{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:47:42Z","timestamp":1753602462919,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472182","type":"proceedings-article","created":{"date-parts":[[2016,6,23]],"date-time":"2016-06-23T21:58:30Z","timestamp":1466719110000},"page":"2772-2776","source":"Crossref","is-referenced-by-count":11,"title":["DEMV-matchmaker: Emotional temporal course representation and deep similarity matching for automatic music video generation"],"prefix":"10.1109","author":[{"given":"Jen-Chun","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Li","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1026711.1026752"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref13","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref14","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"ICML"},{"key":"ref15","article-title":"Deep canonical correlation analysis","author":"andrew","year":"2013","journal-title":"ICML"},{"key":"ref16","article-title":"Distance metric learning for large margin nearest neighbor classification","author":"weinberger","year":"2006","journal-title":"NIPS"},{"key":"ref17","first-page":"491","article-title":"Learning multi-modal similarity","volume":"12","author":"mcfee","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","article-title":"Multimodal learning with deep Boltzmann machines","author":"srivastava","year":"2012","journal-title":"NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.242"},{"key":"ref28","article-title":"A Matlab toolbox for musical feature extraction from audio","author":"lartillot","year":"2007","journal-title":"DAFx"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396495"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393367"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.890831"},{"key":"ref6","article-title":"The acousticvisual emotion Gaussians model for automatic generation of music video","author":"wang","year":"2012","journal-title":"In ACM MM"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-012-0755-3"},{"key":"ref5","article-title":"Background music recommendation for video based on multimodal latent semantic analysis","author":"kuo","year":"2013","journal-title":"ICME"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806359"},{"key":"ref7","article-title":"ADVISOR-personalized video soundtrack recommendation by late fusion with heuristic rankings","author":"shah","year":"2014","journal-title":"In ACM MM"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101278"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X08005293"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502112"},{"journal-title":"The Biopsychology of Mood and Arousal","year":"1989","author":"thayer","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2015.1026658"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349563"},{"journal-title":"Handbook of Cognition and Emotion","year":"1999","author":"ekman","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.15"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655059"}],"event":{"name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2016,3,20]]},"location":"Shanghai","end":{"date-parts":[[2016,3,25]]}},"container-title":["2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7465907\/7471614\/07472182.pdf?arnumber=7472182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T13:00:22Z","timestamp":1498309222000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472182","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}