{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:13:09Z","timestamp":1792080789592,"version":"4.4.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1741472"],"award-info":[{"award-number":["1741472"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,2]]},"DOI":"10.1109\/tmm.2018.2856090","type":"journal-article","created":{"date-parts":[[2018,7,16]],"date-time":"2018-07-16T18:02:38Z","timestamp":1531764158000},"page":"522-535","source":"Crossref","is-referenced-by-count":143,"title":["Creating a Multitrack Classical Music Performance Dataset for Multimodal Music Analysis: Challenges, Insights, and Applications"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8304-6973","authenticated-orcid":false,"given":"Bochen","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinzhao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karthik","family":"Dinesh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8334-9974","authenticated-orcid":false,"given":"Zhiyao","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaurav","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"156","article-title":"ENST-Drums: An extensive audio-visual database for drum signals processing","author":"gillet","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref38","first-page":"71","article-title":"Estimation of guitar fingering and plucking controls based on multimodal analysis of motion, audio and musical score","author":"perez-carrillo","year":"0","journal-title":"Proc Int Symp Computer Music Multidisciplinary Research"},{"key":"ref33","first-page":"315","article-title":"Evaluation of multiple-F0 estimation and tracking systems","author":"bay","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178063"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2557500.2557530"},{"key":"ref30","article-title":"MTG MASS database","author":"vinyes","year":"2008"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/8363507"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3813\/AAA.918104"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2042119"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637776"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.09.009"},{"key":"ref62","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"arXiv 1804 03160"},{"key":"ref61","first-page":"159","article-title":"Audiovisual source association for string ensembles through multi-modal vibrato analysis","author":"li","year":"0","journal-title":"Proc Sound Music Comput"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref28","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","author":"bittner","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref64","article-title":"Audio to body dynamics","author":"shlizerman","year":"0"},{"key":"ref27","first-page":"309","article-title":"Escaping from the abyss of manual annotation: New methodology of building polyphonic datasets for automatic music transcription","author":"su","year":"0","journal-title":"Proc Int Symp Computer Music Multidisciplinary Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2209419"},{"key":"ref2","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":"ref1","author":"smith","year":"2017"},{"key":"ref20","first-page":"59","article-title":"Tracking a conductor's baton","volume":"2003","author":"murphy","year":"0","journal-title":"Proc Danish Conl Pattern Recog Image Anal"},{"key":"ref22","first-page":"2512","author":"yao","year":"0","journal-title":"Proc IEEE Int Conf Comput Vision"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952688"},{"key":"ref24","first-page":"154","article-title":"A discriminative model for polyphonic piano transcription","volume":"2007","author":"poliner","year":"2007","journal-title":"EURASIP J Appl Signal Process"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038819"},{"key":"ref26","first-page":"287","article-title":"RWC music database: Popular, classical and jazz music databases","volume":"2","author":"goto","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref25","first-page":"2153","article-title":"Score-informed transcription for automatic piano tutoring","author":"benetos","year":"0","journal-title":"Proc Eur Signal Proc Conf"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref51","article-title":"URMP project website","year":"0"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2362006"},{"key":"ref58","article-title":"Detection and tracking of point features","author":"tomasi","year":"1991","journal-title":"Carnegie Mellon School of Computer Science"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539939"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2159701"},{"key":"ref54","first-page":"464","article-title":"Realtime chord recognition of musical sound: A system using common lisp music","author":"fujishima","year":"0","journal-title":"Proc Int Comput Music Conf"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2285484"},{"key":"ref52","article-title":"Creating a multi-track classical music performance dataset for multi-modal music analysis: challenges, insights, and applications","author":"li","year":"2018"},{"key":"ref10","article-title":"Vision-based detection of acoustic timed events: A case study on clarinet note onsets","author":"bazzica","year":"2017","journal-title":"arXiv 1706 09556"},{"key":"ref11","first-page":"123","article-title":"Video-based vibrato detection and analysis for polyphonic string music","author":"li","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref40","first-page":"189","article-title":"Modeling musical attributes to characterize ensemble recordings using rhythmic audio features","author":"abe\u00dfer","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952711"},{"key":"ref13","first-page":"201","article-title":"Exploiting instrument-wise playing\/non-playing labels for score synchronization of symphonic music","author":"bazzica","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77129-6_54"},{"key":"ref16","first-page":"97","article-title":"A segmentation-based prototype to compute string instruments fingering","volume":"17","author":"radicioni","year":"0","journal-title":"Proc Conf Interdisciplinary Musicol (CIM05)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ.2010.6148852"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2006.26"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/FCV.2013.6485449"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2011.643314"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1221454110"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291361"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7951787"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2008.4711699"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2473702"},{"key":"ref49","first-page":"23","article-title":"Computer-aided melody note transcription using the tony software: Accuracy and efficiency","author":"mauch","year":"0","journal-title":"Proc 1st Int Conf Technol Music Notation Represent"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415682"},{"key":"ref46","article-title":"Audacity","year":"2015"},{"key":"ref45","article-title":"Sibelius","year":"2014"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/11.40835"},{"key":"ref47","article-title":"Final cut pro","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2014.922999"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref43","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"abu-el-haija","year":"2016","journal-title":"arXiv 1609 08675"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/6046\/8625851\/8411155-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8625851\/08411155.pdf?arnumber=8411155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T16:58:21Z","timestamp":1657731501000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8411155\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2]]},"references-count":64,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2856090","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2]]}}}