{"id":"https://openalex.org/W4402979596","doi":"https://doi.org/10.1109/icme57554.2024.10687424","title":"RevNet: A Review Network with Group Aggregation Fusion for Singing Melody Extraction","display_name":"RevNet: A Review Network with Group Aggregation Fusion for Singing Melody Extraction","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979596","doi":"https://doi.org/10.1109/icme57554.2024.10687424"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5011482849","display_name":"Shuai Yu","orcid":"https://orcid.org/0000-0003-1847-563X"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Yu","raw_affiliation_strings":["Donghua University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donghua University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069435246","display_name":"Xiaoliang He","orcid":"https://orcid.org/0000-0003-1671-166X"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoliang He","raw_affiliation_strings":["Donghua University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donghua University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100611274","display_name":"Yanting Zhang","orcid":"https://orcid.org/0000-0002-4608-9229"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanting Zhang","raw_affiliation_strings":["Donghua University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donghua University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181326427"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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/T10860","display_name":"Speech and Audio Processing","score":0.989300012588501,"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":0.9657999873161316,"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/singing","display_name":"Singing","score":0.7879453897476196},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.6635401248931885},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6264877915382385},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.5941587686538696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5916543006896973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4878711700439453},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.47025811672210693},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36781808733940125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31311163306236267},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17098644375801086},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10241222381591797},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08267533779144287},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06485918164253235},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.059034138917922974}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7879453897476196},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.6635401248931885},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6264877915382385},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.5941587686538696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5916543006896973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4878711700439453},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.47025811672210693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36781808733940125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31311163306236267},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17098644375801086},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10241222381591797},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08267533779144287},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06485918164253235},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.059034138917922974},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1493535305","https://openalex.org/W1526336542","https://openalex.org/W1967815448","https://openalex.org/W1973397896","https://openalex.org/W2161632835","https://openalex.org/W2296704011","https://openalex.org/W2747756448","https://openalex.org/W2932319787","https://openalex.org/W2938109705","https://openalex.org/W2963158112","https://openalex.org/W2963535133","https://openalex.org/W2964177567","https://openalex.org/W3015608758","https://openalex.org/W3191088441","https://openalex.org/W4221165769","https://openalex.org/W4224941193","https://openalex.org/W4392909936","https://openalex.org/W4393158690","https://openalex.org/W6631190155","https://openalex.org/W6714030504","https://openalex.org/W6739879593","https://openalex.org/W6756648248"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2353265673","https://openalex.org/W2152662039"],"abstract_inverted_index":{"Singing":[0],"melody":[1,27,141],"extraction":[2],"(SME)":[3],"is":[4,62,76,147,197],"a":[5,77,80,131,199],"critical":[6],"task":[7],"in":[8,53,91,105,126],"the":[9,32,54,58,64,106,122,144,172,189,204,219,249,254,267,278,282],"field":[10],"of":[11,31,79,155,194,231,284],"music":[12],"information":[13],"retrieval":[14],"(MIR).":[15],"Recently,":[16],"deep":[17],"learning":[18],"based":[19,36,148],"methods":[20],"have":[21],"achieved":[22],"remarkable":[23],"successes":[24],"for":[25,139],"singing":[26,140],"extraction.":[28,142],"However,":[29],"most":[30],"existing":[33],"models":[34,85],"are":[35,235,260],"on":[37,149,237,273],"stacked":[38],"convolution":[39,233],"layers":[40],"to":[41,72,170,176,186,202,206,217,246,262],"progressively":[42],"obtain":[43],"task-specific":[44],"features.":[45,244],"Such":[46],"an":[47,92,150],"architecture":[48],"has":[49],"two":[50,156],"limitations:":[51],"1)":[52],"training":[55,89,178,190],"stage,":[56],"when":[57],"global":[59,65],"semantic":[60,66,98],"feature":[61,67,255],"obtained,":[63],"will":[68],"be":[69,174,263],"directly":[70,264],"used":[71],"make":[73,171],"predictions.":[74],"There":[75],"lack":[78],"process":[81,201],"that":[82],"makes":[83,225],"SME":[84,108],"learn":[86,177,207],"knowledge":[87,208],"from":[88,102,113,209,221,257],"errors":[90,179],"in-depth":[93],"way.":[94],"2)":[95],"there":[96],"exist":[97],"gaps":[99],"between":[100,251],"features":[101,112,220,227],"different":[103,114,222,258],"levels":[104,115,223,259],"prior":[107,210],"models.":[109],"The":[110,166,192,213],"inconsistent":[111],"may":[116],"cause":[117],"suboptimal":[118],"performances.":[119],"To":[120],"address":[121],"above":[123],"mentioned":[124],"problem,":[125],"this":[127,195],"paper,":[128],"we":[129],"propose":[130],"review":[132,158,167,184,188,200],"network":[133,146],"(RevNet)":[134],"with":[135],"group":[136,161],"aggregation":[137,162],"fusion":[138,163],"Specifically,":[143],"proposed":[145,286],"encoder-decoder":[151],"network,":[152],"which":[153],"consists":[154],"modules:":[157],"module":[159,168,196,215],"and":[160,224,242,277],"(GAF)":[164],"module.":[165],"aims":[169,216],"model":[173,205],"able":[175],"interactively.":[180],"We":[181,270],"design":[182,193],"multiple":[183],"modules":[185],"iterately":[187],"errors.":[191,212],"like":[198],"force":[203],"prediction":[211],"GAF":[214],"fuse":[218],"multi-level":[226,252],"complementary.":[228],"A":[229],"set":[230],"dilated":[232],"operations":[234],"performed":[236],"our":[238,285],"designed":[239],"grouped":[240],"high-level":[241],"low-level":[243],"Moreover,":[245],"explicitly":[247],"eliminate":[248],"difference":[250],"features,":[253],"maps":[256],"allowed":[261],"supervised":[265],"by":[266],"ground":[268],"truth.":[269],"conduct":[271],"experiments":[272],"several":[274],"public":[275],"datasets":[276],"promising":[279],"results":[280],"demonstrate":[281],"effectiveness":[283],"method.":[287]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}