{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T20:31:53Z","timestamp":1778272313128,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"H2020 European Project: EasyTv","award":["761999"],"award-info":[{"award-number":["761999"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2976033","type":"journal-article","created":{"date-parts":[[2020,2,25]],"date-time":"2020-02-25T04:08:05Z","timestamp":1582603685000},"page":"39361-39374","source":"Crossref","is-referenced-by-count":42,"title":["A Multimodal End-to-End Deep Learning Architecture for Music Popularity Prediction"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8824-8304","authenticated-orcid":false,"given":"David","family":"Martin-Gutierrez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2177-6185","authenticated-orcid":false,"given":"Gustavo","family":"Hernandez Penaloza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4009-2662","authenticated-orcid":false,"given":"Alberto","family":"Belmonte-Hernandez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Federico","family":"Alvarez Garcia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"597","article-title":"Convergence analysis of two-layer neural networks with ReLU activation","author":"li","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2820903"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.09.100"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44944-9_50"},{"key":"ref31","first-page":"714","article-title":"Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture","volume":"3","author":"karsoliya","year":"2012","journal-title":"Int J Eng Trends Technol"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2703939"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2802558.2814645"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683461"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806475"},{"key":"ref60","first-page":"105","article-title":"Analysis and processing of audio signals using complex form representation","author":"taktakishvili","year":"2019","journal-title":"Proc 24th Conf Open Innov Assoc FRUCT"},{"key":"ref62","first-page":"2725","article-title":"Feature selection guided auto-encoder","author":"wang","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30543-9_71"},{"key":"ref28","article-title":"Gradient flow in recurrent nets: The difficulty of learning long-term dependencies","author":"hochreiter","year":"2001"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3281746"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2014.881888"},{"key":"ref65","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1080\/095281300146272"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2002.1035731"},{"key":"ref67","first-page":"8778","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","author":"zhang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2093894"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85836-2_29"},{"key":"ref20","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref22","first-page":"339","article-title":"Learning features from music audio with deep belief networks","volume":"10","author":"hamel","year":"2010","journal-title":"Proc ISMIR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.2478\/eletel-2014-0042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462261"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59497-3_175"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1178723.1178727"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682912"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.025"},{"key":"ref59","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref58","first-page":"3","article-title":"Hit song detection using lyric features alone","author":"singhi","year":"2014","journal-title":"Proc Int Soc (MIR)"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2849563"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854949"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1121\/1.1919362"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.11.004"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1108\/00220410410560582"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.811356"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2307\/843761"},{"key":"ref11","first-page":"488","article-title":"Automatic prediction of hit songs","author":"dhanaraj","year":"2005","journal-title":"Proc ISMIR"},{"key":"ref40","first-page":"1","article-title":"MEL frequency cepstral coefficients for music modeling","volume":"270","author":"logan","year":"2000","journal-title":"Proc ISMIR"},{"key":"ref12","article-title":"Incorporating nesterov momentum into adam","author":"dozat","year":"2016"},{"key":"ref13","author":"duda","year":"2012","journal-title":"Pattern Classification"},{"key":"ref14","article-title":"The echo nest musical fingerprint","author":"ellis","year":"2010"},{"key":"ref15","first-page":"640","article-title":"Study of Chinese and UK hit songs prediction","author":"fan","year":"2013","journal-title":"Proc Int Symp Computer Music Multidisciplinary Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1117\/12.290336"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3326921"},{"key":"ref19","article-title":"Towards an all-purpose content-based multimedia information retrieval system","author":"gasser","year":"2019","journal-title":"arXiv 1902 03878"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1268517.1268565"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1367\/1\/012016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03348-3_8"},{"key":"ref5","first-page":"10","article-title":"The million song dataset","volume":"2","author":"bertin-mahieux","year":"2011","journal-title":"Proc ISMIR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2125784"},{"key":"ref49","article-title":"Predicting song popularity","volume":"26","author":"pham","year":"2016"},{"key":"ref9","first-page":"402","article-title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping","author":"caruana","year":"2001","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcps.2014.12.004"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1177\/0276237417704339"},{"key":"ref48","article-title":"Hit song science","author":"pachet","year":"2012","journal-title":"Music Data Mining"},{"key":"ref47","first-page":"355","article-title":"Hit song science is not yet a science","author":"pachet","year":"2008","journal-title":"Proc ISMIR"},{"key":"ref42","first-page":"232","article-title":"Structural sentence similarity estimation for short texts","author":"ma","year":"2016","journal-title":"Proc FLAIRS Conf"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/500141.500173"},{"key":"ref44","first-page":"1614","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","author":"martins","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref43","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09007339.pdf?arnumber=9007339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:51:50Z","timestamp":1639770710000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9007339\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2976033","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}