{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T18:28:35Z","timestamp":1776968915050,"version":"3.51.4"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1471472"],"award-info":[{"award-number":["1471472"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1109\/msp.2018.2875511","type":"journal-article","created":{"date-parts":[[2018,12,25]],"date-time":"2018-12-25T19:47:00Z","timestamp":1545767220000},"page":"63-73","source":"Crossref","is-referenced-by-count":13,"title":["Audiovisual Analysis of Music Performances: Overview of an Emerging Field"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8334-9974","authenticated-orcid":false,"given":"Zhiyao","family":"Duan","sequence":"first","affiliation":[]},{"given":"Slim","family":"Essid","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5385-7695","authenticated-orcid":false,"given":"Cynthia C.S.","family":"Liem","sequence":"additional","affiliation":[]},{"given":"Gael","family":"Richard","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9735-9519","authenticated-orcid":false,"given":"Gaurav","family":"Sharma","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WIAMIS.2013.6616151"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref31","first-page":"1","article-title":"SoundNet: Learning sound representations from unlabeled video","author":"aytar","year":"0","journal-title":"Proc Adv Neural Info Process"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2015.7153603"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638337"},{"key":"ref10","first-page":"312","article-title":"Visual analysis for drum sequence transcription","author":"mcguinness","year":"0","journal-title":"Proc IEEE European Signal Processing Conf"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2006.26"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/FCV.2013.6485449"},{"key":"ref13","first-page":"196","article-title":"Visual methods for the retrieval of guitarist fingering","author":"burns","year":"0","journal-title":"Proc Int Conf New Interfaces for Musical Expression"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77129-6_54"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ.2010.6148852"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2008.4711699"},{"key":"ref17","author":"zhang","year":"2009","journal-title":"Automatic music transcription using audio-visual fusion for violin practice in home environment"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952688"},{"key":"ref19","first-page":"159","article-title":"Audiovisual source association for string ensembles through multi-modal vibrato analysis","author":"li","year":"0","journal-title":"Proc Sound and Music Computing"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383344"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1221454110"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1145287.1145311"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1525\/mp.2012.30.1.71","article-title":"When the eye listens: A meta-analysis of how audio-visual presentation enhances the appreciation of music performance","volume":"30","author":"platz","year":"2012","journal-title":"Music Perception: An Interdisciplinary Journal"},{"key":"ref6","first-page":"45","article-title":"Body movement in music information retrieval","author":"god\u00f8y","year":"0","journal-title":"Proc Int Society Music Information Retrieval Conf"},{"key":"ref29","first-page":"1","article-title":"Source-filter based clustering for monaural blind source separation","author":"spiertz","year":"0","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref5","first-page":"800","article-title":"Put the concert attendee in the spotlight. a user-centered design and development approach for classical concert applications","author":"melenhorst","year":"0","journal-title":"Proc Int Society Music Information Retrieval Conf"},{"key":"ref8","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"abu-el-haija","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"key":"ref2","first-page":"37","volume":"3","author":"essid","year":"2012","journal-title":"Fusion of multimodal information in music content analysis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.09.009"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2072529.2072531"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952711"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169995"},{"key":"ref21","first-page":"123","article-title":"Video-based vibrato detection and analysis for polyphonic string music","author":"li","year":"0","journal-title":"Proc Int Society Music Information Retrieval Conf"},{"key":"ref24","first-page":"1","article-title":"Tracking a conductor’s baton","author":"murphy","year":"0","journal-title":"Proc Danish Conf Pattern Recognition and Image Analysis"},{"key":"ref23","article-title":"Vision-based detection of acoustic timed events: A case study on clarinet note onsets","author":"bazzica","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.11.005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2617995.2618016"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/79\/8588402\/8588405-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/79\/8588402\/08588405.pdf?arnumber=8588405","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:41:12Z","timestamp":1657744872000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8588405\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":34,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/msp.2018.2875511","relation":{},"ISSN":["1053-5888","1558-0792"],"issn-type":[{"value":"1053-5888","type":"print"},{"value":"1558-0792","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1]]}}}