{"id":"https://openalex.org/W4396216126","doi":"https://doi.org/10.1145/3662732","title":"Breaking Through the Noisy Correspondence: A Robust Model for Image-Text Matching","display_name":"Breaking Through the Noisy Correspondence: A Robust Model for Image-Text Matching","publication_year":2024,"publication_date":"2024-04-29","ids":{"openalex":"https://openalex.org/W4396216126","doi":"https://doi.org/10.1145/3662732"},"language":"en","primary_location":{"id":"doi:10.1145/3662732","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3662732","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3662732","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3662732","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016820033","display_name":"Hangkun Shi","orcid":"https://orcid.org/0009-0005-0028-1281"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haitao Shi","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0005-0028-1281","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Meng Liu","orcid":"https://orcid.org/0009-0009-6093-6752"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":["Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0009-6093-6752","affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008602430","display_name":"X. Mu","orcid":"https://orcid.org/0009-0004-0048-0232"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxuan Mu","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0004-0048-0232","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072768866","display_name":"Xuemeng Song","orcid":"https://orcid.org/0000-0002-5274-4197"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemeng Song","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-5274-4197","affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875643","display_name":"Yupeng Hu","orcid":"https://orcid.org/0000-0002-5653-8286"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Hu","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-5653-8286","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016820033"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":2.8569,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91796875,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"42","issue":"6","first_page":"1","last_page":"26"},"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":0.9991000294685364,"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":0.995199978351593,"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":0.7040256261825562},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6803939342498779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5520614981651306},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5227013826370239},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4764183759689331},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47190529108047485},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.46723395586013794},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4665503203868866},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46007639169692993},{"id":"https://openalex.org/keywords/correspondence-problem","display_name":"Correspondence problem","score":0.4326504170894623},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3895293176174164},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3377259373664856},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2816581130027771},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2460254728794098},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2319737672805786},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07871353626251221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7040256261825562},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6803939342498779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5520614981651306},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5227013826370239},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4764183759689331},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47190529108047485},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.46723395586013794},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4665503203868866},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46007639169692993},{"id":"https://openalex.org/C3004257","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Correspondence problem","level":2,"score":0.4326504170894623},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3895293176174164},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3377259373664856},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2816581130027771},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2460254728794098},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2319737672805786},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07871353626251221},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3662732","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3662732","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3662732","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3662732","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3662732","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3662732","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G3881774828","display_name":null,"funder_award_id":"ZR2022YQ59","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G6198133373","display_name":null,"funder_award_id":"62376140, 62376137, and U23A20315","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"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396216126.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2185175083","https://openalex.org/W2481240925","https://openalex.org/W2739759426","https://openalex.org/W2778100917","https://openalex.org/W2886641317","https://openalex.org/W2962964995","https://openalex.org/W2963176022","https://openalex.org/W2963249562","https://openalex.org/W2963467339","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W2998356391","https://openalex.org/W3035284526","https://openalex.org/W3035454331","https://openalex.org/W3092820619","https://openalex.org/W3118694826","https://openalex.org/W3155230099","https://openalex.org/W3165959647","https://openalex.org/W3169785106","https://openalex.org/W3177224328","https://openalex.org/W3190386329","https://openalex.org/W3198064418","https://openalex.org/W4207052765","https://openalex.org/W4214819138","https://openalex.org/W4304014355","https://openalex.org/W4312080192","https://openalex.org/W4312682661","https://openalex.org/W4312761738","https://openalex.org/W4317436342","https://openalex.org/W4321488152","https://openalex.org/W4385569851","https://openalex.org/W4386076631","https://openalex.org/W4386083137","https://openalex.org/W6600612351"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2340870721","https://openalex.org/W2358318464","https://openalex.org/W2979236518","https://openalex.org/W3091955004"],"abstract_inverted_index":{"Unleashing":[0],"the":[1,42,53,67,80,89,95,111,115,125,130,146,159,162,168,174,183],"power":[2],"of":[3,56,83,110,133,187],"image-text":[4,39],"matching":[5],"in":[6,114],"real-world":[7],"applications":[8],"is":[9,18,36],"hampered":[10],"by":[11,78,98],"noisy":[12,49,57,68,104,112,135,169],"correspondence.":[13,50],"Manually":[14],"curating":[15],"high-quality":[16],"datasets":[17,23],"expensive":[19],"and":[20,22,103,173,185],"time-consuming,":[21],"generated":[24],"using":[25],"diffusion":[26],"models":[27],"are":[28],"not":[29],"adequately":[30],"well-aligned.":[31],"The":[32],"most":[33,109],"promising":[34],"way":[35],"to":[37,93,106,123],"collect":[38],"pairs":[40],"from":[41],"Internet,":[43],"but":[44],"it":[45],"will":[46],"inevitably":[47],"introduce":[48],"To":[51,127],"reduce":[52,129],"negative":[54,131],"impact":[55,132],"correspondence,":[58,136],"we":[59,87,118,149],"propose":[60,150],"a":[61,73,138,151],"novel":[62],"model":[63,92,94,175,189],"that":[64],"first":[65],"transforms":[66],"correspondence":[69,113,170],"filtering":[70],"problem":[71,77],"into":[72],"similarity":[74,96],"distribution":[75,102],"modeling":[76],"exploiting":[79],"powerful":[81],"capabilities":[82],"pre-trained":[84],"models.":[85],"Specifically,":[86],"use":[88],"Gaussian":[90],"Mixture":[91],"obtained":[97],"CLIP":[99],"as":[100],"clean":[101,121],"distribution,":[105],"filter":[107],"out":[108],"dataset.":[116],"Afterward,":[117],"used":[119],"relatively":[120],"data":[122],"fine-tune":[124],"model.":[126],"further":[128,157],"unfiltered":[134],"i.e.,":[137],"minimal":[139],"part":[140],"where":[141],"two":[142,163],"distributions":[143],"intersect":[144],"during":[145],"fine-tuning":[147],"process,":[148],"distribution-sensitive":[152],"dynamic":[153],"margin":[154],"ranking":[155],"loss,":[156],"increasing":[158],"distance":[160],"between":[161],"distributions.":[164],"Through":[165],"continuous":[166],"iteration,":[167],"gradually":[171,177],"decreases":[172],"performance":[176],"improves.":[178],"Our":[179],"extensive":[180],"experiments":[181],"demonstrate":[182],"effectiveness":[184],"robustness":[186],"our":[188],"even":[190],"under":[191],"high":[192],"noise":[193],"rates.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}