-by":"crossref","unstructured":"Liu, X., Wang, Y., Tang, Z.: A clump splitting based method to localize speech balloons in comics. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 901\u2013905 (2015)","DOI":"10.1109\/ICDAR.2015.7333892"},{"key":"330_CR27","doi-asserted-by":"crossref","unstructured":"Matsui, Y., Ito, K., Aramaki, Y., Yamasaki, T., Aizawa, K.: Sketch-based manga retrieval using Manga109 dataset. CoRR abs\/1510.04389 (2015)","DOI":"10.1007\/s11042-016-4020-z"},{"issue":"7","key":"330_CR28","doi-asserted-by":"publisher","first-page":"89","DOI":"10.3390\/jimaging4070089","volume":"4","author":"N Nguyen","year":"2018","unstructured":"Nguyen, N., Rigaud, C., Burie, J.: Digital comics image indexing based on deep learning. J. Imaging 4(7), 89 (2018)","journal-title":"J. Imaging"},{"key":"330_CR29","unstructured":"Nguyen, N.V., Rigaud, C., Burie, J.: Comic characters detection using deep learning. In: 2nd International Workshop on coMics Analysis, Processing, and Understanding, MANPU 2017, Kyoto, Japan, November 9\u201315, 2017, pp. 41\u201346 (2017)"},{"issue":"7","key":"330_CR30","doi-asserted-by":"publisher","first-page":"89","DOI":"10.3390\/jimaging4070089","volume":"4","author":"NV Nguyen","year":"2018","unstructured":"Nguyen, N.V., Rigaud, C., Burie, J.C.: Digital comics image indexing based on deep learning. J. Imaging 4(7), 89 (2018)","journal-title":"J. Imaging"},{"key":"330_CR31","unstructured":"Obispo, S.L., Kuboi, T.: Element detection in Japanese comic book panels (2014)"},{"key":"330_CR32","unstructured":"Ogawa, T., Otsubo, A., Narita, R., Matsui, Y., Yamasaki, T., Aizawa, K.: Object detection for comics using manga109 annotations. CoRR abs\/1803.08670 (2018). arXiv:1803.08670"},{"key":"330_CR33","doi-asserted-by":"crossref","unstructured":"Pang, X., Cao, Y., Lau, R.W., Chan, A.B.: A robust panel extraction method for manga. In: Proceedings of the 22nd ACM International Conference on Multimedia, MM \u201914, pp. 1125\u20131128. ACM, New York (2014)","DOI":"10.1145\/2647868.2654990"},{"key":"330_CR34","unstructured":"Plank, B., Alonso, H.M.: When is multitask learning effective? semantic sequence prediction under varying data conditions. In: EACL (2017)"},{"key":"330_CR35","doi-asserted-by":"crossref","unstructured":"Ponsard, C., Ramdoyal, R., Dziamski, D.: An OCR-enabled digital comic books viewer. In: Computers Helping People with Special Needs, pp. 471\u2013478. Springer (2012)","DOI":"10.1007\/978-3-642-31522-0_71"},{"key":"330_CR36","doi-asserted-by":"crossref","unstructured":"Qin, X., Zhou, Y., He, Z., Wang, Y., Tang, Z.: A faster r-cnn based method for comic characters face detection. 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 1074\u20131080 (2017)","DOI":"10.1109\/ICDAR.2017.178"},{"key":"330_CR37","first-page":"91","volume-title":"Advances in Neural Information Processing Systems","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28, pp. 91\u201399. Curran Associates Inc, Red Hook (2015)"},{"key":"330_CR38","unstructured":"Rigaud, C., Burie, J., Ogier, J.: Segmentation-free speech text recognition for comic books. In: 2nd International Workshop on coMics Analysis, Processing, and Understanding, 2017, Kyoto, Japan, November 9-15, pp. 29\u201334 (2017)"},{"key":"330_CR39","doi-asserted-by":"crossref","unstructured":"Rigaud, C., Burie, J.C., Ogier, J.M.: Text-independent speech balloon segmentation for comics and manga. In: Graphic Recognition. Current Trends and Challenges: 11th International Workshop, GREC 2015, Nancy, France, pp. 133\u2013147. Cham (2017)","DOI":"10.1007\/978-3-319-52159-6_10"},{"issue":"3","key":"330_CR40","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/s10032-015-0243-1","volume":"18","author":"C Rigaud","year":"2015","unstructured":"Rigaud, C., Gu\u00e9rin, C., Karatzas, D., Burie, J.C., Ogier, J.M.: Knowledge-driven understanding of images in comic books. Int. J. Doc. Anal. Recogn. 18(3), 199\u2013221 (2015)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"330_CR41","doi-asserted-by":"crossref","unstructured":"Rigaud, C., Karatzas, D., Van\u00a0de Weijer, J., Burie, J.C., Ogier, J.M.: An active contour model for speech balloon detection in comics. In: Proceedings of the 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 1240\u20131244 (2013)","DOI":"10.1109\/ICDAR.2013.251"},{"key":"330_CR42","unstructured":"Rigaud, C., Karatzas, D., Van\u00a0de Weijer, J., Burie, J.C., Ogier, J.M.: Automatic text localisation in scanned comic books. In: Proceedings of the 8th International Conference on Computer Vision Theory and Applications (VISAPP) (2013)"},{"key":"330_CR43","doi-asserted-by":"crossref","unstructured":"Rigaud, C., Thanh, N.L., Burie, J.., Ogier, J.., 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 (2015)","DOI":"10.1109\/ICDAR.2015.7333782"},{"key":"330_CR44","doi-asserted-by":"crossref","unstructured":"Rigaud, C., Tsopze, N., Burie, J.C., Ogier, J.M.: Robust frame and text extraction from comic books. In: Graphics Recognition. New Trends and Challenges, vol. 7423, pp. 129\u2013138. Springer, Berlin (2013)","DOI":"10.1007\/978-3-642-36824-0_13"},{"key":"330_CR45","doi-asserted-by":"crossref","unstructured":"Stommel, M., Merhej, L.I., M\u00fcller, M.G.: Segmentation-free detection of comic panels. In: Computer Vision and Graphics, pp. 633\u2013640. Springer (2012)","DOI":"10.1007\/978-3-642-33564-8_76"},{"key":"330_CR46","doi-asserted-by":"crossref","unstructured":"Sun, W., Burie, J.C., Ogier, J.M., Kise, K.: Specific comic character detection using local feature matching. In: 12th International Conference on Document Analysis and Recognition, pp. 275\u2013279. Washington, DC (2013)","DOI":"10.1109\/ICDAR.2013.62"},{"key":"330_CR47","unstructured":"Tanaka, T., Shoji, K., Toyama, F., Miyamichi, J.: Layout analysis of tree-structured scene frames in comic images. In: IJCAI\u201907, pp. 2885\u20132890 (2007)"},{"issue":"6","key":"330_CR48","first-page":"1370","volume":"87\u2013D","author":"M Yamada","year":"2004","unstructured":"Yamada, M., Budiarto, R., Endo, M., Miyazaki, S.: Comic image decomposition for reading comics on cellular phones. IEICE Trans. 87\u2013D(6), 1370\u20131376 (2004)","journal-title":"IEICE Trans."},{"key":"330_CR49","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W.B., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: Disentangling task transfer learning. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 3712\u20133722 (2018)","DOI":"10.1109\/CVPR.2018.00391"},{"key":"330_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, W., Wang, B., Ye, J., Yang, M., Zhao, Z., Luo, R., Qiao, Y.: A multi-task learning approach for image captioning. In: IJCAI (2018)","DOI":"10.24963\/ijcai.2018\/168"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-019-00330-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-019-00330-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-019-00330-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,24]],"date-time":"2022-09-24T01:25:00Z","timestamp":1663982700000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-019-00330-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,17]]},"references-count":50,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["330"],"URL":"https:\/\/doi.org\/10.1007\/s10032-019-00330-3","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,17]]},"assertion":[{"value":"15 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}