{"id":"https://openalex.org/W4206739119","doi":"https://doi.org/10.1145/3503047.3503119","title":"Groovy Pixels: Generating Drum Set Rhythms from Images","display_name":"Groovy Pixels: Generating Drum Set Rhythms from Images","publication_year":2021,"publication_date":"2021-11-26","ids":{"openalex":"https://openalex.org/W4206739119","doi":"https://doi.org/10.1145/3503047.3503119"},"language":"en","primary_location":{"id":"doi:10.1145/3503047.3503119","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503047.3503119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056383618","display_name":"Yanjia Zhang","orcid":"https://orcid.org/0000-0003-2094-7309"},"institutions":[{"id":"https://openalex.org/I2800533921","display_name":"United World College of South East Asia","ror":"https://ror.org/025kf5q07","country_code":"SG","type":"education","lineage":["https://openalex.org/I2800533921"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yanjia Zhang","raw_affiliation_strings":["United World College of South East Asia, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"United World College of South East Asia, Singapore","institution_ids":["https://openalex.org/I2800533921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5056383618"],"corresponding_institution_ids":["https://openalex.org/I2800533921"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24731183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9955000281333923,"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/drum","display_name":"Drum","score":0.8756073713302612},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7975509762763977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7253131866455078},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.6889742612838745},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6071252822875977},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5969293117523193},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5558096170425415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5145279765129089},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.49501270055770874},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4693252444267273},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46492934226989746},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46054357290267944},{"id":"https://openalex.org/keywords/beat","display_name":"Beat (acoustics)","score":0.434966117143631},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41550299525260925},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14950129389762878},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14016351103782654},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06276032328605652}],"concepts":[{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.8756073713302612},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7975509762763977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253131866455078},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.6889742612838745},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6071252822875977},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5969293117523193},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5558096170425415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5145279765129089},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.49501270055770874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4693252444267273},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46492934226989746},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46054357290267944},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.434966117143631},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41550299525260925},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14950129389762878},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14016351103782654},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06276032328605652},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503047.3503119","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503047.3503119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1627533391","https://openalex.org/W1969026697","https://openalex.org/W2006556239","https://openalex.org/W2031777151","https://openalex.org/W2080391922","https://openalex.org/W2113409081","https://openalex.org/W2144198023","https://openalex.org/W2340600463","https://openalex.org/W2560674852","https://openalex.org/W2898554302","https://openalex.org/W2950081742"],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W794274922","https://openalex.org/W2035884861","https://openalex.org/W2242088654","https://openalex.org/W2551486807","https://openalex.org/W2379304833","https://openalex.org/W2247299430","https://openalex.org/W2951162327","https://openalex.org/W1966361153","https://openalex.org/W2048942062"],"abstract_inverted_index":{"It":[0],"is":[1,81],"a":[2,32,53,58,71],"consensus":[3],"that":[4],"auditory":[5],"and":[6,20,67,94,101],"visual":[7],"information":[8],"can":[9],"be":[10],"quite":[11],"similar":[12],"in":[13],"terms":[14],"of":[15,18,57,78,92,99,113,116],"the":[16,42,45,79,85,89,114,117],"expression":[17],"emotions":[19],"knowledge.":[21],"To":[22],"explore":[23],"this":[24,29,64],"relationship":[25],"with":[26,96],"machine":[27],"learning,":[28],"paper":[30,108],"proposes":[31],"feasible":[33],"system":[34,118],"to":[35,48,70],"generate":[36],"drum":[37,60,102],"beats":[38],"from":[39],"images.":[40],"Specifically,":[41],"model":[43,80],"converts":[44,68],"input":[46],"image":[47,65],"an":[49,111],"embedding":[50,56],"vector,":[51],"calculates":[52],"corresponding":[54],"music":[55],"4-bar":[59],"set":[61,91],"performance":[62,115],"for":[63,104],"embedding,":[66],"it":[69],"playable":[72],"MIDI":[73],"file.":[74],"The":[75],"training":[76,95],"process":[77],"implemented":[82],"by":[83],"categorising":[84],"source":[86],"dataset":[87],"into":[88],"same":[90],"genres":[93],"different":[97,120],"combinations":[98],"images":[100],"beat":[103],"each":[105],"genre.":[106],"This":[107],"also":[109],"includes":[110],"evaluation":[112],"under":[119],"configurations.":[121]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
