{"id":"https://openalex.org/W6893719137","doi":"https://doi.org/10.5281/zenodo.4285388","title":"Analysing Musical Performance in Videos Using Deep Neural Networks","display_name":"Analysing Musical Performance in Videos Using Deep Neural Networks","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W6893719137","doi":"https://doi.org/10.5281/zenodo.4285388"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.4285388","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4285388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.4285388","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Foteini Simistira Liwicki","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Foteini Simistira Liwicki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Marcus Liwicki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcus Liwicki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pedro Malo Perise","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro Malo Perise","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Federico Ghelli Visi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Federico Ghelli Visi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Stefan Ostersjo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Ostersjo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27741935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7027999758720398,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7027999758720398,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14034","display_name":"Musicians\u2019 Health and Performance","score":0.10159999877214432,"subfield":{"id":"https://openalex.org/subfields/2742","display_name":"Rehabilitation"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.08110000193119049,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7091000080108643},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6431000232696533},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.6008999943733215},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48820000886917114},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4803999960422516},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4772000014781952},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.334199994802475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746999859809875},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7091000080108643},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6431000232696533},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5544000267982483},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43130001425743103},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3212999999523163},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27149999141693115},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2660999894142151}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.4285388","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4285388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.4285388","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4285388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,62,75,96,112,144],"method":[4,77],"to":[5,66,85,106],"facilitate":[6],"labelling":[7,21,76],"of":[8,19,33,45,88,120,146,156],"music":[9,108,148],"performance":[10,37,42,109,149],"videos":[11,56],"with":[12],"automatic":[13],"methods":[14],"(3D-Convolutional":[15],"Neural":[16],"Networks)":[17],"instead":[18],"tedious":[20],"by":[22,61],"human":[23,63],"experts.":[24],"In":[25,52,91,116],"particular,":[26,117],"we":[27,94],"are":[28,176],"interested":[29],"in":[30,69],"the":[31,34,41,67,70,107,118,121,128,160,167],"detection":[32],"17":[35,147],"musical":[36,46,71],"gestures":[38,150,175],"generated":[39],"during":[40],"(guitar":[43],"play)":[44],"pieces":[47],"which":[48,174],"have":[49,57],"been":[50,58],"video-recorded.":[51],"earlier":[53],"work,":[54],"these":[55],"annotated":[59],"manually":[60],"expert":[64],"according":[65],"labels":[68],"analysis":[72,172],"methodology.":[73],"Such":[74],"is":[78],"time-consuming":[79],"and":[80,103,126,151,163,179],"would":[81],"not":[82],"be":[83],"scalable":[84],"big":[86],"collections":[87],"video":[89],"recordings.":[90],"this":[92],"paper,":[93],"use":[95],"3D-CNN":[97],"model":[98,140],"from":[99],"activity":[100],"recognition":[101],"tasks":[102],"adapt":[104],"it":[105],"dataset":[110],"following":[111],"transfer":[113],"learning":[114],"approach.":[115],"weights":[119],"first":[122],"blocks":[123],"were":[124,137],"kept":[125],"only":[127],"later":[129],"layers":[130,136],"as":[131,133],"well":[132],"additional":[134,171],"classification":[135],"re-trained.":[138],"The":[139],"was":[141],"evaluated":[142],"on":[143,159,166],"set":[145,162],"reports":[152],"an":[153],"average":[154],"accuracy":[155],"97.9%":[157],"(F1:77.8%)":[158],"training":[161],"85.7%":[164],"(F1:38.6%)":[165],"test":[168],"set.":[169],"An":[170],"shows":[173],"particularly":[177],"difficult":[178],"suggest":[180],"improvements":[181],"for":[182],"future":[183],"work.":[184]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}