{"id":"https://openalex.org/W4360897523","doi":"https://doi.org/10.1109/tmm.2023.3261443","title":"Integrating Language Guidance Into Image-Text Matching for Correcting False Negatives","display_name":"Integrating Language Guidance Into Image-Text Matching for Correcting False Negatives","publication_year":2023,"publication_date":"2023-03-24","ids":{"openalex":"https://openalex.org/W4360897523","doi":"https://doi.org/10.1109/tmm.2023.3261443"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3261443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3261443","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-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/A5100415053","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0003-2535-2523"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Li","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2535-2523","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058648594","display_name":"Caili Guo","orcid":"https://orcid.org/0000-0001-8892-4520"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caili Guo","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8892-4520","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019172074","display_name":"Zerun Feng","orcid":"https://orcid.org/0000-0003-3987-0591"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zerun Feng","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3987-0591","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101702810","display_name":"Jenq\u2013Neng Hwang","orcid":"https://orcid.org/0000-0002-8877-2421"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jenq-Neng Hwang","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8877-2421","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110965933","display_name":"Zhongtian Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongtian Du","raw_affiliation_strings":["China Telecom Digital Intelligence Technology Company, Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Digital Intelligence Technology Company, Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3683,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93980378,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"103","last_page":"116"},"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":0.9976000189781189,"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":0.9962999820709229,"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":0.8173980116844177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5961220860481262},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5802670121192932},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.545322597026825},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5382895469665527},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5326274037361145},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4876903295516968},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39987871050834656},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08226907253265381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173980116844177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5961220860481262},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5802670121192932},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.545322597026825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5382895469665527},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5326274037361145},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4876903295516968},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39987871050834656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08226907253265381},{"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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3261443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3261443","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2914057848","display_name":null,"funder_award_id":"2021XD-A01-1","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2101498401","https://openalex.org/W2108598243","https://openalex.org/W2132199310","https://openalex.org/W2151385494","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2195164399","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2745461083","https://openalex.org/W2842511635","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2962964995","https://openalex.org/W2964120214","https://openalex.org/W2964281014","https://openalex.org/W2965848243","https://openalex.org/W2970641574","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W3035454331","https://openalex.org/W3035524453","https://openalex.org/W3035552787","https://openalex.org/W3035605030","https://openalex.org/W3088460296","https://openalex.org/W3090449556","https://openalex.org/W3094172275","https://openalex.org/W3109684201","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3131251978","https://openalex.org/W3155594712","https://openalex.org/W3175888430","https://openalex.org/W4206314411","https://openalex.org/W4210894218","https://openalex.org/W4221142658","https://openalex.org/W4226391640","https://openalex.org/W4282968790","https://openalex.org/W4283276478","https://openalex.org/W4283812943","https://openalex.org/W4285118104","https://openalex.org/W4292828571","https://openalex.org/W4297808394","https://openalex.org/W4304014355","https://openalex.org/W4309368547","https://openalex.org/W4312341105","https://openalex.org/W4312463400","https://openalex.org/W4312761738","https://openalex.org/W4312989333","https://openalex.org/W4313030099","https://openalex.org/W6631190155","https://openalex.org/W6676497082","https://openalex.org/W6678470764","https://openalex.org/W6747225742","https://openalex.org/W6763701032","https://openalex.org/W6776148200","https://openalex.org/W6784333009","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6803448863"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Image-Text":[0],"Matching":[1],"(ITM)":[2],"aims":[3],"to":[4,15,115,174],"establish":[5],"the":[6,27,85,97,116,171,190,196,212,220],"correspondence":[7],"between":[8],"images":[9,40,101,109,112],"and":[10,18,41],"sentences.":[11,117],"ITM":[12,30,35,129,150,172,204,216],"is":[13,92,168,235,262],"fundamental":[14],"various":[16],"vision":[17],"language":[19,165,184],"understanding":[20],"tasks.":[21],"However,":[22,106],"there":[23],"are":[24,32,49,53,60,66,72,102,121,131],"limitations":[25],"in":[26,68,195,242],"way":[28],"existing":[29,215],"benchmarks":[31,205],"constructed.":[33],"The":[34,247,260],"benchmark":[36],"collects":[37],"pairs":[38],"of":[39,87,192,214,222],"sentences":[42],"during":[43,142],"construction.":[44],"Therefore,":[45],"only":[46,81],"samples":[47,59,70,120],"that":[48,71,113,207,251],"paired":[50],"at":[51,84,264],"collection":[52],"annotated":[54,61,73,93,103],"as":[55,62,74,94,104],"positive.":[56],"All":[57,99],"other":[58,100],"negative.":[63,75,105],"Many":[64],"correlations":[65],"missed":[67],"these":[69,107],"For":[76],"example,":[77],"a":[78,236],"sentence":[79],"matches":[80],"one":[82],"image":[83,91],"time":[86],"collection.":[88],"Only":[89],"this":[90,145],"positive":[95],"for":[96,160],"sentence.":[98],"negative":[108],"may":[110],"contain":[111],"correspond":[114],"These":[118],"mislabeled":[119],"called":[122],"<italic":[123,156],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[124,157,266],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">false":[125],"negatives</i>":[126],".":[127,268],"Existing":[128],"models":[130],"optimized":[132],"based":[133],"on":[134,202,230],"annotations":[135,243],"containing":[136],"mislabels,":[137],"which":[138,187],"can":[139,210,254],"introduce":[140],"noise":[141],"training.":[143],"In":[144],"paper,":[146],"we":[147,182,226],"propose":[148,183],"an":[149],"framework":[151,173],"integrating":[152],"Language":[153],"Guidance":[154],"(":[155],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">LG</i>":[158],")":[159],"correcting":[161,223],"false":[162,176,180,193,224,240,258],"negatives.":[163,177,259],"A":[164],"pre-training":[166],"model":[167],"introduced":[169],"into":[170],"identify":[175],"To":[178,218],"correct":[179],"negatives,":[181,225],"guidance":[185],"loss,":[186],"adaptively":[188],"corrects":[189],"locations":[191],"negatives":[194,241],"visual-semantic":[197],"embedding":[198],"space.":[199],"Extensive":[200],"experiments":[201,229],"two":[203],"show":[206,250],"our":[208,252],"method":[209,253],"improve":[211],"performance":[213,221],"models.":[217],"verify":[219],"conduct":[227],"further":[228],"ECCV":[231,233],"Caption.":[232],"Caption":[234],"verified":[237],"dataset":[238],"where":[239],"have":[244],"been":[245],"corrected.":[246],"experimental":[248],"results":[249],"recall":[255],"more":[256],"relevant":[257],"code":[261],"available":[263],"<uri":[265],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/AAA-Zheng/LG_ITM</uri>":[267]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}