{"id":"https://openalex.org/W4412434117","doi":"https://doi.org/10.1016/j.patrec.2025.06.020","title":"Prompt-based Weakly-supervised Vision-language Pre-training","display_name":"Prompt-based Weakly-supervised Vision-language Pre-training","publication_year":2025,"publication_date":"2025-07-15","ids":{"openalex":"https://openalex.org/W4412434117","doi":"https://doi.org/10.1016/j.patrec.2025.06.020"},"language":"en","primary_location":{"id":"doi:10.1016/j.patrec.2025.06.020","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patrec.2025.06.020","pdf_url":null,"source":{"id":"https://openalex.org/S151820558","display_name":"Pattern Recognition Letters","issn_l":"0167-8655","issn":["0167-8655","1872-7344"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.patrec.2025.06.020","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079044890","display_name":"Zixin Guo","orcid":"https://orcid.org/0000-0002-7088-2331"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Zixin Guo","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-7088-2331","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077052515","display_name":"Tzu-Jui Julius Wang","orcid":"https://orcid.org/0000-0002-8840-3079"},"institutions":[{"id":"https://openalex.org/I4210086940","display_name":"Zenuity (Sweden)","ror":"https://ror.org/000dpyn16","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210086940"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Tzu-Jui Julius Wang","raw_affiliation_strings":["Zenseact AB, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zenseact AB, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210086940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071798070","display_name":"Selen Pehlivan","orcid":"https://orcid.org/0000-0002-8658-8890"},"institutions":[{"id":"https://openalex.org/I87653560","display_name":"VTT Technical Research Centre of Finland","ror":"https://ror.org/04b181w54","country_code":"FI","type":"nonprofit","lineage":["https://openalex.org/I4210089493","https://openalex.org/I87653560"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Selen Pehlivan","raw_affiliation_strings":["VTT Technical Research Centre of Finland, Oulu, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VTT Technical Research Centre of Finland, Oulu, Finland","institution_ids":["https://openalex.org/I87653560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049343215","display_name":"Abduljalil Radman","orcid":"https://orcid.org/0000-0002-6317-9752"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Abduljalil Radman","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111346891","display_name":"Min Cao","orcid":"https://orcid.org/0000-0002-6628-0370"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Cao","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036133390","display_name":"Jorma Laaksonen","orcid":"https://orcid.org/0000-0001-7218-3131"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jorma Laaksonen","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079044890"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":{"value":2500,"currency":"USD","value_usd":2500},"apc_paid":{"value":2500,"currency":"USD","value_usd":2500},"fwci":2.3839,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.89359369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"197","issue":null,"first_page":"8","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.994700014591217,"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/training","display_name":"Training (meteorology)","score":0.6495959758758545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6217571496963501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.599374532699585},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41791048645973206},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41445744037628174},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39258718490600586},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3693046569824219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3409344255924225},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07926294207572937}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6495959758758545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6217571496963501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.599374532699585},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41791048645973206},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41445744037628174},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39258718490600586},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3693046569824219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3409344255924225},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07926294207572937},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.patrec.2025.06.020","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patrec.2025.06.020","pdf_url":null,"source":{"id":"https://openalex.org/S151820558","display_name":"Pattern Recognition Letters","issn_l":"0167-8655","issn":["0167-8655","1872-7344"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition Letters","raw_type":"journal-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/138357","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=105010851050&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1016/j.patrec.2025.06.020","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patrec.2025.06.020","pdf_url":null,"source":{"id":"https://openalex.org/S151820558","display_name":"Pattern Recognition Letters","issn_l":"0167-8655","issn":["0167-8655","1872-7344"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4706251453","display_name":"Understanding speech and scene with ears and eyes","funder_award_id":"345791","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G6781587187","display_name":null,"funder_award_id":"62476188","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8994705204","display_name":null,"funder_award_id":"345791","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F1100377486","display_name":"European High Performance Computing Joint Undertaking","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1821462560","https://openalex.org/W2108598243","https://openalex.org/W2185175083","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2912371042","https://openalex.org/W2963530300","https://openalex.org/W2965373594","https://openalex.org/W3035524453","https://openalex.org/W3173220247","https://openalex.org/W4225166070","https://openalex.org/W4287824654","https://openalex.org/W4312245858","https://openalex.org/W4312877428","https://openalex.org/W4319300178","https://openalex.org/W4384659783","https://openalex.org/W4385565298","https://openalex.org/W4385573407","https://openalex.org/W4389984066","https://openalex.org/W4390023570","https://openalex.org/W6639102338","https://openalex.org/W6753938374","https://openalex.org/W6775970589","https://openalex.org/W6782745545","https://openalex.org/W6792155083","https://openalex.org/W6839224452","https://openalex.org/W6845300607"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Weakly-supervised":[0],"Vision-Language":[1],"Pre-training":[2],"(W-VLP)":[3],"explores":[4],"methods":[5],"leveraging":[6],"weak":[7],"cross-modal":[8,31,56,169],"supervision,":[9,170],"typically":[10],"relying":[11],"on":[12,190,196,210],"object":[13,19],"tags":[14],"generated":[15,93],"by":[16,94,188,194],"a":[17,61,85,123,216],"pre-trained":[18,160,172],"detector":[20],"(OD)":[21],"from":[22,76],"images.":[23,83],"However,":[24],"training":[25,136],"such":[26,113],"an":[27,89,95,111,156],"OD":[28],"necessitates":[29],"dense":[30],"information,":[32],"including":[33],"images":[34],"paired":[35],"with":[36,54,65,161],"numerous":[37],"object-level":[38],"annotations.":[39],"To":[40,125],"alleviate":[41],"that":[42,133],"requirement,":[43],"this":[44],"paper":[45],"addresses":[46],"W-VLP":[47,178,236],"in":[48,122,129,180,199,201],"two":[49],"stages:":[50],"(1)":[51],"creating":[52],"data":[53,70],"weaker":[55,168],"supervision":[57],"and":[58,138,147,182,192],"(2)":[59],"pre-training":[60],"vision-language":[62],"(VL)":[63],"model":[64,159,174],"the":[66,100,127,130,135,162,221,231,234],"created":[67,163],"data.":[68,164],"The":[69,228],"creation":[71],"process":[72,137],"involves":[73],"collecting":[74],"knowledge":[75,104,145,150],"large":[77],"language":[78,101],"models":[79],"(LLMs)":[80],"to":[81,141],"describe":[82],"Given":[84],"category":[86],"label":[87],"of":[88,223,233],"image,":[90],"its":[91,167],"descriptions":[92,132],"LLM":[96],"are":[97],"used":[98],"as":[99,114],"counterpart.":[102],"This":[103],"supplements":[105],"what":[106],"can":[107],"be":[108],"obtained":[109],"using":[110],"OD,":[112],"spatial":[115],"relationships":[116],"among":[117],"objects":[118],"most":[119],"likely":[120],"appearing":[121],"scene.":[124],"mitigate":[126],"noise":[128],"LLM-generated":[131],"destabilizes":[134],"may":[139],"lead":[140],"overfitting,":[142],"we":[143,154],"incorporate":[144],"distillation":[146],"external":[148],"retrieval-augmented":[149],"during":[151],"pre-training.":[152],"Furthermore,":[153],"present":[155],"effective":[157],"VL":[158,173,212],"Empirically,":[165],"despite":[166],"our":[171],"notably":[175],"outperforms":[176],"other":[177,211],"works":[179],"image":[181],"text":[183],"retrieval":[184,203],"tasks,":[185,214],"e.g.,":[186],"VLMixer":[187],"17.7%":[189],"MSCOCO":[191],"RELIT":[193],"11.25%":[195],"Flickr30K":[197],"relatively":[198],"Recall@1":[200],"text-to-image":[202],"task.":[204],"It":[205],"also":[206],"shows":[207],"superior":[208],"performance":[209],"downstream":[213],"making":[215],"big":[217],"stride":[218],"towards":[219],"matching":[220],"performances":[222],"strongly":[224],"supervised":[225],"VLP":[226],"models.":[227],"results":[229],"reveal":[230],"effectiveness":[232],"proposed":[235],"methodology.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
