{"id":"https://openalex.org/W4408345587","doi":"https://doi.org/10.1109/icassp49660.2025.10888226","title":"Diffusion Models are Zero-Shot Generative Text-Vision Retrievers","display_name":"Diffusion Models are Zero-Shot Generative Text-Vision Retrievers","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345587","doi":"https://doi.org/10.1109/icassp49660.2025.10888226"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888226","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/A5102978152","display_name":"Bao Li","orcid":"https://orcid.org/0000-0003-1154-6423"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bao Li","raw_affiliation_strings":["Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457290","display_name":"Zhao Xie","orcid":"https://orcid.org/0000-0001-9834-4730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeke Xie","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101895218","display_name":"Xiaomei Zhang","orcid":"https://orcid.org/0000-0003-1219-268X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomei Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632822","display_name":"Xiangyu Zhu","orcid":"https://orcid.org/0000-0002-4636-9677"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhu","raw_affiliation_strings":["Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101629247","display_name":"Zhen Lei","orcid":"https://orcid.org/0000-0002-0450-0913"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Lei","raw_affiliation_strings":["Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102978152"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03989973,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9776999950408936,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9776999950408936,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9509999752044678,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9478999972343445,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.7303300499916077},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6369678974151611},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6330691576004028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6196778416633606},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5741772055625916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.513090968132019},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5120856761932373},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3669425845146179},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10977327823638916},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.09015169739723206},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06763216853141785}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7303300499916077},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6369678974151611},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6330691576004028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6196778416633606},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5741772055625916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.513090968132019},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5120856761932373},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3669425845146179},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10977327823638916},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09015169739723206},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06763216853141785},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888226","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1901129140","https://openalex.org/W1933349210","https://openalex.org/W2128272608","https://openalex.org/W2161236525","https://openalex.org/W2185175083","https://openalex.org/W2425121537","https://openalex.org/W3175939205","https://openalex.org/W4285606530","https://openalex.org/W4312933868","https://openalex.org/W4313136445","https://openalex.org/W4313186260","https://openalex.org/W4375869198","https://openalex.org/W4390872669","https://openalex.org/W4392909058","https://openalex.org/W4403757510","https://openalex.org/W4404965447","https://openalex.org/W6684090549","https://openalex.org/W6739901393","https://openalex.org/W6779823529","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6811013733","https://openalex.org/W6838639034","https://openalex.org/W6846007759","https://openalex.org/W6852224567","https://openalex.org/W6852642789","https://openalex.org/W6862995742"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Large-scale":[0],"text-to-image":[1,32,100],"diffusion":[2,33,101,164],"models":[3,34],"have":[4,24,45],"demonstrated":[5],"impressive":[6],"capabilities":[7],"for":[8,35,73,91],"downstream":[9],"tasks":[10],"by":[11],"leveraging":[12],"strong":[13],"vision-language":[14],"alignment":[15],"from":[16,57],"generative":[17,41,87],"pre-training.":[18],"Recently,":[19],"a":[20,82],"number":[21],"of":[22,31,120,148],"works":[23],"explored":[25],"how":[26],"to":[27,66,109,157],"use":[28],"the":[29,50,64,117,121,146,151,155],"power":[30],"text-image":[36,42,93,139],"matching":[37,43],"tasks.":[38],"While":[39],"previous":[40],"methods":[44],"shown":[46],"potential":[47],"in":[48,113],"retrieving":[49],"most":[51],"challenging":[52],"candidates,":[53],"they":[54],"still":[55],"suffer":[56],"extremely":[58],"slow":[59],"retrieval":[60,89,132,140,161],"speeds":[61],"and":[62,94,115,134],"lack":[63],"ability":[65],"handle":[67],"temporal":[68],"dimensions,":[69],"making":[70],"them":[71],"impractical":[72],"text-video":[74,95,131,160],"retrieval.":[75],"In":[76],"this":[77],"paper,":[78],"we":[79],"propose":[80],"ZSGenRet,":[81],"simple":[83],"yet":[84],"effective":[85],"zero-shot":[86,159],"text-vision":[88],"framework":[90],"both":[92],"tasks,":[96],"based":[97,162],"on":[98,138,163],"pre-trained":[99],"models.":[102,165],"We":[103],"further":[104],"incorporate":[105],"inversion":[106],"saliency":[107],"detection":[108],"identify":[110],"key":[111],"frames":[112],"videos":[114],"enhance":[116],"semantic":[118],"representation":[119],"vision":[122],"encoder.":[123],"Experimental":[124],"results":[125,137],"demonstrate":[126],"that":[127],"ZSGenRet":[128,153],"significantly":[129],"improves":[130],"performance":[133],"achieves":[135],"competitive":[136],"while":[141],"remarkably":[142],"improving":[143],"efficiency.":[144],"To":[145],"best":[147],"our":[149],"knowledge,":[150],"proposed":[152],"is":[154],"first":[156],"explore":[158]},"counts_by_year":[],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}