{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T19:53:05Z","timestamp":1759693985103,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T00:00:00Z","timestamp":1605225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T00:00:00Z","timestamp":1605225600000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s11042-020-10125-y","type":"journal-article","created":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T05:02:57Z","timestamp":1605243777000},"page":"9749-9764","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["ASTS: attention based spatio-temporal sequential framework for movie trailer genre classification"],"prefix":"10.1007","volume":"80","author":[{"given":"Yitong","family":"Yu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3049-0085","authenticated-orcid":false,"given":"Ziyu","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Delong","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,13]]},"reference":[{"key":"10125_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10674-4","volume-title":"Feature selection and enhanced krill herd algorithm for text document clustering","author":"L Abualigah","year":"2019","unstructured":"Abualigah L, Qasim M (2019) Feature selection and enhanced krill herd algorithm for text document clustering. Springer, Berlin"},{"key":"10125_CR2","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? A new model and the kinetics dataset. arXiv:1705.07750","DOI":"10.1109\/CVPR.2017.502"},{"key":"10125_CR3","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"10125_CR4","doi-asserted-by":"publisher","unstructured":"Chu WT, Guo HJ (2017) Movie genre classification based on poster images with deep neural networks, pp 39\u201345. https:\/\/doi.org\/10.1145\/3132515.3132516","DOI":"10.1145\/3132515.3132516"},{"key":"10125_CR5","unstructured":"Chung J, G\u00fcl\u00e7ehre \u00c7, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555"},{"key":"10125_CR6","doi-asserted-by":"publisher","unstructured":"Deldjoo Y, Elahi M, Quadrana M, Cremonesi P (2015) Toward building a content-based video recommendation system based on low-level features. https:\/\/doi.org\/10.1007\/978-3-319-27729-5","DOI":"10.1007\/978-3-319-27729-5"},{"key":"10125_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13740-016-0060-9","volume":"5","author":"Y Deldjoo","year":"2016","unstructured":"Deldjoo Y, Elahi M, Cremonesi P, Garzotto F, Piazzolla P, Quadrana M (2016) Content-based video recommendation system based on stylistic visual features. Journal on Data Semantics 5:1\u201315. https:\/\/doi.org\/10.1007\/s13740-016-0060-9","journal-title":"Journal on Data Semantics"},{"key":"10125_CR8","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, IEEE, pp 248\u2013 255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10125_CR9","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne Hendricks L, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2625\u20132634","DOI":"10.1109\/CVPR.2015.7298878"},{"issue":"2","key":"10125_CR10","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams C K I, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"issue":"4","key":"10125_CR11","first-page":"19:1","volume":"5","author":"FM Harper","year":"2015","unstructured":"Harper F M, Konstan J A (2015) The movielens datasets: history and context. ACM Trans Interact Intell Syst 5(4):19:1\u201319:19","journal-title":"ACM Trans Interact Intell Syst"},{"key":"10125_CR12","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"10125_CR13","doi-asserted-by":"crossref","unstructured":"Huang H, Shih W, Hsu W (2007) A film classifier based on low-level visual features. In: 2007 IEEE 9th workshop on multimedia signal processing, pp 465\u2013468","DOI":"10.1109\/MMSP.2007.4412917"},{"key":"10125_CR14","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2014.223"},{"key":"10125_CR15","unstructured":"Kingma D, Ba J (2014) Adam: A method for stochastic optimization. Computer Science"},{"key":"10125_CR16","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/s41133-019-0029-y","volume":"5","author":"K Kundalia","year":"2019","unstructured":"Kundalia K, Patel Y, Shah M (2019) Multi-label movie genre detection from a movie poster using knowledge transfer learning. Augmented Human Research 5:11. https:\/\/doi.org\/10.1007\/s41133-019-0029-y","journal-title":"Augmented Human Research"},{"key":"10125_CR17","doi-asserted-by":"crossref","unstructured":"Li Q, Qiu Z, Yao T, Mei T, Rui Y, Luo J (2016) Action recognition by learning deep multi-granular spatio-temporal video representation. In: Proceedings of the 2016 ACM on international conference on multimedia retrieval, pp 159\u2013166","DOI":"10.1145\/2911996.2912001"},{"key":"10125_CR18","doi-asserted-by":"crossref","unstructured":"Rasheed Z, Shah M (2002) Movie genre classification by exploiting audio-visual features of previews. In: Object recognition supported by user interaction for service robots, vol 2, pp 1086\u20131089","DOI":"10.1109\/ICPR.2002.1048494"},{"key":"10125_CR19","unstructured":"Rasheed Z, Shah M (2002) Movie genre classification by exploiting audio-visual features of previews. In: International conference on pattern recognition"},{"key":"10125_CR20","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/TCSVT.2004.839993","volume":"15","author":"Z Rasheed","year":"2005","unstructured":"Rasheed Z, Sheikh Y, Shah M (2005) On the use of computable features for film classification. IEEE Transactions on Circuits And Systems for Video Technology 15:52\u201364","journal-title":"IEEE Transactions on Circuits And Systems for Video Technology"},{"issue":"11","key":"10125_CR21","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster M, Paliwal K K (1997) Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing 45(11):2673\u20132681","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10125_CR22","doi-asserted-by":"publisher","unstructured":"Sim\u00f5es G, Wehrmann J, Barros R, Ruiz D (2016) Movie genre classification with convolutional neural networks, pp 259\u2013266. https:\/\/doi.org\/10.1109\/IJCNN.2016.7727207","DOI":"10.1109\/IJCNN.2016.7727207"},{"key":"10125_CR23","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: Advances in neural information processing systems, pp 568\u2013576"},{"key":"10125_CR24","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"10125_CR25","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Zhe W, Yu Q, Lin D, Tang X, Gool L V (2016) Temporal segment networks: towards good practices for deep action recognition. In: Eccv","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"10125_CR26","doi-asserted-by":"crossref","unstructured":"Wehrmann J, Barros R C (2017) Movie genre classification: a multi-label approach based on convolutions through time. Appl Soft Comput 61","DOI":"10.1016\/j.asoc.2017.08.029"},{"key":"10125_CR27","doi-asserted-by":"crossref","unstructured":"Wehrmann J, Barros R C, Sim\u00f5es G S, Paula T S, Ruiz DD (2017) (Deep) Learning from frames. In: Intelligent systems","DOI":"10.1109\/BRACIS.2016.012"},{"key":"10125_CR28","doi-asserted-by":"crossref","unstructured":"Zha S, Luisier F, Andrews W, Srivastava N, Salakhutdinov R (2015) Exploiting image-trained cnn architectures for unconstrained video classification. arXiv:1503.04144","DOI":"10.5244\/C.29.60"},{"key":"10125_CR29","doi-asserted-by":"crossref","unstructured":"Zhou H, Hermans T, Karandikar A V, Rehg J M (2010) Movie genre classification via scene categorization. In: International conference on multimedia","DOI":"10.1145\/1873951.1874068"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-10125-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-020-10125-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-10125-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T23:55:32Z","timestamp":1616716532000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-020-10125-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,13]]},"references-count":29,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2021,3]]}},"alternative-id":["10125"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-10125-y","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2020,11,13]]},"assertion":[{"value":"15 August 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 October 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}