{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T11:10:24Z","timestamp":1775301024813,"version":"3.50.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030057091","type":"print"},{"value":"9783030057107","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,12,8]],"date-time":"2018-12-08T00:00:00Z","timestamp":1544227200000},"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\/978-3-030-05710-7_25","type":"book-chapter","created":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T07:48:55Z","timestamp":1544168935000},"page":"300-311","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Character Prediction in TV Series via a Semantic Projection Network"],"prefix":"10.1007","author":[{"given":"Ke","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiasong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianxu","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bozhi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoping","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,8]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., Bach, F., Laptev, I., Ponce, J., Schmid, C., Sivic, J.: Finding actors and actions in movies. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 2280\u20132287. IEEE (2013)","DOI":"10.1109\/ICCV.2013.283"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Cour, T., Sapp, B., Nagle, A., Taskar, B.: Talking pictures: temporal grouping and dialog-supervised person recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1014\u20131021 (2011)","DOI":"10.1109\/CVPR.2010.5540106"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Cour, T., Sapp, B., Jordan, C., Taskar, B.: Learning from ambiguously labeled images. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 919\u2013926 (2009)","DOI":"10.1109\/CVPR.2009.5206667"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Cour, T., Sapp, B., Nagle, A., Taskar, B.: Talking pictures: temporal grouping and dialog-supervised person recognition. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1014\u20131021. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540106"},{"key":"25_CR5","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: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Dong, Z., Jia, S., Wu, T., Pei, M.: Face video retrieval via deep learning of binary hash representations. In: AAAI, pp. 3471\u20133477 (2016)","DOI":"10.1609\/aaai.v30i1.10445"},{"key":"25_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"},{"issue":"C","key":"25_CR8","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1016\/j.neucom.2015.05.039","volume":"168","author":"Z He","year":"2015","unstructured":"He, Z., Chen, C., Bu, J., Li, P., Cai, D.: Multi-view based multi-label propagation for image annotation. Neurocomputing 168(C), 853\u2013860 (2015)","journal-title":"Neurocomputing"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Iwata, M., Ito, A., Kise, K.: A study to achieve manga character retrieval method for manga images. In: 2014 11th IAPR International Workshop on Document Analysis Systems (DAS), pp. 309\u2013313. IEEE (2014)","DOI":"10.1109\/DAS.2014.60"},{"key":"25_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Kostinger, M., Wohlhart, P., Roth, P.M., Bischof, H.: Learning to recognize faces from videos and weakly related information cues. In: IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 23\u201328 (2011)","DOI":"10.1109\/AVSS.2011.6027287"},{"key":"25_CR12","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. M.Sc. thesis, University of Toronto (2009)"},{"key":"25_CR13","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Li, C., Kang, Q., Ge, G., Song, Q., Lu, H., Cheng, J.: Deepbe: learning deep binary encoding for multi-label classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 39\u201346 (2016)","DOI":"10.1109\/CVPRW.2016.98"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, R., Cui, Z., Shan, S., Chen, X.: Compact video code and its application to robust face retrieval in tv-series. In: BMVC (2014)","DOI":"10.5244\/C.28.93"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, R., Shan, S., Chen, X.: Hierarchical hybrid statistic based video binary code and its application to face retrieval in tv-series. In: 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), vol. 1, pp. 1\u20138. IEEE (2015)","DOI":"10.1109\/FG.2015.7163089"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Zisserman, A.: From benedict cumberbatch to sherlock holmes: Character identification in tv series without a script. CoRR abs\/1801.10442 (2017)","DOI":"10.5244\/C.31.107"},{"key":"25_CR18","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/978-3-662-44851-9_28","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"J Nam","year":"2014","unstructured":"Nam, J., Kim, J., Loza Menc\u00eda, E., Gurevych, I., F\u00fcrnkranz, J.: Large-scale multi-label text classification\u2014revisiting neural networks. In: Calders, T., Esposito, F., H\u00fcllermeier, E., Meo, R. (eds.) ECML PKDD 2014. LNCS (LNAI), vol. 8725, pp. 437\u2013452. Springer, Heidelberg (2014). https:\/\/doi.org\/10.1007\/978-3-662-44851-9_28"},{"key":"25_CR19","unstructured":"Parkhi, O.M., Rahtu, E., Zisserman, A.: It\u2019s in the bag: stronger supervision for automated face labelling. In: ICCV Workshop, vol. 2, p. 6 (2015)"},{"key":"25_CR20","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch. In: NIPS-W (2017)"},{"issue":"1","key":"25_CR21","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1109\/TPAMI.2016.2537320","volume":"39","author":"J Pont-Tuset","year":"2015","unstructured":"Pont-Tuset, J., Arbel\u00e1ez, P., Barron, J.T., Marques, F., Malik, J.: Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE Trans. Pattern Anal. Mach. Intell. 39(1), 128\u2013140 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/978-3-319-10590-1_7","volume-title":"Computer Vision \u2013 ECCV 2014","author":"V Ramanathan","year":"2014","unstructured":"Ramanathan, V., Joulin, A., Liang, P., Fei-Fei, L.: Linking people in videos with \u201ctheir\u201d names using coreference resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 95\u2013110. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_7"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 512\u2013519 (2014)","DOI":"10.1109\/CVPRW.2014.131"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Rifai, S., Vincent, P., Muller, X., Glorot, X., Bengio, Y.: Contractive auto-encoders: explicit invariance during feature extraction. In: ICML (2011)","DOI":"10.1007\/978-3-642-23783-6_41"},{"key":"25_CR25","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1007\/978-3-642-12900-1_9","volume":"287","author":"C Shan","year":"2010","unstructured":"Shan, C.: Face recognition and retrieval in video. Stud. Comput. Intell. 287, 235\u2013260 (2010)","journal-title":"Stud. Comput. Intell."},{"issue":"8","key":"25_CR26","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888\u2013905 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR27","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Sivic, J., Everingham, M., Zisserman, A.: \u201cwho are you?\"- learning person specific classifiers from video. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 1145\u20131152. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206513"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., B\u00e4uml, M., Stiefelhagen, R.: Story-based video retrieval in TV series using plot synopses. In: Proceedings of International Conference on Multimedia Retrieval, p. 137. ACM (2014)","DOI":"10.1145\/2578726.2578727"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Bauml, M., Stiefelhagen, R.: Storygraphs: visualizing character interactions as a timeline. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 827\u2013834 (2014)","DOI":"10.1109\/CVPR.2014.111"},{"issue":"3","key":"25_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/jdwm.2007070101","volume":"3","author":"G Tsoumakas","year":"2007","unstructured":"Tsoumakas, G., Katakis, I.: Multi-label classification: an overview. Int. J. Data Warehous. Min. (IJDWM) 3(3), 1\u201313 (2007)","journal-title":"Int. J. Data Warehous. Min. (IJDWM)"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, Y., Mao, J., Huang, Z., Huang, C., Xu, W.: CNN-RNN: a unified framework for multi-label image classification. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2285\u20132294. IEEE (2016)","DOI":"10.1109\/CVPR.2016.251"},{"key":"25_CR33","unstructured":"Wei, Y., et al.: CNN: single-label to multi-label. arXiv preprint arXiv:1406.5726 (2014)"},{"issue":"9","key":"25_CR34","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1109\/TPAMI.2015.2491929","volume":"38","author":"Y Wei","year":"2016","unstructured":"Wei, Y., et al.: HCP: A flexible CNN framework for multi-label image classification. IEEE Trans. Pattern Anal. Mach. Intell. 38(9), 1901\u20131907 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1007\/978-3-642-23123-0_14","volume-title":"Pattern Recognition","author":"P Wohlhart","year":"2011","unstructured":"Wohlhart, P., K\u00f6stinger, M., Roth, P.M., Bischof, H.: Multiple instance boosting for face recognition in videos. In: Mester, R., Felsberg, M. (eds.) DAGM 2011. LNCS, vol. 6835, pp. 132\u2013141. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-23123-0_14"},{"issue":"3","key":"25_CR36","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/TBDATA.2015.2497270","volume":"1","author":"F Wu","year":"2015","unstructured":"Wu, F., Wang, Z., Zhang, Z., Yang, Y., Luo, J., Zhu, W., Zhuang, Y.: Weakly semi-supervised deep learning for multi-label image annotation. IEEE Trans. Big Data 1(3), 109\u2013122 (2015)","journal-title":"IEEE Trans. Big Data"},{"key":"25_CR37","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.neucom.2016.12.051","volume":"235","author":"Q Yu","year":"2017","unstructured":"Yu, Q., Wang, J., Zhang, S., Gong, Y., Zhao, J.: Combining local and global hypotheses in deep neural network for multi-label image classification. Neurocomputing 235, 38\u201345 (2017)","journal-title":"Neurocomputing"},{"issue":"7","key":"25_CR38","doi-asserted-by":"publisher","first-page":"2038","DOI":"10.1016\/j.patcog.2006.12.019","volume":"40","author":"M Zhang","year":"2007","unstructured":"Zhang, M., Zhou, Z.: ML-KNN: a lazy learning approach to multi-label learning. Pattern Recognit. 40(7), 2038\u20132048 (2007)","journal-title":"Pattern Recognit."},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Saligrama, V.: Zero-shot learning via joint latent similarity embedding. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 6034\u20136042 (2016)","DOI":"10.1109\/CVPR.2016.649"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05710-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T10:15:08Z","timestamp":1775297708000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05710-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,8]]},"ISBN":["9783030057091","9783030057107"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05710-7_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,8]]},"assertion":[{"value":"8 December 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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"}}]}}