{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T05:51:39Z","timestamp":1748929899921,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031466632"},{"type":"electronic","value":"9783031466649"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-46664-9_45","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T13:02:29Z","timestamp":1699102949000},"page":"676-691","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MFMGC: A Multi-modal Data Fusion Model for\u00a0Movie Genre Classification"],"prefix":"10.1007","author":[{"given":"Xiaorui","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"key":"45_CR1","unstructured":"Arevalo, J., Solorio, T., Montes-y G\u00f3mez, M., Gonz\u00e1lez, F.A.: Gated multimodal units for information fusion. arXiv:1702.01992 (2017)"},{"key":"45_CR2","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: Wav2Vec 2.0: a framework for self-supervised learning of speech representations. NeurIPS 33, 12449\u201312460 (2020)"},{"key":"45_CR3","unstructured":"Bamman, D., O\u2019Connor, B., Smith, N.A.: Learning latent personas of film characters. In: ACL, vol. 1, pp. 352\u2013361 (2013)"},{"key":"45_CR4","doi-asserted-by":"crossref","unstructured":"Behrouzi, T., Toosi, R., Akhaee, M.A.: Multimodal movie genre classification using recurrent neural network. Multimedia Tools Appl. 82, 1\u201322 (2022)","DOI":"10.1007\/s11042-022-13418-6"},{"key":"45_CR5","doi-asserted-by":"crossref","unstructured":"Bi, T., Jarnikov, D., Lukkien, J.: Shot-based hybrid fusion for movie genre classification. In: ICIP, pp. 257\u2013269 (2022)","DOI":"10.1007\/978-3-031-06427-2_22"},{"key":"45_CR6","doi-asserted-by":"crossref","unstructured":"Bi, T., Jarnikov, D., Lukkien, J.: Video representation fusion network for multi-label movie genre classification. In: ICPR, pp. 9386\u20139391 (2021)","DOI":"10.1109\/ICPR48806.2021.9412480"},{"key":"45_CR7","doi-asserted-by":"crossref","unstructured":"Bribiesca, I.R., Monroy, A.P.L., Montes, M.: Multimodal weighted fusion of transformers for movie genre classification. In: Proceedings of the Third Workshop on Multimodal Artificial Intelligence, pp. 1\u20135 (2021)","DOI":"10.18653\/v1\/2021.maiworkshop-1.1"},{"key":"45_CR8","unstructured":"Cascante-Bonilla, P., Sitaraman, K., Luo, M., Ordonez, V.: Moviescope: large-scale analysis of movies using multiple modalities. arXiv:1908.03180 (2019)"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Chen, S., Nie, X., Fan, D., Zhang, D., Bhat, V., Hamid, R.: Shot contrastive self-supervised learning for scene boundary detection. In: CVPR, pp. 9796\u20139805 (2021)","DOI":"10.1109\/CVPR46437.2021.00967"},{"key":"45_CR10","doi-asserted-by":"crossref","unstructured":"Cui, Y., Che, W., Liu, T., Qin, B., Wang, S., Hu, G.: Revisiting pre-trained models for Chinese natural language processing. In: EMNLP, pp. 657\u2013668 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Davis, J., Goadrich, M.: The relationship between precision-recall and roc curves. In: ICML, pp. 233\u2013240 (2006)","DOI":"10.1145\/1143844.1143874"},{"key":"45_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2018)"},{"key":"45_CR13","unstructured":"Dridi, A., Recupero, D.R.: MORE SENSE: MOvie REviews SENtiment analysis boosted with SEmantics. In: EMSASW (2017)"},{"key":"45_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/978-3-030-58548-8_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Q Huang","year":"2020","unstructured":"Huang, Q., Xiong, Yu., Rao, A., Wang, J., Lin, D.: MovieNet: a holistic dataset for movie understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 709\u2013727. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_41"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Kukleva, A., Tapaswi, M., Laptev, I.: Learning interactions and relationships between movie characters. In: CVPR, pp. 9849\u20139858 (2020)","DOI":"10.1109\/CVPR42600.2020.00987"},{"issue":"1","key":"45_CR16","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s10479-020-03804-4","volume":"308","author":"Y Liao","year":"2020","unstructured":"Liao, Y., Peng, Y., Shi, S., Shi, V., Yu, X.: Early box office prediction in China\u2019s film market based on a stacking fusion model. Ann. Oper. Res. 308(1), 321\u2013338 (2020). https:\/\/doi.org\/10.1007\/s10479-020-03804-4","journal-title":"Ann. Oper. Res."},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin Transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"14","key":"45_CR18","doi-asserted-by":"publisher","first-page":"19071","DOI":"10.1007\/s11042-020-10086-2","volume":"81","author":"RB Mangolin","year":"2022","unstructured":"Mangolin, R.B., et al.: A multimodal approach for multi-label movie genre classification. Multimedia Tools Appl. 81(14), 19071\u201319096 (2022)","journal-title":"Multimedia Tools Appl."},{"key":"45_CR19","doi-asserted-by":"crossref","unstructured":"Nambiar, G., Roy, P., Singh, D.: Multi modal genre classification of movies. In: INOCON, pp. 1\u20136 (2020)","DOI":"10.1109\/INOCON50539.2020.9298385"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Rao, A., et al.: A local-to-global approach to multi-modal movie scene segmentation. In: CVPR, pp. 10146\u201310155 (2020)","DOI":"10.1109\/CVPR42600.2020.01016"},{"key":"45_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in Homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"45_CR22","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. arXiv:1908.08530 (2019)"},{"key":"45_CR23","doi-asserted-by":"crossref","unstructured":"Thet, T.T., Na, J.C., Khoo, C.S., Shakthikumar, S.: Sentiment analysis of movie reviews on discussion boards using a linguistic approach. In: CIKM, pp. 81\u201384 (2009)","DOI":"10.1145\/1651461.1651476"},{"key":"45_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"45_CR25","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1016\/j.asoc.2017.08.029","volume":"61","author":"J Wehrmann","year":"2017","unstructured":"Wehrmann, J., Barros, R.C.: Movie genre classification: a multi-label approach based on convolutions through time. Appl. Soft Comput. 61, 973\u2013982 (2017)","journal-title":"Appl. Soft Comput."},{"key":"45_CR26","first-page":"1086","volume":"34","author":"M Xu","year":"2021","unstructured":"Xu, M., et al.: Long short-term transformer for online action detection. NeurIPS 34, 1086\u20131099 (2021)","journal-title":"NeurIPS"},{"key":"45_CR27","unstructured":"Zhang, Z., Gu, Y., Plummer, B.A., Miao, X., Liu, J., Wang, H.: Effectively leveraging multi-modal features for movie genre classification. arXiv:2203.13281 (2022)"},{"issue":"6","key":"45_CR28","doi-asserted-by":"publisher","first-page":"1855","DOI":"10.1007\/s00521-017-3162-x","volume":"31","author":"Y Zhou","year":"2019","unstructured":"Zhou, Y., Zhang, L., Yi, Z.: Predicting movie box-office revenues using deep neural networks. Neural Comput. Appl. 31(6), 1855\u20131865 (2019)","journal-title":"Neural Comput. Appl."}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46664-9_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T11:09:50Z","timestamp":1730459390000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46664-9_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031466632","9783031466649"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46664-9_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2023.uqcloud.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes. Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"503","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"216","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"43% - 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 (provided by the conference organizers)"}},{"value":"2.97","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.77","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}