{"id":"https://openalex.org/W2929853905","doi":"https://doi.org/10.1109/icassp.2019.8683133","title":"Learning Affective Correspondence between Music and Image","display_name":"Learning Affective Correspondence between Music and Image","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2929853905","doi":"https://doi.org/10.1109/icassp.2019.8683133","mag":"2929853905"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.00150","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016194897","display_name":"Gaurav Verma","orcid":"https://orcid.org/0000-0001-7350-0813"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gaurav Verma","raw_affiliation_strings":["Adobe Research, India"],"affiliations":[{"raw_affiliation_string":"Adobe Research, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044545212","display_name":"Eeshan Gunesh Dhekane","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA","DZ"],"is_corresponding":false,"raw_author_name":"Eeshan Gunesh Dhekane","raw_affiliation_strings":["Mila, Université de Montréal, Canada","MILA, Universit\u00e9 de Montr\u00e9al, Canada"],"affiliations":[{"raw_affiliation_string":"Mila, Université de Montréal, Canada","institution_ids":["https://openalex.org/I4210155582"]},{"raw_affiliation_string":"MILA, Universit\u00e9 de Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021354054","display_name":"Tanaya Guha","orcid":"https://orcid.org/0000-0003-2167-4891"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tanaya Guha","raw_affiliation_strings":["University of Warwick, UK","#N#        University of Warwick, UK"],"affiliations":[{"raw_affiliation_string":"University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"#N#        University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016194897"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.82090046,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71680873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3975","last_page":"3979"},"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9936000108718872,"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/T10860","display_name":"Speech and Audio Processing","score":0.9837999939918518,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6691266894340515},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6085854172706604},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5985047221183777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5784577131271362},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5494371056556702},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5088655948638916},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5083958506584167},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48357337713241577},{"id":"https://openalex.org/keywords/crossmodal","display_name":"Crossmodal","score":0.48237720131874084},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3884727954864502},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3637901544570923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3435320556163788},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23186638951301575},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.1725335717201233},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.14673608541488647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6691266894340515},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6085854172706604},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5985047221183777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5784577131271362},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5494371056556702},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5088655948638916},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5083958506584167},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48357337713241577},{"id":"https://openalex.org/C60115397","wikidata":"https://www.wikidata.org/wiki/Q5188732","display_name":"Crossmodal","level":4,"score":0.48237720131874084},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3884727954864502},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3637901544570923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3435320556163788},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23186638951301575},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.1725335717201233},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.14673608541488647},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2019.8683133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:wrap.warwick.ac.uk:114068","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400665","display_name":"Warwick Research Archive Portal (University of Warwick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39555362","host_organization_name":"University of Warwick","host_organization_lineage":["https://openalex.org/I39555362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Item"},{"id":"pmh:oai:arXiv.org:1904.00150","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.00150","pdf_url":"https://arxiv.org/pdf/1904.00150","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2929853905","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1904.00150","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1904.00150","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.00150","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.00150","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.00150","pdf_url":"https://arxiv.org/pdf/1904.00150","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W166347353","https://openalex.org/W1522301498","https://openalex.org/W1556219185","https://openalex.org/W1797428404","https://openalex.org/W1975929202","https://openalex.org/W2063948594","https://openalex.org/W2074356411","https://openalex.org/W2081835714","https://openalex.org/W2095540482","https://openalex.org/W2110052520","https://openalex.org/W2117539524","https://openalex.org/W2124033848","https://openalex.org/W2125324924","https://openalex.org/W2148600927","https://openalex.org/W2163293471","https://openalex.org/W2183341477","https://openalex.org/W2347880541","https://openalex.org/W2388114291","https://openalex.org/W2404368331","https://openalex.org/W2511428026","https://openalex.org/W2619697695","https://openalex.org/W2773686055","https://openalex.org/W2777181663","https://openalex.org/W2796992393","https://openalex.org/W2951589678","https://openalex.org/W2962960500","https://openalex.org/W2963887950","https://openalex.org/W2963992782","https://openalex.org/W6606724909","https://openalex.org/W6631190155","https://openalex.org/W6638333121","https://openalex.org/W6670991099","https://openalex.org/W6676494506","https://openalex.org/W6678360021","https://openalex.org/W6678788828","https://openalex.org/W6691937106","https://openalex.org/W6705060728","https://openalex.org/W6713190814","https://openalex.org/W6725104640","https://openalex.org/W6730410798","https://openalex.org/W6737037043","https://openalex.org/W6747045456"],"related_works":["https://openalex.org/W2963978237","https://openalex.org/W2600638094","https://openalex.org/W3142793812","https://openalex.org/W3034624317","https://openalex.org/W3176106916","https://openalex.org/W2972287851","https://openalex.org/W2972738697","https://openalex.org/W3093162393","https://openalex.org/W3124817158","https://openalex.org/W2509286793","https://openalex.org/W3092931289","https://openalex.org/W2808336242","https://openalex.org/W2774085128","https://openalex.org/W2981843773","https://openalex.org/W3093521632","https://openalex.org/W2547190339","https://openalex.org/W2798657061","https://openalex.org/W2798610091","https://openalex.org/W2609258829","https://openalex.org/W2765291577"],"abstract_inverted_index":{"We":[0,128],"introduce":[1],"the":[2,55,58,74,82,114],"problem":[3],"of":[4,72,137],"learning":[5],"affective":[6,75,115],"correspondence":[7,76,116],"between":[8],"audio":[9],"(music)":[10],"and":[11,21,66,97,125],"visual":[12],"data":[13,56],"(images).":[14],"For":[15],"this":[16,40,120],"task,":[17],"a":[18,46,62,68,87],"music":[19,95],"clip":[20],"an":[22],"image":[23],"are":[24,147],"considered":[25],"similar":[26,33],"(having":[27],"true":[28],"correspondence)":[29],"if":[30],"they":[31],"have":[32],"emotion":[34,102,138,144,150],"content.":[35],"In":[36],"order":[37],"to":[38,53,61],"estimate":[39],"crossmodal,":[41],"emotion-centric":[42],"similarity,":[43],"we":[44,85],"propose":[45],"deep":[47],"neural":[48],"network":[49,133],"architecture":[50],"that":[51,131],"learns":[52,134],"project":[54],"from":[57],"two":[59,123],"modalities":[60],"common":[63],"representation":[64],"space,":[65],"performs":[67],"binary":[69],"classification":[70],"task":[71,118],"predicting":[73],"(true":[77],"or":[78],"false).":[79],"To":[80],"facilitate":[81],"current":[83],"study,":[84],"construct":[86],"large":[88],"scale":[89],"database":[90],"containing":[91],"more":[92],"than":[93],"$3,500$":[94],"clips":[96],"$85,000$":[98],"images":[99],"with":[100,143],"three":[101],"classes":[103],"(positive,":[104],"neutral,":[105],"negative).":[106],"The":[107],"proposed":[108],"approach":[109],"achieves":[110],"$61.67\\%$":[111],"accuracy":[112],"for":[113,149],"prediction":[117],"on":[119],"database,":[121],"outperforming":[122],"relevant":[124],"competitive":[126],"baselines.":[127],"also":[129],"demonstrate":[130],"our":[132],"modality-specific":[135],"representations":[136],"(without":[139],"explicitly":[140],"being":[141],"trained":[142],"labels),":[145],"which":[146],"useful":[148],"recognition":[151],"in":[152],"individual":[153],"modalities.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}