{"id":"https://openalex.org/W4402673375","doi":"https://doi.org/10.1109/tpami.2024.3463799","title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","display_name":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","publication_year":2024,"publication_date":"2024-09-20","ids":{"openalex":"https://openalex.org/W4402673375","doi":"https://doi.org/10.1109/tpami.2024.3463799","pmid":"https://pubmed.ncbi.nlm.nih.gov/39302778"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3463799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3463799","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04729219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031538967","display_name":"Lucas Ventura","orcid":"https://orcid.org/0000-0001-5795-0064"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I142631665","display_name":"\u00c9cole nationale des ponts et chauss\u00e9es","ror":"https://ror.org/02nwvxz07","country_code":"FR","type":"education","lineage":["https://openalex.org/I142631665","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4210154111","display_name":"Universit\u00e9 Gustave Eiffel","ror":"https://ror.org/03x42jk29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210154111"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lucas Ventura","raw_affiliation_strings":["LIGM, École des Ponts, CNRS, Univ Gustave Eiffel, Champs-sur-Marne, France","WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)"],"raw_orcid":"https://orcid.org/0000-0001-5795-0064","affiliations":[{"raw_affiliation_string":"LIGM, École des Ponts, CNRS, Univ Gustave Eiffel, Champs-sur-Marne, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210152518","https://openalex.org/I4210154111"]},{"raw_affiliation_string":"WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009826104","display_name":"Antoine Yang","orcid":"https://orcid.org/0000-0002-7258-571X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI","FR"],"is_corresponding":false,"raw_author_name":"Antoine Yang","raw_affiliation_strings":["Inria, Ecole normale supérieure, CNRS, PSL Research University, Paris, France","WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)"],"raw_orcid":"https://orcid.org/0000-0002-7258-571X","affiliations":[{"raw_affiliation_string":"Inria, Ecole normale supérieure, CNRS, PSL Research University, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I29607241","https://openalex.org/I4210103330"]},{"raw_affiliation_string":"WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI","FR"],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["Inria, Ecole normale supérieure, CNRS, PSL Research University, Paris, France","WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)"],"raw_orcid":"https://orcid.org/0009-0005-7239-3741","affiliations":[{"raw_affiliation_string":"Inria, Ecole normale supérieure, CNRS, PSL Research University, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I29607241","https://openalex.org/I4210103330"]},{"raw_affiliation_string":"WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024292507","display_name":"G\u00fcl Varol","orcid":"https://orcid.org/0000-0002-8438-6152"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I142631665","display_name":"\u00c9cole nationale des ponts et chauss\u00e9es","ror":"https://ror.org/02nwvxz07","country_code":"FR","type":"education","lineage":["https://openalex.org/I142631665","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4210154111","display_name":"Universit\u00e9 Gustave Eiffel","ror":"https://ror.org/03x42jk29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210154111"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G\u00fcl Varol","raw_affiliation_strings":["LIGM, École des Ponts, CNRS, Univ Gustave Eiffel, Champs-sur-Marne, France"],"raw_orcid":"https://orcid.org/0000-0002-8438-6152","affiliations":[{"raw_affiliation_string":"LIGM, École des Ponts, CNRS, Univ Gustave Eiffel, Champs-sur-Marne, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210152518","https://openalex.org/I4210154111"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1383,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88667245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"46","issue":"12","first_page":"11409","last_page":"11421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.986299991607666,"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/computer-science","display_name":"Computer science","score":0.8350913524627686},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6417374610900879},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6377021670341492},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5717880725860596},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5476261377334595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5303804278373718},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46067628264427185},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4600406289100647},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35641780495643616},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34271419048309326},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2871335744857788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8350913524627686},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6417374610900879},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6377021670341492},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5717880725860596},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5476261377334595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5303804278373718},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46067628264427185},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4600406289100647},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35641780495643616},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34271419048309326},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2871335744857788},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2024.3463799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3463799","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39302778","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39302778","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:HAL:hal-04729219v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04729219","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, pp.1-12. ⟨10.1109/TPAMI.2024.3463799⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04729219v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04729219","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, pp.1-12. ⟨10.1109/TPAMI.2024.3463799⟩","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G388094421","display_name":"Translating sign language with computer vision","funder_award_id":"ANR-21-CE23-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2842511635","https://openalex.org/W2886641317","https://openalex.org/W2905544595","https://openalex.org/W2963096510","https://openalex.org/W2963530300","https://openalex.org/W2984008963","https://openalex.org/W3026458074","https://openalex.org/W3034556939","https://openalex.org/W3035635319","https://openalex.org/W3038703236","https://openalex.org/W3082247278","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3096034082","https://openalex.org/W3105232955","https://openalex.org/W3150955418","https://openalex.org/W3172514680","https://openalex.org/W3175684172","https://openalex.org/W3176799298","https://openalex.org/W3176909828","https://openalex.org/W3197457832","https://openalex.org/W3203247393","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W3204670646","https://openalex.org/W3206128852","https://openalex.org/W3212304713","https://openalex.org/W4226289673","https://openalex.org/W4280632620","https://openalex.org/W4285606530","https://openalex.org/W4297808394","https://openalex.org/W4304014690","https://openalex.org/W4312299780","https://openalex.org/W4312825288","https://openalex.org/W4312940158","https://openalex.org/W4313186260","https://openalex.org/W4322718191","https://openalex.org/W4360103755","https://openalex.org/W4384918448","https://openalex.org/W4386065554","https://openalex.org/W4386071700","https://openalex.org/W4386075908","https://openalex.org/W4386076215","https://openalex.org/W4386076314","https://openalex.org/W4386076522","https://openalex.org/W4386273457","https://openalex.org/W4389820801","https://openalex.org/W4390873539","https://openalex.org/W4402727158","https://openalex.org/W6751039726","https://openalex.org/W6767211374","https://openalex.org/W6775439340","https://openalex.org/W6778883912","https://openalex.org/W6780783783","https://openalex.org/W6782139059","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6793664725","https://openalex.org/W6793736971","https://openalex.org/W6797148833","https://openalex.org/W6798805250","https://openalex.org/W6803545775","https://openalex.org/W6803953248","https://openalex.org/W6810334672","https://openalex.org/W6810496820","https://openalex.org/W6811013733","https://openalex.org/W6838269690","https://openalex.org/W6846007759","https://openalex.org/W6846305988","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6850956941","https://openalex.org/W6851592950","https://openalex.org/W6854866820","https://openalex.org/W6857401808","https://openalex.org/W6859504253","https://openalex.org/W6862741695","https://openalex.org/W6894216603"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Composed":[0,90],"Image":[1],"Retrieval":[2,92],"(CoIR)":[3],"has":[4],"recently":[5],"gained":[6],"popularity":[7],"as":[8],"a":[9,25,41,68,102,106,111,143,149,244],"task":[10,87],"that":[11,74,161,242],"considers":[12],"both":[13],"text":[14,39],"and":[15,59,109,196,267],"image":[16,46],"queries":[17],"together,":[18],"to":[19,47,88,115,124,167,190,203,228,252,255],"search":[20],"for":[21,146,218],"relevant":[22],"images":[23],"in":[24,136,259],"database.":[26],"Most":[27],"CoIR":[28,55,174],"approaches":[29],"require":[30],"manually":[31,150],"annotated":[32,151],"datasets,":[33],"comprising":[34],"image-text-image":[35],"triplets,":[36],"where":[37],"the":[38,44,48,83,86,117,125,178,208,230,260,264],"describes":[40],"modification":[42,119],"from":[43,105],"query":[45],"target":[49],"image.":[50],"However,":[51],"manual":[52],"curation":[53],"of":[54,85],"triplets":[56,76,176],"is":[57,164,211],"expensive":[58],"prevents":[60],"scalability.":[61],"In":[62],"this":[63,95,122],"work,":[64],"we":[65,97,129,141],"instead":[66],"propose":[67],"scalable":[69],"automatic":[70],"dataset":[71],"creation":[72],"methodology":[73,123,163],"generates":[75],"given":[77],"video-caption":[78],"pairs,":[79,169],"while":[80],"also":[81,240],"expanding":[82],"scope":[84],"include":[89],"Video":[91],"(CoVR).":[93],"To":[94],"end,":[96],"mine":[98],"paired":[99],"videos":[100],"with":[101,148,155],"similar":[103],"caption":[104,200],"large":[107,112],"database,":[108],"leverage":[110],"language":[113],"model":[114,183,246],"generate":[116],"corresponding":[118],"text.":[120],"Applying":[121],"extensive":[126,226],"WebVid2M":[127],"collection,":[128],"automatically":[130],"construct":[131],"our":[132,162,219,234,248],"WebVid-CoVR":[133],"dataset,":[134],"resulting":[135],"1.6":[137],"million":[138,173],"triplets.":[139],"Moreover,":[140],"introduce":[142],"new":[144,235],"benchmark":[145],"CoVR":[147,236,245],"evaluation":[152],"set,":[153],"along":[154],"baseline":[156],"results.":[157],"We":[158,224],"further":[159],"validate":[160],"equally":[165],"applicable":[166],"image-caption":[168],"by":[170,222],"generating":[171],"3.3":[172],"training":[175,220,243],"using":[177],"Conceptual":[179],"Captions":[180],"dataset.":[181],"Our":[182,238],"builds":[184],"on":[185,233,247,263],"BLIP-2":[186],"pretraining,":[187],"adapting":[188],"it":[189],"composed":[191],"video":[192],"(or":[193],"image)":[194],"retrieval,":[195],"incorporates":[197],"an":[198],"additional":[199],"retrieval":[201],"loss":[202],"exploit":[204],"extra":[205],"supervision":[206],"beyond":[207],"triplet,":[209],"which":[210],"possible":[212],"since":[213],"captions":[214],"are":[215],"readily":[216],"available":[217],"data":[221],"design.":[223],"provide":[225],"ablations":[227],"analyze":[229],"design":[231],"choices":[232],"benchmark.":[237],"experiments":[239],"demonstrate":[241],"datasets":[249],"effectively":[250],"transfers":[251],"CoIR,":[253],"leading":[254],"improved":[256],"state-of-the-art":[257],"performance":[258],"zero-shot":[261],"setup":[262],"CIRR,":[265],"FashionIQ,":[266],"CIRCO":[268],"benchmarks.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}