{"id":"https://openalex.org/W4392909507","doi":"https://doi.org/10.1109/icassp48485.2024.10446362","title":"Align, Adapt and Inject: Audio-Guided Image Generation, Editing and Stylization","display_name":"Align, Adapt and Inject: Audio-Guided Image Generation, Editing and Stylization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909507","doi":"https://doi.org/10.1109/icassp48485.2024.10446362"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100601250","display_name":"Yue Yang","orcid":"https://orcid.org/0000-0002-5939-4820"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai AI Laboratory, China","Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai AI Laboratory, China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036606244","display_name":"Kaipeng Zhang","orcid":"https://orcid.org/0000-0001-6105-6532"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaipeng Zhang","raw_affiliation_strings":["Shanghai AI Laboratory,China","Shanghai AI Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai AI Laboratory, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062830848","display_name":"Yuying Ge","orcid":"https://orcid.org/0000-0001-5818-2589"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuying Ge","raw_affiliation_strings":["The University of Hong Kong,China","The University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]},{"raw_affiliation_string":"The University of Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101827257","display_name":"Wenqi Shao","orcid":"https://orcid.org/0000-0003-3781-4086"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqi Shao","raw_affiliation_strings":["Shanghai AI Laboratory,China","Shanghai AI Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai AI Laboratory, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040083129","display_name":"Zeyue Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zeyue Xue","raw_affiliation_strings":["The University of Hong Kong,China","The University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]},{"raw_affiliation_string":"The University of Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["Shanghai AI Laboratory,China","Shanghai AI Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai AI Laboratory, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100752686","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-6685-7950"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["Shanghai AI Laboratory,China","Shanghai AI Laboratory, China","The University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai AI Laboratory, China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The University of Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3475","last_page":"3479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.6462000012397766,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.6462000012397766,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7733426094055176},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.7459152936935425},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5880821943283081},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4887080192565918},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.46641242504119873},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.40825557708740234},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37088316679000854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3397587537765503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7733426094055176},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.7459152936935425},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5880821943283081},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4887080192565918},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.46641242504119873},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.40825557708740234},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37088316679000854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3397587537765503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2765811365","https://openalex.org/W2780124704","https://openalex.org/W3015371781","https://openalex.org/W3035524453","https://openalex.org/W3102619627","https://openalex.org/W3110013267","https://openalex.org/W3176445421","https://openalex.org/W3184735396","https://openalex.org/W3215180973","https://openalex.org/W4281485151","https://openalex.org/W4285981780","https://openalex.org/W4289785045","https://openalex.org/W4289785095","https://openalex.org/W4312933868","https://openalex.org/W4365600514","https://openalex.org/W4385822589","https://openalex.org/W4386072096","https://openalex.org/W4390874468","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6838639034","https://openalex.org/W6841366371","https://openalex.org/W6841755765","https://openalex.org/W6845577938","https://openalex.org/W6852162230"],"related_works":["https://openalex.org/W4206059703","https://openalex.org/W4389500762","https://openalex.org/W4319453795","https://openalex.org/W4210895630","https://openalex.org/W4384652403","https://openalex.org/W4205104112","https://openalex.org/W2017202843","https://openalex.org/W4389713802","https://openalex.org/W4311389145","https://openalex.org/W2368355376"],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"have":[2],"significantly":[3],"advanced":[4],"various":[5],"image":[6,10,44,74,135],"generative":[7,25,45,136],"tasks,":[8],"including":[9],"generation,":[11,75],"editing,":[12,76],"and":[13,38,54,60,77,90,129],"stylization.":[14],"While":[15],"text":[16],"prompts":[17],"are":[18],"commonly":[19],"used":[20],"as":[21,32],"guidance":[22],"in":[23,113,133],"most":[24],"models,":[26],"audio":[27,85,95],"presents":[28],"a":[29,52,114],"valuable":[30],"alternative,":[31],"it":[33],"inherently":[34],"accompanies":[35],"corresponding":[36],"scenes":[37],"provides":[39],"abundant":[40],"information":[41,126],"for":[42],"guiding":[43],"tasks.":[46,137],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"novel":[53],"unified":[55],"framework":[56],"named":[57],"Align,":[58],"Adapt,":[59],"Inject":[61],"(AAI)":[62],"to":[63,97],"explore":[64],"the":[65,84,93,106],"cue":[66],"role":[67],"of":[68],"audio,":[69,128],"which":[70],"effectively":[71],"realizes":[72],"audio-guided":[73],"stylization":[78],"simultaneously.":[79],"Specifically,":[80],"AAI":[81,122],"first":[82],"aligns":[83],"embedding":[86,96],"with":[87,101],"visual":[88,102],"features,":[89],"then":[91],"adapts":[92],"aligned":[94],"an":[98],"AudioCue":[99,107],"enriched":[100],"semantics,":[103],"finally":[104],"injects":[105],"into":[108],"existing":[109],"Text-to-Image":[110],"diffusion":[111],"model":[112],"plug-and-play":[115],"manner.":[116],"The":[117],"experiment":[118],"results":[119],"demonstrate":[120],"that":[121],"successfully":[123],"extracts":[124],"rich":[125],"from":[127],"outperforms":[130],"previous":[131],"work":[132],"multiple":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
