{"id":"https://openalex.org/W4391742988","doi":"https://doi.org/10.1109/imcom60618.2024.10418410","title":"Lyric-Based Image Generation for Individual Songs with Text2Image Model","display_name":"Lyric-Based Image Generation for Individual Songs with Text2Image Model","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4391742988","doi":"https://doi.org/10.1109/imcom60618.2024.10418410"},"language":"en","primary_location":{"id":"doi:10.1109/imcom60618.2024.10418410","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/imcom60618.2024.10418410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Conference on Ubiquitous Information Management and Communication (IMCOM)","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/A5100544490","display_name":"Shoichi Sasaki","orcid":null},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shoichi Sasaki","raw_affiliation_strings":["Graduate School of Design, Kyushu University,Fukuoka,Japan","Graduate School of Design, Kyushu University, Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Design, Kyushu University,Fukuoka,Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Graduate School of Design, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054658403","display_name":"Hiroko Nishida","orcid":"https://orcid.org/0000-0003-0962-8024"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroko Nishida","raw_affiliation_strings":["Kyushu University,Faculty of Design,Fukuoka,Japan","Faculty of Design, Kyushu University, Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu University,Faculty of Design,Fukuoka,Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Faculty of Design, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091026878","display_name":"Ken-ichi Sawai","orcid":null},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ken-Ichi Sawai","raw_affiliation_strings":["Kyushu University,Faculty of Design,Fukuoka,Japan","Faculty of Design, Kyushu University, Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu University,Faculty of Design,Fukuoka,Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Faculty of Design, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018948845","display_name":"Taketoshi Ushiama","orcid":"https://orcid.org/0000-0002-1306-0526"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taketoshi Ushiama","raw_affiliation_strings":["Kyushu University,Faculty of Design,Fukuoka,Japan","Faculty of Design, Kyushu University, Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu University,Faculty of Design,Fukuoka,Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Faculty of Design, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100544490"],"corresponding_institution_ids":["https://openalex.org/I135598925"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01235444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9861999750137329,"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"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9861999750137329,"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":0.9751999974250793,"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/T11309","display_name":"Music and Audio Processing","score":0.9532999992370605,"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/lyrics","display_name":"Lyrics","score":0.8973826766014099},{"id":"https://openalex.org/keywords/thumbnail","display_name":"Thumbnail","score":0.8538916110992432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.787065863609314},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.7641533613204956},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5982539653778076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5977750420570374},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.502509593963623},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.47764623165130615},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4367043972015381},{"id":"https://openalex.org/keywords/impression","display_name":"Impression","score":0.4133978486061096},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32940709590911865},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3225885033607483},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.0986936092376709},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06633150577545166}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8973826766014099},{"id":"https://openalex.org/C160174412","wikidata":"https://www.wikidata.org/wiki/Q873806","display_name":"Thumbnail","level":3,"score":0.8538916110992432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787065863609314},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.7641533613204956},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5982539653778076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5977750420570374},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.502509593963623},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.47764623165130615},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4367043972015381},{"id":"https://openalex.org/C2776684213","wikidata":"https://www.wikidata.org/wiki/Q6007582","display_name":"Impression","level":2,"score":0.4133978486061096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32940709590911865},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3225885033607483},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0986936092376709},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06633150577545166},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/imcom60618.2024.10418410","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/imcom60618.2024.10418410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Conference on Ubiquitous Information Management and Communication (IMCOM)","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":14,"referenced_works":["https://openalex.org/W999953838","https://openalex.org/W2131744502","https://openalex.org/W2963978237","https://openalex.org/W3129576130","https://openalex.org/W4224035735","https://openalex.org/W4281485151","https://openalex.org/W4281557260","https://openalex.org/W4312933868","https://openalex.org/W6679775712","https://openalex.org/W6755694806","https://openalex.org/W6790978476","https://openalex.org/W6809885388","https://openalex.org/W6838639034","https://openalex.org/W6838865847"],"related_works":["https://openalex.org/W137154299","https://openalex.org/W2011506639","https://openalex.org/W2095080241","https://openalex.org/W2501702011","https://openalex.org/W2908847257","https://openalex.org/W2512435841","https://openalex.org/W2951818954","https://openalex.org/W4298160414","https://openalex.org/W4246915297","https://openalex.org/W2951675648"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,12,43,85,96],"method":[4,86],"for":[5,87,116],"generating":[6,89],"images":[7,16,90,141],"to":[8,26,35,58,79,126,130],"represent":[9,71,92],"impressions":[10],"of":[11,29,40,46,60,74,95,111,138],"song":[13,97,99],"automatically.":[14],"Thumbnail":[15],"associated":[17],"with":[18],"songs":[19,30,41,62],"in":[20,42,63],"music":[21],"distribution":[22],"services":[23],"contribute":[24],"greatly":[25],"the":[27,38,49,53,61,64,72,93,103,109,112,127,136,139],"selection":[28],"because":[31],"they":[32,67],"allow":[33],"users":[34],"visually":[36],"grasp":[37],"characteristics":[39],"short":[44],"period":[45],"time.":[47],"On":[48],"other":[50],"hand,":[51],"when":[52],"same":[54,65],"image":[55,117],"is":[56],"assigned":[57],"all":[59],"album,":[66],"may":[68],"not":[69],"adequately":[70],"contents":[73],"each":[75],"song.":[76],"In":[77],"order":[78],"solve":[80],"this":[81],"problem,":[82],"we":[83],"propose":[84],"automatically":[88],"that":[91],"impression":[94],"using":[98],"lyrics":[100],"information":[101],"and":[102,121],"Text2Image":[104,128],"model.":[105],"Specifically,":[106],"by":[107],"analyzing":[108],"meaning":[110],"lyrics,":[113],"prompts":[114,123],"suitable":[115],"generation":[118],"are":[119,124],"created,":[120],"these":[122],"input":[125],"model":[129],"obtain":[131],"images.":[132],"We":[133],"then":[134],"evaluate":[135],"validity":[137],"generated":[140],"through":[142],"user":[143],"studies.":[144]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
