{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T11:56:46Z","timestamp":1775303806895,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030057152","type":"print"},{"value":"9783030057169","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,12,11]],"date-time":"2018-12-11T00:00:00Z","timestamp":1544486400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-05716-9_57","type":"book-chapter","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T14:17:32Z","timestamp":1544451452000},"page":"637-649","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Multi-task Model for Comic Book Image Analysis"],"prefix":"10.1007","author":[{"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":[[2018,12,11]]},"reference":[{"issue":"11","key":"57_CR1","doi-asserted-by":"publisher","first-page":"1949","DOI":"10.1109\/TMM.2015.2477680","volume":"17","author":"AH Abdulnabi","year":"2015","unstructured":"Abdulnabi, A.H., Wang, G., Lu, J., Jia, K.: Multi-task CNN model for attribute prediction. IEEE Trans. Multimedia 17(11), 1949\u20131959 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"57_CR2","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, pp. 370\u2013375. IEEE Computer Society, Washington DC (2010)","DOI":"10.1109\/ITNG.2010.22"},{"issue":"6","key":"57_CR3","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. (IJIP) 4(6), 669\u2013676 (2011)","journal-title":"Int. J. Image Process. (IJIP)"},{"key":"57_CR4","doi-asserted-by":"crossref","unstructured":"Augereau, O., Iwata, M., Kise, K.: A survey of comics research in computer science. J. Imaging 4 (2018)","DOI":"10.3390\/jimaging4070087"},{"key":"57_CR5","doi-asserted-by":"crossref","unstructured":"Chu, W.T., Cheng, W.C.: Manga-specific features and latent style model formanga style analysis. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1332\u20131336, March 2016","DOI":"10.1109\/ICASSP.2016.7471893"},{"key":"57_CR6","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"},{"issue":"1","key":"57_CR7","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. Vision 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"57_CR8","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/978-3-319-94649-8_17","volume-title":"Distributed Computing and Artificial Intelligence, 15th International Conference","author":"S Fujino","year":"2019","unstructured":"Fujino, S., Mori, N., Matsumoto, K.: Recognizing the order of four-scene comics by evolutionary deep learning. In: De La Prieta, F., Omatu, S., Fern\u00e1ndez-Caballero, A. (eds.) DCAI 2018. AISC, vol. 800, pp. 136\u2013144. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-319-94649-8_17"},{"key":"57_CR9","doi-asserted-by":"crossref","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, August 2013","DOI":"10.1109\/ICDAR.2013.232"},{"key":"57_CR10","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":"57_CR11","doi-asserted-by":"crossref","unstructured":"Ho, A.K.N., Burie, J.C., Ogier, J.M.: Panel and speech balloon extraction from comic books. In: 2012 10th IAPR International Workshop on Document Analysis Systems, pp. 424\u2013428, March 2012","DOI":"10.1109\/DAS.2012.66"},{"issue":"2","key":"57_CR12","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."},{"issue":"1","key":"57_CR13","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. Multimedia Tools Appl. 69(1), 171\u2013197 (2014)","journal-title":"Multimedia Tools Appl."},{"issue":"4","key":"57_CR14","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. Computer 32(4), 501\u2013511 (2016)","journal-title":"Vis. Computer"},{"key":"57_CR15","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"},{"key":"57_CR16","doi-asserted-by":"crossref","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, 9\u201315 November 2017, pp. 41\u201346 (2017)","DOI":"10.1109\/ICDAR.2017.290"},{"issue":"7","key":"57_CR17","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":"57_CR18","unstructured":"Obispo, S.L., Kuboi, T.: Element detection in Japanese comic book panels (2014)"},{"key":"57_CR19","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)"},{"key":"57_CR20","doi-asserted-by":"crossref","unstructured":"Pang, X., Cao, Y., Lau, R.W., Chan, A.B.: A robust panel extraction method formanga. In: Proceedings of the 22nd ACM International Conference on Multimedia, MM 2014, pp. 1125\u20131128. ACM, New York (2014)","DOI":"10.1145\/2647868.2654990"},{"key":"57_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/978-3-642-31522-0_71","volume-title":"Computers Helping People with Special Needs","author":"C Ponsard","year":"2012","unstructured":"Ponsard, C., Ramdoyal, R., Dziamski, D.: An OCR-enabled digital comic books viewer. In: Miesenberger, K., Karshmer, A., Penaz, P., Zagler, W. (eds.) ICCHP 2012. LNCS, vol. 7382, pp. 471\u2013478. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31522-0_71"},{"key":"57_CR22","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 28, pp. 91\u201399. Curran Associates, Inc. (2015)"},{"key":"57_CR23","doi-asserted-by":"crossref","unstructured":"Rigaud, C., et al.: Speech balloon and speaker association for comics and manga understanding. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 351\u2013355, August 2015","DOI":"10.1109\/ICDAR.2015.7333782"},{"key":"57_CR24","doi-asserted-by":"crossref","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, Kyoto, Japan, 9\u201315 November, pp. 29\u201334 (2017)","DOI":"10.1109\/ICDAR.2017.288"},{"key":"57_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/978-3-319-52159-6_10","volume-title":"Graphic Recognition. Current Trends and Challenges","author":"C Rigaud","year":"2017","unstructured":"Rigaud, C., Burie, J.-C., Ogier, J.-M.: Text-independent speech balloon segmentation for comics and manga. In: Lamiroy, B., Dueire Lins, R. (eds.) GREC 2015. LNCS, vol. 9657, pp. 133\u2013147. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-52159-6_10"},{"issue":"3","key":"57_CR26","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. (IJDAR) 18(3), 199\u2013221 (2015)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"57_CR27","doi-asserted-by":"crossref","unstructured":"Rigaud, C., Karatzas, D., Van de 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, August 2013","DOI":"10.1109\/ICDAR.2013.251"},{"key":"57_CR28","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":"57_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/978-3-642-36824-0_13","volume-title":"Graphics Recognition. New Trends and Challenges","author":"C Rigaud","year":"2013","unstructured":"Rigaud, C., Tsopze, N., Burie, J.-C., Ogier, J.-M.: Robust frame and text extraction from comic books. In: Kwon, Y.-B., Ogier, J.-M. (eds.) GREC 2011. LNCS, vol. 7423, pp. 129\u2013138. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-36824-0_13"},{"key":"57_CR30","unstructured":"Singh, S.P., Markovitch, S. (eds.): Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 4\u20139 February 2017, San Francisco, California, USA (2017)"},{"key":"57_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1007\/978-3-642-33564-8_76","volume-title":"Computer Vision and Graphics","author":"M Stommel","year":"2012","unstructured":"Stommel, M., Merhej, L.I., M\u00fcller, M.G.: Segmentation-free detection of comic panels. In: Bolc, L., Tadeusiewicz, R., Chmielewski, L.J., Wojciechowski, K. (eds.) ICCVG 2012. LNCS, vol. 7594, pp. 633\u2013640. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33564-8_76"},{"key":"57_CR32","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, Washington, DC, USA, pp. 275\u2013279 (2013)","DOI":"10.1109\/ICDAR.2013.62"},{"key":"57_CR33","first-page":"1370","volume":"87\u2013D(6)","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":"57_CR34","doi-asserted-by":"crossref","unstructured":"Yim, J., Jung, H., Yoo, B., Choi, C., Park, D., Kim, J.: Rotating your face using multi-task deep neural network. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 676\u2013684, June 2015","DOI":"10.1109\/CVPR.2015.7298667"},{"key":"57_CR35","unstructured":"Zhang, Y., Yang, Q.: A survey on multi-task learning. CoRR abs\/1707.08114 (2017). http:\/\/arxiv.org\/abs\/1707.08114"},{"key":"57_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/978-3-319-10599-4_7","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Z Zhang","year":"2014","unstructured":"Zhang, Z., Luo, P., Loy, C.C., Tang, X.: Facial landmark detection by deep multi-task learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 94\u2013108. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_7"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05716-9_57","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T11:02:38Z","timestamp":1775300558000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05716-9_57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,11]]},"ISBN":["9783030057152","9783030057169"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05716-9_57","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,11]]},"assertion":[{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thessaloniki","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/mmm2019.iti.gr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double blind for full papers and workshop papers, single blind for other paper types","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"204","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"96","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"47% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.67","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"6 demonstration papers, 5 industry papers, 6 workshop papers, and 6 Video Browser Showdown papers were also accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}