{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T02:37:38Z","timestamp":1730342258796,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.23919\/apsipa.2018.8659514","type":"proceedings-article","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T23:11:49Z","timestamp":1552950709000},"page":"329-334","source":"Crossref","is-referenced-by-count":0,"title":["MMANN: Multimodal Multilevel Attention Neural Network for Horror Clip Detection"],"prefix":"10.23919","author":[{"given":"Xingliang","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxing","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas Fang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.547"},{"key":"ref11","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Advances in neural information processing systems"},{"journal-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"bahdanau","key":"ref12"},{"key":"ref13","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"simonyan","key":"ref15"},{"key":"ref16","article-title":"The MediaEval 2017 emotional impact of movies task","author":"dellandr\u00e9a","year":"2017","journal-title":"Working Notes Proceedings of the MediaEval 2017 Workshop"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2396531"},{"key":"ref18","first-page":"12","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","volume":"4","author":"szegedy","year":"2017","journal-title":"AAAI"},{"journal-title":"Openimages A public dataset for large-scale multi-label and multi-class image classification","year":"2017","author":"krasin","key":"ref19"},{"key":"ref4","first-page":"599","article-title":"Horror video scene recognition based on multi-view multi-instance learning","author":"ding","year":"2012","journal-title":"Asian Conference on Computer Vision"},{"key":"ref27","article-title":"MIC-TJU in MediaEval 2017 emotional impact of movies task","author":"yi","year":"2017","journal-title":"Working Notes Proceedings of the MediaEval 2017 Workshop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946656"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/UPCON.2016.7894690"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SECon.2012.6196925"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e91-d.5.1562"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.095"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2010.5651515"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749400"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-7967(03)00034-2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref22","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref24","article-title":"HKBU at MediaEval 2017 emotional impact of movies task","author":"liu","year":"2017","journal-title":"Working Notes Proceedings of the MediaEval 2017 Workshop"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref23"},{"key":"ref26","article-title":"THUHCSI in MediaEval 2017 emotional impact of movies task","author":"jin","year":"2017","journal-title":"Working Notes Proceedings of the MediaEval 2017 Workshop"},{"key":"ref25","article-title":"TCNJ-CS @ MediaEval 2017 emotional impact of movie task","author":"yoon","year":"2017","journal-title":"Working Notes Proceedings of the MediaEval 2017 Workshop"}],"event":{"name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2018,11,12]]},"location":"Honolulu, HI, USA","end":{"date-parts":[[2018,11,15]]}},"container-title":["2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8648538\/8659446\/08659514.pdf?arnumber=8659514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:19:21Z","timestamp":1598221161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8659514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":27,"URL":"https:\/\/doi.org\/10.23919\/apsipa.2018.8659514","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}