{"id":"https://openalex.org/W4415540016","doi":"https://doi.org/10.1145/3746027.3755130","title":"CatchPhrase: EXPrompt-Guided Encoder Adaptation for Audio-to-Image Generation","display_name":"CatchPhrase: EXPrompt-Guided Encoder Adaptation for Audio-to-Image Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540016","doi":"https://doi.org/10.1145/3746027.3755130"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755130","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755130","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065486703","display_name":"Hyunwoo Oh","orcid":"https://orcid.org/0000-0002-1428-7888"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyunwoo Oh","raw_affiliation_strings":["Hanyang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1428-7888","affiliations":[{"raw_affiliation_string":"Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018417380","display_name":"SeungJu Cha","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"SeungJu Cha","raw_affiliation_strings":["Hanyang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0003-1941-0691","affiliations":[{"raw_affiliation_string":"Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kwanyoung Lee","orcid":"https://orcid.org/0009-0006-4525-871X"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kwanyoung Lee","raw_affiliation_strings":["Hanyang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0006-4525-871X","affiliations":[{"raw_affiliation_string":"Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Si-Woo Kim","orcid":"https://orcid.org/0009-0003-3373-3390"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Si-Woo Kim","raw_affiliation_strings":["Hanyang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0003-3373-3390","affiliations":[{"raw_affiliation_string":"Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393157","display_name":"Dong-Jin Kim","orcid":"https://orcid.org/0000-0001-7231-7494"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Jin Kim","raw_affiliation_strings":["Hanyang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-7231-7494","affiliations":[{"raw_affiliation_string":"Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5065486703"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37070598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9773","last_page":"9782"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9980999827384949,"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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/encoder","display_name":"Encoder","score":0.6912000179290771},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5049999952316284},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4812000095844269},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.435699999332428},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3578999936580658},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3522000014781952},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3424000144004822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440999984741211},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6912000179290771},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5049999952316284},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4961000084877014},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45260000228881836},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34790000319480896},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3018999993801117},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.2732999920845032},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2612999975681305},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755130","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3746027.3755130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755130","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W3015371781","https://openalex.org/W3176445421","https://openalex.org/W4312933868","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4385822589","https://openalex.org/W4386071707","https://openalex.org/W4386076027","https://openalex.org/W4386076215","https://openalex.org/W4390873054","https://openalex.org/W4390873732"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"CatchPhrase,":[2],"a":[3],"novel":[4],"audio-to-image":[5,125],"generation":[6,109,130],"framework":[7],"designed":[8],"to":[9,39,84,105,111],"mitigate":[10],"semantic":[11,51,134],"misalignment":[12],"between":[13],"audio":[14,67,93,112,118],"inputs":[15],"and":[16,35,66,75,82,127],"generated":[17],"images.":[18],"While":[19],"recent":[20],"advances":[21],"in":[22,28],"multi-modal":[23,80],"encoders":[24],"have":[25],"enabled":[26],"progress":[27],"cross-modal":[29,50],"generation,":[30],"ambiguity":[31],"stemming":[32],"from":[33,56],"homographs":[34],"auditory":[36],"illusions":[37],"continues":[38],"hinder":[40],"accurate":[41],"alignment.":[42],"To":[43,71],"address":[44,72],"this":[45],"issue,":[46],"CatchPhrase":[47,123],"generates":[48],"enriched":[49],"prompts":[52],"(EXPrompt":[53,95],"Mining":[54],")":[55],"weak":[57],"class":[58],"labels":[59],"by":[60,132],"leveraging":[61],"large":[62],"language":[63],"models":[64,69,110],"(LLMs)":[65],"captioning":[68],"(ACMs).":[70],"both":[73],"class-level":[74],"instance-level":[76],"misalignment,":[77],"we":[78],"apply":[79],"filtering":[81],"retrieval":[83],"select":[85],"the":[86],"most":[87],"semantically":[88],"aligned":[89],"prompt":[90],"for":[91],"each":[92],"sample":[94],"Selector":[96],").":[97],"A":[98],"lightweight":[99],"mapping":[100],"network":[101],"is":[102],"then":[103],"trained":[104],"adapt":[106],"pre-trained":[107],"text-to-image":[108],"input.":[113],"Extensive":[114],"experiments":[115],"on":[116],"multiple":[117],"classification":[119],"datasets":[120],"demonstrate":[121],"that":[122],"improves":[124],"alignment":[126],"consistently":[128],"enhances":[129],"quality":[131],"mitigating":[133],"misalignment.":[135]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}