{"id":"https://openalex.org/W1999999865","doi":"https://doi.org/10.1186/s13636-015-0050-0","title":"SIFT-based local spectrogram image descriptor: a novel feature for robust music identification","display_name":"SIFT-based local spectrogram image descriptor: a novel feature for robust music identification","publication_year":2015,"publication_date":"2015-02-11","ids":{"openalex":"https://openalex.org/W1999999865","doi":"https://doi.org/10.1186/s13636-015-0050-0","mag":"1999999865"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-015-0050-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0050-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0050-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0050-0","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100603768","display_name":"Xiu Zhang","orcid":"https://orcid.org/0000-0002-2736-8687"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiu Zhang","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, 201203, China","School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, 201203, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100934338","display_name":"Bilei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bilei Zhu","raw_affiliation_strings":["SAP Labs, Shanghai, 201203, China","SAP Labs, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"SAP Labs, Shanghai, 201203, China","institution_ids":[]},{"raw_affiliation_string":"SAP Labs, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100721239","display_name":"Linwei Li","orcid":"https://orcid.org/0000-0002-8406-8322"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linwei Li","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, 201203, China","School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, 201203, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318193","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4486-8341"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, 201203, China","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, 200433, China","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, 201203, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, 200433, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339621","display_name":"Xiaoqiang Li","orcid":"https://orcid.org/0000-0001-7243-2783"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqiang Li","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China","School of Computer Engineering and Science, Shanghai University Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China","institution_ids":["https://openalex.org/I141962983"]},{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392006","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-5477-1017"},"institutions":[{"id":"https://openalex.org/I4210111959","display_name":"Shanghai Advanced Research Institute","ror":"https://ror.org/02br7py06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210111959"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Naval Medical Research Institute, Shanghai, 200433, China","Naval Medical Research Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Naval Medical Research Institute, Shanghai, 200433, China","institution_ids":[]},{"raw_affiliation_string":"Naval Medical Research Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210111959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110192960","display_name":"Peizhong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peizhong Lu","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, 201203, China","School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, 201203, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087549682","display_name":"Wenqiang Zhang","orcid":"https://orcid.org/0000-0003-1568-1200"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqiang Zhang","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, 201203, China","School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, 201203, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100603768"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":3.4461,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93154918,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2015","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9959999918937683,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9952999949455261,"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/scale-invariant-feature-transform","display_name":"Scale-invariant feature transform","score":0.8434929251670837},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.802768349647522},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7306077480316162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7081818580627441},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.70155930519104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6551815271377563},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.5319820642471313},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.5088215470314026},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4191918671131134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38795387744903564},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37944847345352173},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.33669155836105347},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.06451991200447083}],"concepts":[{"id":"https://openalex.org/C61265191","wikidata":"https://www.wikidata.org/wiki/Q767770","display_name":"Scale-invariant feature transform","level":3,"score":0.8434929251670837},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.802768349647522},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7306077480316162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7081818580627441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.70155930519104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6551815271377563},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.5319820642471313},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.5088215470314026},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4191918671131134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38795387744903564},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37944847345352173},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.33669155836105347},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.06451991200447083},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s13636-015-0050-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0050-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0050-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s13636-015-0050-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0050-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0050-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1999999865.pdf","grobid_xml":"https://content.openalex.org/works/W1999999865.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W4650756","https://openalex.org/W83334756","https://openalex.org/W122994913","https://openalex.org/W1966699657","https://openalex.org/W1969552659","https://openalex.org/W1980771692","https://openalex.org/W1988660987","https://openalex.org/W2012481918","https://openalex.org/W2026609075","https://openalex.org/W2028491571","https://openalex.org/W2034785406","https://openalex.org/W2046972719","https://openalex.org/W2047411082","https://openalex.org/W2053111920","https://openalex.org/W2055289292","https://openalex.org/W2066941820","https://openalex.org/W2080470053","https://openalex.org/W2101590843","https://openalex.org/W2103434133","https://openalex.org/W2104160358","https://openalex.org/W2116867711","https://openalex.org/W2119747362","https://openalex.org/W2124714966","https://openalex.org/W2130103520","https://openalex.org/W2135127658","https://openalex.org/W2136951780","https://openalex.org/W2139689188","https://openalex.org/W2144211147","https://openalex.org/W2147717514","https://openalex.org/W2151103935","https://openalex.org/W2152926413","https://openalex.org/W2158452612","https://openalex.org/W2162006472","https://openalex.org/W2163195643","https://openalex.org/W2166442947","https://openalex.org/W2168874565","https://openalex.org/W2172187724","https://openalex.org/W2177274842","https://openalex.org/W2186582651","https://openalex.org/W2295559688","https://openalex.org/W2737146868","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4281928084","https://openalex.org/W2076289882","https://openalex.org/W4244083225","https://openalex.org/W2168562287","https://openalex.org/W2069595590","https://openalex.org/W2083751184","https://openalex.org/W2345915074","https://openalex.org/W3080336085","https://openalex.org/W2738461075","https://openalex.org/W4385636057"],"abstract_inverted_index":{"Abstract":[0],"Music":[1],"identification":[2,50,117],"via":[3],"audio":[4],"fingerprinting":[5],"has":[6],"been":[7],"an":[8,123],"active":[9],"research":[10],"field":[11],"in":[12,48],"recent":[13],"years.":[14],"In":[15,52,92],"the":[16,116,131,138],"real-world":[17],"environment,":[18],"music":[19,49,74,147],"queries":[20,148],"are":[21,108],"often":[22],"deformed":[23],"by":[24,36,129],"various":[25],"interferences":[26],"which":[27,114],"typically":[28],"include":[29],"signal":[30],"distortions":[31],"and":[32,88,103,119,143],"time-frequency":[33,132],"misalignments":[34],"caused":[35],"time":[37,86,141],"stretching,":[38],"pitch":[39,89,144],"shifting,":[40],"etc.":[41],"Therefore,":[42],"robustness":[43,83],"plays":[44],"a":[45,68,94,104],"crucial":[46],"role":[47],"technique.":[51],"this":[53],"paper,":[54],"we":[55,126],"propose":[56],"to":[57],"use":[58],"scale":[59],"invariant":[60],"feature":[61],"transform":[62],"(SIFT)":[63],"local":[64],"descriptors":[65],"computed":[66],"from":[67],"spectrogram":[69],"image":[70],"as":[71,122],"sub-fingerprints":[72,80],"for":[73,110],"identification.":[75],"Experiments":[76],"show":[77],"that":[78,128,146],"these":[79],"exhibit":[81],"strong":[82],"against":[84],"serious":[85],"stretching":[87,142],"shifting":[90,145],"simultaneously.":[91],"addition,":[93],"locality":[95],"sensitive":[96],"hashing":[97],"(LSH)-based":[98],"nearest":[99],"sub-fingerprint":[100,112],"retrieval":[101],"method":[102],"matching":[105],"determination":[106],"mechanism":[107],"applied":[109],"robust":[111],"matching,":[113],"makes":[115],"efficient":[118],"precise.":[120],"Finally,":[121],"auxiliary":[124],"function,":[125],"demonstrate":[127],"comparing":[130],"locations":[133],"of":[134,140],"corresponding":[135],"SIFT":[136],"keypoints,":[137],"factor":[139],"might":[149],"have":[150],"experienced":[151],"can":[152],"be":[153],"accurately":[154],"estimated.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
