{"id":"https://openalex.org/W3093162393","doi":"https://doi.org/10.1145/3394171.3413776","title":"Emotion-Based End-to-End Matching Between Image and Music in Valence-Arousal Space","display_name":"Emotion-Based End-to-End Matching Between Image and Music in Valence-Arousal Space","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093162393","doi":"https://doi.org/10.1145/3394171.3413776","mag":"3093162393"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5051149140","display_name":"Sicheng Zhao","orcid":"https://orcid.org/0000-0001-5843-6411"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sicheng Zhao","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107932873","display_name":"Yaxian Li","orcid":"https://orcid.org/0009-0001-1221-7990"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxian Li","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076460510","display_name":"Xingxu Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingxu Yao","raw_affiliation_strings":["Nankai University, Didi Chuxing, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Nankai University, Didi Chuxing, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001185571","display_name":"Weizhi Nie","orcid":"https://orcid.org/0000-0002-0578-8138"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhi Nie","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600606","display_name":"Pengfei Xu","orcid":"https://orcid.org/0000-0003-1067-3607"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Xu","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089409678","display_name":"Jufeng Yang","orcid":"https://orcid.org/0000-0003-0219-3443"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jufeng Yang","raw_affiliation_strings":["Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047285420","display_name":"Kurt Keutzer","orcid":"https://orcid.org/0000-0003-3868-8501"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt Keutzer","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5051149140"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":2.273,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.88999342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2945","last_page":"2954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.994700014591217,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7105016112327576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5689608454704285},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5460959672927856},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5168436169624329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5015888214111328},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.47195640206336975},{"id":"https://openalex.org/keywords/multidimensional-scaling","display_name":"Multidimensional scaling","score":0.41854071617126465},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41440141201019287},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3822198212146759},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32182663679122925},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26681074500083923},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18885108828544617}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7105016112327576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5689608454704285},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5460959672927856},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5168436169624329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5015888214111328},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.47195640206336975},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.41854071617126465},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41440141201019287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3822198212146759},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32182663679122925},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26681074500083923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18885108828544617},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W44741455","https://openalex.org/W1525099241","https://openalex.org/W1834939702","https://openalex.org/W1966797434","https://openalex.org/W1983507146","https://openalex.org/W1984354687","https://openalex.org/W1995681409","https://openalex.org/W2003856922","https://openalex.org/W2005152349","https://openalex.org/W2006625185","https://openalex.org/W2028948654","https://openalex.org/W2048783874","https://openalex.org/W2055387001","https://openalex.org/W2063948594","https://openalex.org/W2074356411","https://openalex.org/W2074788634","https://openalex.org/W2075953807","https://openalex.org/W2078833921","https://openalex.org/W2081352230","https://openalex.org/W2083488428","https://openalex.org/W2087618018","https://openalex.org/W2088511157","https://openalex.org/W2096733369","https://openalex.org/W2118526556","https://openalex.org/W2125105112","https://openalex.org/W2129186114","https://openalex.org/W2142663217","https://openalex.org/W2143380612","https://openalex.org/W2152491694","https://openalex.org/W2157364932","https://openalex.org/W2169096000","https://openalex.org/W2173163709","https://openalex.org/W2194775991","https://openalex.org/W2197620369","https://openalex.org/W2402288201","https://openalex.org/W2410860376","https://openalex.org/W2462290672","https://openalex.org/W2525579820","https://openalex.org/W2531468424","https://openalex.org/W2552972371","https://openalex.org/W2559078338","https://openalex.org/W2564325886","https://openalex.org/W2578895956","https://openalex.org/W2584561145","https://openalex.org/W2619697695","https://openalex.org/W2739474071","https://openalex.org/W2741561025","https://openalex.org/W2741630455","https://openalex.org/W2752234108","https://openalex.org/W2753840835","https://openalex.org/W2765291577","https://openalex.org/W2765354427","https://openalex.org/W2766094568","https://openalex.org/W2793857798","https://openalex.org/W2896591327","https://openalex.org/W2904451048","https://openalex.org/W2945956523","https://openalex.org/W2963026686","https://openalex.org/W2963042261","https://openalex.org/W2963162200","https://openalex.org/W2963263909","https://openalex.org/W2963464104","https://openalex.org/W2963978237","https://openalex.org/W2964236337","https://openalex.org/W2967957126","https://openalex.org/W2971671927","https://openalex.org/W2971765953","https://openalex.org/W2972850892","https://openalex.org/W2973909019","https://openalex.org/W2981843773","https://openalex.org/W2996799978","https://openalex.org/W3098061148","https://openalex.org/W3098670224","https://openalex.org/W3099206234","https://openalex.org/W3124728922","https://openalex.org/W4256361765","https://openalex.org/W6600648412","https://openalex.org/W6603094881"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4200285273","https://openalex.org/W2374778813","https://openalex.org/W1582127415","https://openalex.org/W2012281976","https://openalex.org/W4238212629","https://openalex.org/W305894733","https://openalex.org/W4245539973","https://openalex.org/W1900592362","https://openalex.org/W4233692833"],"abstract_inverted_index":{"Both":[0],"images":[1,17,146],"and":[2,8,18,31,36,52,75,147,156,170,188],"music":[3,19,37,76,189],"can":[4],"convey":[5],"rich":[6],"semantics":[7],"are":[9,163],"widely":[10],"used":[11],"to":[12,25,109,193],"induce":[13],"specific":[14],"emotions.":[15],"Matching":[16],"with":[20,95],"similar":[21],"emotions":[22,79],"might":[23],"help":[24],"make":[26],"emotion":[27,44,138],"perceptions":[28],"more":[29],"vivid":[30],"stronger.":[32],"Existing":[33],"emotion-based":[34,186],"image":[35,74,187],"matching":[38,59,72,125,169,190],"methods":[39],"either":[40],"employ":[41],"limited":[42],"categorical":[43],"states":[45],"which":[46,116],"cannot":[47],"well":[48],"reflect":[49],"the":[50,58,81,118,123,130,136,141,153,160,181,194],"complexity":[51],"subtlety":[53],"of":[54,144,183],"emotions,":[55],"or":[56],"train":[57],"model":[60],"using":[61],"an":[62],"impractical":[63],"multi-stage":[64],"pipeline.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,87,101,128],"study":[70],"end-to-end":[71],"between":[73],"based":[77],"on":[78,178],"in":[80,122,140,152,159],"continuous":[82,105,124],"valence-arousal":[83],"(VA)":[84],"space.":[85,126],"First,":[86],"construct":[88],"a":[89,111],"large-scale":[90],"dataset,":[91],"termed":[92],"Image-Music-Emotion-Matching-Net":[93],"(IMEMNet),":[94],"over":[96],"140K":[97],"image-music":[98],"pairs.":[99],"Second,":[100],"propose":[102],"cross-modal":[103,119,168],"deep":[104],"metric":[106,150],"learning":[107,151],"(CDCML)":[108],"learn":[110],"shared":[112],"latent":[113],"embedding":[114,131,154],"space":[115,132,155,162],"preserves":[117],"similarity":[120],"relationship":[121,139],"Finally,":[127],"refine":[129],"by":[133],"further":[134],"preserving":[135],"single-modal":[137,171],"VA":[142,172],"spaces":[143],"both":[145,167],"music.":[148],"The":[149,174],"task":[157],"regression":[158],"label":[161],"jointly":[164],"optimized":[165],"for":[166,185],"prediction.":[173],"extensive":[175],"experiments":[176],"conducted":[177],"IMEMNet":[179],"demonstrate":[180],"superiority":[182],"CDCML":[184],"as":[191],"compared":[192],"state-of-the-art":[195],"approaches.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}