{"id":"https://openalex.org/W4413010798","doi":"https://doi.org/10.1109/tpami.2025.3596394","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-Training","display_name":"Global and Local Semantic Completion Learning for Vision-Language Pre-Training","publication_year":2025,"publication_date":"2025-08-06","ids":{"openalex":"https://openalex.org/W4413010798","doi":"https://doi.org/10.1109/tpami.2025.3596394","pmid":"https://pubmed.ncbi.nlm.nih.gov/40768455"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3596394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3596394","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008273094","display_name":"Rong-Cheng Tu","orcid":"https://orcid.org/0000-0002-9567-159X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Rong-Cheng Tu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015360017","display_name":"Yatai Ji","orcid":"https://orcid.org/0009-0000-8096-2928"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Yatai Ji","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037387576","display_name":"Jie Jiang","orcid":"https://orcid.org/0000-0001-9658-5127"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Jiang","raw_affiliation_strings":["Tencent Hunyuan team, Shenzhen, China","Tencent Hunyuan team, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109153417","display_name":"Weijie Kong","orcid":"https://orcid.org/0000-0003-1700-4801"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijie Kong","raw_affiliation_strings":["Tencent Hunyuan team, Shenzhen, China","Tencent Hunyuan team, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051527826","display_name":"Chengfei Cai","orcid":"https://orcid.org/0000-0002-9582-0348"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengfei Cai","raw_affiliation_strings":["Tencent Hunyuan team, Shenzhen, China","Tencent Hunyuan team, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080918639","display_name":"Wenzhe Zhao","orcid":"https://orcid.org/0000-0002-5130-7219"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhe Zhao","raw_affiliation_strings":["Tencent Hunyuan team, Shenzhen, China","Tencent Hunyuan team, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070033770","display_name":"Hongfa Wang","orcid":"https://orcid.org/0000-0001-8230-9471"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfa Wang","raw_affiliation_strings":["Tencent Hunyuan team, Shenzhen, China","Tencent Hunyuan team, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020953714","display_name":"Yujiu Yang","orcid":"https://orcid.org/0000-0002-6427-1024"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Yujiu Yang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Tencent Hunyuan team, Shenzhen, China","Tencent Hunyuan team, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Hunyuan team, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5008273094"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":7.0705,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96715793,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"47","issue":"12","first_page":"11065","last_page":"11079"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9532999992370605,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9532999992370605,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7097992300987244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6884492039680481},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5479328036308289},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4858662486076355},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37843644618988037},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34806281328201294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7097992300987244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6884492039680481},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5479328036308289},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4858662486076355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37843644618988037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34806281328201294},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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:10.1109/tpami.2025.3596394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3596394","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:40768455","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40768455","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}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2563629645","display_name":null,"funder_award_id":"U21B2009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4290911580","display_name":null,"funder_award_id":"62402043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6095425281","display_name":null,"funder_award_id":"62276110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8878491478","display_name":null,"funder_award_id":"62172039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2078238240","https://openalex.org/W2251512949","https://openalex.org/W2270070752","https://openalex.org/W2277195237","https://openalex.org/W2425121537","https://openalex.org/W2560730294","https://openalex.org/W2568262903","https://openalex.org/W2886641317","https://openalex.org/W2963341956","https://openalex.org/W2963530300","https://openalex.org/W2963705779","https://openalex.org/W2970231061","https://openalex.org/W3035682985","https://openalex.org/W3043840704","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3173220247","https://openalex.org/W3176824248","https://openalex.org/W3177224328","https://openalex.org/W3184784418","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W3212037738","https://openalex.org/W3216551675","https://openalex.org/W4221142658","https://openalex.org/W4304084163","https://openalex.org/W4312312750","https://openalex.org/W4312538879","https://openalex.org/W4312626422","https://openalex.org/W4312784228","https://openalex.org/W4312877428","https://openalex.org/W4313181088","https://openalex.org/W4313186260","https://openalex.org/W4385245566","https://openalex.org/W4386071687","https://openalex.org/W4386076176","https://openalex.org/W4386076615","https://openalex.org/W4399418349"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407"],"abstract_inverted_index":{"Cross-modal":[0],"alignment":[1,106,137,140],"plays":[2],"a":[3,103,124,186,218,226],"crucial":[4],"role":[5],"in":[6,33,102,119],"vision-language":[7,253],"pre-training":[8,36],"(VLP)":[9],"models,":[10],"enabling":[11,230],"them":[12,87],"to":[13,47,61,91,111,134,233],"capture":[14],"meaningful":[15],"associations":[16,77],"across":[17],"different":[18],"modalities.":[19],"For":[20],"this":[21,120],"purpose,":[22],"inspired":[23],"by":[24,159],"the":[25,34,65,92,98,115,143,147,190,210],"success":[26],"of":[27,55,86,108,114,150,165,192,205],"masked":[28,39,57,66,99,151,166,172],"language":[29],"modeling":[30,40,58],"(MLM)":[31],"tasks":[32,41,59],"NLP":[35],"area,":[37],"numerous":[38],"have":[42,185],"been":[43],"proposed":[44,211,246],"for":[45,72,97],"VLP":[46],"further":[48,201],"promote":[49],"cross-modal":[50,105,160,214],"interactions.":[51,161],"The":[52],"core":[53],"idea":[54],"previous":[56],"is":[60],"focus":[62],"on":[63,69,189,213,251],"reconstructing":[64],"tokens":[67],"based":[68],"visible":[70],"context":[71],"learning":[73,179],"local-local":[74,139],"alignment,":[75,215],"i.e.,":[76],"between":[78],"image":[79],"patches":[80],"and":[81,127,138,153,156,171,237,262],"text":[82],"tokens.":[83],"However,":[84],"most":[85],"pay":[88],"little":[89],"attention":[90],"global":[93,109,155,167,182],"semantic":[94,168],"features":[95,113,158],"generated":[96],"data,":[100],"resulting":[101],"limited":[104],"ability":[107],"representations":[110],"local":[112,157,173,199],"other":[116],"modality.":[117],"Therefore,":[118],"paper,":[121],"we":[122,216,224],"propose":[123],"novel":[125],"Global":[126],"Local":[128],"Semantic":[129],"Completion":[130],"Learning":[131],"(GLSCL)":[132],"task":[133,145],"facilitate":[135],"global-local":[136],"simultaneously.":[141],"Specifically,":[142],"GLSCL":[144,163],"complements":[146],"missing":[148],"semantics":[149],"data":[152],"recovers":[154],"Our":[162],"consists":[164],"completion":[169,175],"(MGSC)":[170],"token":[174],"(MLTC).":[176],"MGSC":[177],"promotes":[178],"more":[180],"representative":[181],"features,":[183],"which":[184],"great":[187],"impact":[188],"performance":[191,250],"downstream":[193],"tasks,":[194],"while":[195],"MLTC":[196],"reconstructs":[197],"modal-fusion":[198],"tokens,":[200],"enhancing":[202],"accurate":[203],"comprehension":[204],"multimodal":[206,239],"data.":[207],"To":[208],"evaluate":[209],"approaches":[212],"develop":[217],"validation":[219],"benchmark":[220],"called":[221],"ALIGN-BENCH.":[222],"Moreover,":[223],"present":[225],"flexible":[227],"vision":[228],"encoder,":[229],"our":[231,245],"model":[232],"simultaneously":[234],"perform":[235],"image-text":[236,260],"video-text":[238,263],"tasks.":[240],"Experimental":[241],"results":[242],"show":[243],"that":[244],"method":[247],"obtains":[248],"state-of-the-art":[249],"various":[252],"benchmarks,":[254],"such":[255],"as":[256],"visual":[257],"question":[258],"answering,":[259],"retrieval,":[261],"retrieval.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}