{"id":"https://openalex.org/W4390872676","doi":"https://doi.org/10.1109/iccv51070.2023.00244","title":"VL-Match: Enhancing Vision-Language Pretraining with Token-Level and Instance-Level Matching","display_name":"VL-Match: Enhancing Vision-Language Pretraining with Token-Level and Instance-Level Matching","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4390872676","doi":"https://doi.org/10.1109/iccv51070.2023.00244"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51070.2023.00244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","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/A5014239027","display_name":"Junyu Bi","orcid":null},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Bi","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049999785","display_name":"Daixuan Cheng","orcid":"https://orcid.org/0000-0003-0405-9707"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Daixuan Cheng","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003271371","display_name":"Ping Yao","orcid":"https://orcid.org/0000-0002-0192-9546"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Yao","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044362498","display_name":"Bochen Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Bochen Pang","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069711443","display_name":"Yuefeng Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yuefeng Zhan","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046293929","display_name":"Chuanguang Yang","orcid":"https://orcid.org/0000-0001-5890-289X"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanguang Yang","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100776576","display_name":"Yujing Wang","orcid":"https://orcid.org/0000-0002-7940-5216"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yujing Wang","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101539732","display_name":"Hao Sun","orcid":"https://orcid.org/0009-0004-5027-7478"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088715602","display_name":"Weiwei Deng","orcid":"https://orcid.org/0000-0002-8331-9249"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Weiwei Deng","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100665639","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0003-0709-3273"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3368,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60726524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2584","last_page":"2593"},"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":0.9976000189781189,"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/security-token","display_name":"Security token","score":0.9469811916351318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7937527894973755},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6279008388519287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6006221771240234},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5890883803367615},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5890064239501953},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.5819950699806213},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5600905418395996},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5103916525840759},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4680017828941345},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4257364869117737},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39835911989212036},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34328627586364746},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.10642403364181519},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08216115832328796}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.9469811916351318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7937527894973755},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6279008388519287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6006221771240234},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5890883803367615},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5890064239501953},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5819950699806213},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5600905418395996},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5103916525840759},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4680017828941345},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4257364869117737},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39835911989212036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34328627586364746},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.10642403364181519},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08216115832328796},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51070.2023.00244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2109586012","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2568262903","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2912371042","https://openalex.org/W2963530300","https://openalex.org/W2965373594","https://openalex.org/W2966715458","https://openalex.org/W2970231061","https://openalex.org/W3005680577","https://openalex.org/W3009561768","https://openalex.org/W3035524453","https://openalex.org/W3035682985","https://openalex.org/W3035688398","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3166396011","https://openalex.org/W3177487519","https://openalex.org/W3184735396","https://openalex.org/W3208314443","https://openalex.org/W4226182655","https://openalex.org/W4281623693","https://openalex.org/W4281633937","https://openalex.org/W4287824654","https://openalex.org/W4312460555","https://openalex.org/W4312784228","https://openalex.org/W4312877428","https://openalex.org/W4312910992","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6676497082","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6758704467","https://openalex.org/W6766673545","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6771917389","https://openalex.org/W6774314701","https://openalex.org/W6774670964","https://openalex.org/W6779068807","https://openalex.org/W6779473860","https://openalex.org/W6784333009","https://openalex.org/W6788554130","https://openalex.org/W6789753369","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6797508077","https://openalex.org/W6798805250","https://openalex.org/W6800139874","https://openalex.org/W6803953248","https://openalex.org/W6810274143","https://openalex.org/W6811013733","https://openalex.org/W6838580846"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2057775761","https://openalex.org/W1608433645","https://openalex.org/W2366944513"],"abstract_inverted_index":{"Vision-Language":[0,26,39],"Pretraining":[1],"(VLP)":[2],"has":[3],"significantly":[4,159],"improved":[5],"the":[6,13,35,48,57,72,88,92,95,99,127,132,141],"performance":[7],"of":[8,15,60,75,156],"various":[9],"vision-language":[10],"tasks":[11],"with":[12,28,152],"matching":[14],"images":[16,148],"and":[17,31,54,71,149],"texts.":[18,150],"In":[19,135],"this":[20,136],"paper,":[21],"we":[22,111,138],"propose":[23,112],"VL-Match,":[24],"a":[25,38,64,68,79,113,153],"framework":[27],"Enhanced":[29],"Token-level":[30],"Instance-level":[32],"Matching.":[33],"At":[34,94],"token":[36,86,133],"level,":[37,97],"Replaced":[40],"Token":[41],"Detection":[42],"task":[43,102],"is":[44,109],"designed":[45],"to":[46,66,81,117,143],"boost":[47],"substantial":[49],"interaction":[50],"between":[51,147],"text":[52,58,85,90,121],"tokens":[53],"images,":[55],"where":[56],"encoder":[59,74],"VLP":[61,76],"works":[62,77],"as":[63,78],"generator":[65],"generate":[67,118],"corrupted":[69,89],"text,":[70],"multimodal":[73],"discriminator":[80],"predict":[82],"whether":[83,105],"each":[84],"in":[87,98],"matches":[91],"image.":[93],"instance":[96],"Image-Text":[100],"Matching":[101],"that":[103,123],"judges":[104],"an":[106],"image-text":[107,165],"pair":[108],"matched,":[110],"novel":[114],"bootstrapping":[115],"method":[116],"hard":[119],"negative":[120],"samples":[122],"are":[124],"different":[125],"from":[126],"positive":[128],"ones":[129],"only":[130],"at":[131],"level.":[134],"way,":[137],"can":[139],"force":[140],"network":[142],"detect":[144],"fine-grained":[145],"differences":[146],"Notably,":[151],"smaller":[154],"amount":[155],"parameters,":[157],"VL-Match":[158],"outperforms":[160],"previous":[161],"SOTA":[162],"on":[163],"all":[164],"retrieval":[166],"tasks.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}