{"id":"https://openalex.org/W4415537259","doi":"https://doi.org/10.1145/3746027.3754921","title":"Music2Palette: Emotion-aligned Color Palette Generation via Cross-Modal Representation Learning","display_name":"Music2Palette: Emotion-aligned Color Palette Generation via Cross-Modal Representation Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537259","doi":"https://doi.org/10.1145/3746027.3754921"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754921","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5102391669","display_name":"Jiayun Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiayun Hu","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-1606-5832","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112893680","display_name":"Yongchuan He","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueyi He","raw_affiliation_strings":["School of Software Engineering, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-7550-0918","affiliations":[{"raw_affiliation_string":"School of Software Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianyi Liang","orcid":"https://orcid.org/0000-0001-8372-8379"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Liang","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8372-8379","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063110936","display_name":"Changbo Wang","orcid":"https://orcid.org/0000-0001-8940-6418"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changbo Wang","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8940-6418","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100649746","display_name":"Chenhui Li","orcid":"https://orcid.org/0000-0001-9835-2650"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenhui Li","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9835-2650","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102391669"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":2.1559,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89813365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6615","last_page":"6624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12496","display_name":"Color perception and design","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12496","display_name":"Color perception and design","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9787999987602234,"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"}},{"id":"https://openalex.org/T11666","display_name":"Color Science and Applications","score":0.9581999778747559,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/palette","display_name":"Palette (painting)","score":0.6604999899864197},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4564000070095062},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.453000009059906},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4228000044822693},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.34709998965263367},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3450999855995178},{"id":"https://openalex.org/keywords/dither","display_name":"Dither","score":0.3231000006198883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7621999979019165},{"id":"https://openalex.org/C2779674283","wikidata":"https://www.wikidata.org/wiki/Q425548","display_name":"Palette (painting)","level":2,"score":0.6604999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5253000259399414},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4564000070095062},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C70451592","wikidata":"https://www.wikidata.org/wiki/Q376493","display_name":"Dither","level":3,"score":0.3231000006198883},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C142616399","wikidata":"https://www.wikidata.org/wiki/Q5148604","display_name":"Color image","level":4,"score":0.2809999883174896},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2961294","wikidata":"https://www.wikidata.org/wiki/Q166863","display_name":"Color space","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754921","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1966797434","https://openalex.org/W1975514318","https://openalex.org/W1997222220","https://openalex.org/W2001700175","https://openalex.org/W2008689769","https://openalex.org/W2023772589","https://openalex.org/W2072691998","https://openalex.org/W2075953807","https://openalex.org/W2087618018","https://openalex.org/W2118526556","https://openalex.org/W2141461755","https://openalex.org/W2149628368","https://openalex.org/W2164480306","https://openalex.org/W2191779130","https://openalex.org/W2197620369","https://openalex.org/W2402288201","https://openalex.org/W2410860376","https://openalex.org/W2531468424","https://openalex.org/W2552972371","https://openalex.org/W2622139206","https://openalex.org/W2765291577","https://openalex.org/W2808471375","https://openalex.org/W3093162393","https://openalex.org/W3189205145","https://openalex.org/W3200054522","https://openalex.org/W4224323398","https://openalex.org/W4319308497","https://openalex.org/W4366547422","https://openalex.org/W4385668779","https://openalex.org/W4389371446","https://openalex.org/W4401635231","https://openalex.org/W4402727350","https://openalex.org/W4404479914"],"related_works":[],"abstract_inverted_index":{"Emotion":[0],"alignment":[1],"between":[2,159],"music":[3,89,101,134],"and":[4,103,120,136,139,153,161],"palettes":[5],"is":[6],"crucial":[7,48],"for":[8,61],"effective":[9],"multimedia":[10],"content,":[11],"yet":[12],"misalignment":[13],"creates":[14],"confusion":[15],"that":[16,113,126],"weakens":[17],"the":[18,45,157],"intended":[19],"message.":[20],"However,":[21],"existing":[22],"methods":[23,131],"often":[24],"generate":[25],"only":[26],"a":[27,58,74,94,100,109],"single":[28],"dominant":[29],"color,":[30],"missing":[31],"emotion":[32,49,84,116,135,163],"variation.":[33],"Others":[34],"rely":[35],"on":[36],"indirect":[37],"mappings":[38],"through":[39,82],"text":[40],"or":[41],"images,":[42],"resulting":[43],"in":[44,132],"loss":[46],"of":[47,76],"details.":[50],"To":[51,86],"address":[52],"these":[53],"challenges,":[54],"we":[55,92],"present":[56],"Music2Palette,":[57],"novel":[59],"method":[60,128],"emotion-aligned":[62],"color":[63,104,118,141],"palette":[64,121],"generation":[65],"via":[66],"cross-modal":[67,95],"representation":[68,96],"learning.":[69],"We":[70,106],"first":[71],"construct":[72],"MuCED,":[73],"dataset":[75],"2,634":[77],"expert-validated":[78],"music-palette":[79],"pairs":[80],"aligned":[81],"Russell-based":[83],"vectors.":[85],"directly":[87],"translate":[88],"into":[90],"palettes,":[91],"propose":[93,108],"learning":[97],"framework":[98],"with":[99],"encoder":[102],"decoder.":[105],"further":[107],"multi-objective":[110],"optimization":[111],"approach":[112,144],"jointly":[114],"enhances":[115],"alignment,":[117],"diversity,":[119],"coherence.":[122],"Extensive":[123],"experiments":[124],"demonstrate":[125],"our":[127],"outperforms":[129],"current":[130],"interpreting":[133],"generating":[137],"attractive":[138],"diverse":[140],"palettes.":[142],"Our":[143],"enables":[145],"applications":[146],"like":[147],"music-driven":[148],"image":[149],"recoloring,":[150],"video":[151],"generating,":[152],"data":[154],"visualization,":[155],"bridging":[156],"gap":[158],"auditory":[160],"visual":[162],"experiences.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}
