{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:35:23Z","timestamp":1774600523326,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2013,11,1]],"date-time":"2013-11-01T00:00:00Z","timestamp":1383264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2013,11]]},"DOI":"10.1109\/tmm.2013.2267205","type":"journal-article","created":{"date-parts":[[2013,6,7]],"date-time":"2013-06-07T18:01:46Z","timestamp":1370628106000},"page":"1553-1568","source":"Crossref","is-referenced-by-count":229,"title":["Multimodal Saliency and Fusion for Movie Summarization Based on Aural, Visual, and Textual Attention"],"prefix":"10.1109","volume":"15","author":[{"given":"Georgios","family":"Evangelopoulos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Athanasia","family":"Zlatintsi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandros","family":"Potamianos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petros","family":"Maragos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Rapantzikos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Skoumas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yannis","family":"Avrithis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946961"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.19.10.2780"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref70","author":"jurafsky","year":"2008","journal-title":"Speech and Language Processing"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1002\/9781118219546.ch21"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2010.5650991"},{"key":"ref75","first-page":"1294","article-title":"A saliency-based approach to audio event detection and summarization","author":"zlatintsi","year":"2012","journal-title":"Proc 20th Eur Signal Process Conf"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1109\/TPAMI.2009.27","article-title":"Discriminant saliency, the detection of suspicious coincidences, and applications to visual recognition","volume":"31","author":"gao","year":"2009","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1411"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2156803"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.113.4.766"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.53"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1167\/9.3.5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012460413855"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TIP.2009.2030969","article-title":"A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression","volume":"19","author":"guo","year":"2010","journal-title":"IEEE Trans Image Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/78.258071"},{"key":"ref62","author":"hering","year":"1964","journal-title":"Outlines of a Theory of the Light Sense"},{"key":"ref61","first-page":"123","author":"yuille","year":"1996","journal-title":"Bayesian Decision Theory and Psychophysics"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2004.1394309"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/11526346_1"},{"key":"ref64","first-page":"iii","article-title":"Three-dimensional <formula formulatype=\"inline\"><tex Notation=\"TeX\">$n$<\/tex><\/formula>th derivative of Gaussian separable steerable filters","author":"derpanis","year":"2005","journal-title":"Proc IEEE Int Conf Image Process"},{"key":"ref65","author":"pellom","year":"2001","journal-title":"?SONIC The University of colorado continuous speech recognizer ?"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(01)00250-4"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref67","first-page":"806","article-title":"Large-vocabulary speech recognition under adverse acoustic environments","author":"deng","year":"2000","journal-title":"Proc Int Conf Spoken Language Process"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047756"},{"key":"ref69","first-page":"44","article-title":"Probabilistic part-of-speech tagging using decision trees","author":"schmid","year":"1994","journal-title":"Proc Int Conf New Methods Language Process"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.30.051606.094256"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.ne.13.030190.000325"},{"key":"ref20","first-page":"383","article-title":"Video Manga: generating semantically meaningful video summaries","author":"uchihashi","year":"1999","journal-title":"Proc 7th ACM Int Conf Multimedia"},{"key":"ref22","first-page":"174","article-title":"Video summarization using singular value decomposition","author":"gong","year":"2000","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/76.809162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/265563.265572"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937645"},{"key":"ref26","first-page":"199","article-title":"CueVideo automated multimedia indexing and retrieval","author":"ponceleon","year":"1999","journal-title":"Proc ACM Int l Conf Multimedia"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1997.609414"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(88)90021-0"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00958-7_37"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2004.08.008"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/78.277799"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36127-8_20"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/215206.215333"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/345508.345566"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1523"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WIIAT.2008.175"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30586-6_70"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"907","DOI":"10.1109\/TMM.2005.854410","article-title":"A generic framework of user attention model and its application in video summarization","volume":"7","author":"ma","year":"2005","journal-title":"IEEE Trans Multimedia"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1109\/TCSVT.2004.841694","article-title":"Video summarization and scene detection by graph modeling","volume":"15","author":"ngo","year":"2005","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206525"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.890857"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960393"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/79.888862"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2006.1621451"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1198302.1198305"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2010.01.007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2007.04.002"},{"key":"ref19","first-page":"866","article-title":"Adaptive key frame extraction using unsupervised clustering","author":"zhuang","year":"1998","journal-title":"Proc IEEE Int Conf Image Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.ne.18.030195.001205"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2007.07.011"},{"key":"ref6","first-page":"219","article-title":"Shifts in selective visual attention: towards the underlying neural circuitry","volume":"4","author":"koch","year":"1985","journal-title":"Human Neurobiol"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.1000129"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2005.09.040"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/35058500"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2005.853050"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2010.00168"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.02.005"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2014795"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.872625"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1121\/1.414997"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.832710"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-011-9097-0"},{"key":"ref44","first-page":"887","article-title":"A model of saliency-based auditory attention to environmental sound","author":"coensel","year":"2010","journal-title":"Proc 20th Int Congress Acoust"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-71305-2_5"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/6630084\/06527322.pdf?arnumber=6527322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,23]],"date-time":"2021-12-23T18:16:17Z","timestamp":1640283377000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6527322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11]]},"references-count":75,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2013.2267205","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,11]]}}}