{"id":"https://openalex.org/W4408352316","doi":"https://doi.org/10.1109/icassp49660.2025.10889139","title":"DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap","display_name":"DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352316","doi":"https://doi.org/10.1109/icassp49660.2025.10889139"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5111203531","display_name":"Seong-Jong Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shentong Mo","raw_affiliation_strings":["Tsinghua University,Department of CST,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of CST,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718745","display_name":"Zehua Chen","orcid":"https://orcid.org/0000-0001-8157-0109"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Chen","raw_affiliation_strings":["Tsinghua University,Department of CST,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of CST,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057466192","display_name":"Fan Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Bao","raw_affiliation_strings":["Tsinghua University,Department of CST,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of CST,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100606993","display_name":"Jun Zhu","orcid":"https://orcid.org/0000-0002-1833-3917"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhu","raw_affiliation_strings":["Tsinghua University,Department of CST,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of CST,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111203531"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07890447,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.4065000116825104,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.4065000116825104,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T13067","display_name":"Geological Modeling and Analysis","score":0.3634999990463257,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.9425426721572876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5157654285430908},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0858275294303894}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.9425426721572876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5157654285430908},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0858275294303894}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W3015371781","https://openalex.org/W3155072588","https://openalex.org/W4312653918","https://openalex.org/W4312933868","https://openalex.org/W4319300865","https://openalex.org/W4367359628","https://openalex.org/W4372260310","https://openalex.org/W4372348103","https://openalex.org/W4386072368","https://openalex.org/W4386075858","https://openalex.org/W4390873486","https://openalex.org/W4390873759","https://openalex.org/W4393160294","https://openalex.org/W4400524387","https://openalex.org/W4401895246","https://openalex.org/W4402726986","https://openalex.org/W4402904133","https://openalex.org/W4403888124","https://openalex.org/W4403942708","https://openalex.org/W4404439850","https://openalex.org/W4409347685","https://openalex.org/W4411245083","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6786375611","https://openalex.org/W6838639034","https://openalex.org/W6843326755","https://openalex.org/W6845281891","https://openalex.org/W6845479124","https://openalex.org/W6852820501","https://openalex.org/W6852891092","https://openalex.org/W6853353164","https://openalex.org/W6853668808","https://openalex.org/W6854445938","https://openalex.org/W6858202640","https://openalex.org/W6858762933","https://openalex.org/W6862315687","https://openalex.org/W6869216339","https://openalex.org/W6870010132","https://openalex.org/W6874092166"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214"],"abstract_inverted_index":{"Recent":[0],"works":[1],"in":[2,48,137,146],"cross-modal":[3,60,93,121,148],"understanding":[4,149],"and":[5,15,28,44,57,104,111,119,128,140,150],"generation,":[6],"notably":[7],"through":[8],"models":[9],"like":[10],"CLAP":[11],"(Contrastive":[12,17],"Language-Audio":[13],"Pretraining)":[14],"CAVP":[16],"Audio-Visual":[18],"Pretraining),":[19],"have":[20],"significantly":[21,134],"enhanced":[22],"the":[23,41,55,78,92],"alignment":[24],"of":[25,59],"text,":[26],"video,":[27],"audio":[29,109],"embeddings":[30,106,110],"via":[31],"a":[32,69,73,85,99,116],"single":[33],"contrastive":[34,79],"loss.":[35],"However,":[36],"these":[37],"methods":[38],"often":[39],"overlook":[40],"bidirectional":[42,86],"interactions":[43],"inherent":[45],"noises":[46],"present":[47],"each":[49],"modality,":[50],"which":[51],"can":[52],"crucially":[53],"impact":[54],"quality":[56],"efficacy":[58],"integration.":[61],"To":[62],"address":[63],"this":[64],"limitation,":[65],"we":[66],"introduce":[67],"DiffGAP,":[68],"novel":[70],"approach":[71],"incorporating":[72],"lightweight":[74],"generative":[75],"module":[76],"within":[77],"space.":[80],"Specifically,":[81],"our":[82],"DiffGAP":[83,133],"employs":[84],"diffusion":[87],"process":[88,101],"tailored":[89],"to":[90],"bridge":[91],"gap":[94],"more":[95,117],"effectively.":[96],"This":[97],"involves":[98],"denoising":[100],"on":[102,108,126],"text":[103],"video":[105],"conditioned":[107],"vice":[112],"versa,":[113],"thus":[114],"facilitating":[115],"nuanced":[118],"robust":[120],"interaction.":[122],"Our":[123],"experimental":[124],"results":[125],"VGGSound":[127],"AudioCaps":[129],"datasets":[130],"demonstrate":[131],"that":[132],"improves":[135],"performance":[136],"video/text-audio":[138],"generation":[139,151],"retrieval":[141],"tasks,":[142],"confirming":[143],"its":[144],"effectiveness":[145],"enhancing":[147],"capabilities.":[152]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}