{"id":"https://openalex.org/W7140180476","doi":"https://doi.org/10.1109/tip.2026.3675497","title":"Pseudo-Text Guided Robust Learning for Noisy Correspondence in Cross-Modal Retrieval","display_name":"Pseudo-Text Guided Robust Learning for Noisy Correspondence in Cross-Modal Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140180476","doi":"https://doi.org/10.1109/tip.2026.3675497","pmid":"https://pubmed.ncbi.nlm.nih.gov/41874996"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3675497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3675497","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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/A5038599874","display_name":"Dan Shi","orcid":"https://orcid.org/0000-0003-2773-9924"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Shi","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2773-9924","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5131071317","display_name":"Zechao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zechao Li","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5341-5985","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5131179844","display_name":"Lei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2993-7142","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jinhui Tang","orcid":"https://orcid.org/0000-0001-9008-222X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Tang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9008-222X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29297945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"3299","last_page":"3310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.4124999940395355,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.4124999940395355,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3921999931335449,"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":0.038600001484155655,"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/noise","display_name":"Noise (video)","score":0.6656000018119812},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.6053000092506409},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5828999876976013},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5120999813079834},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.499099999666214},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4749000072479248},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.39750000834465027},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.3790000081062317},{"id":"https://openalex.org/keywords/data-consistency","display_name":"Data consistency","score":0.3596000075340271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814300000667572},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6656000018119812},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.6053000092506409},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5828999876976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5662000179290771},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5120999813079834},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.499099999666214},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4749000072479248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44339999556541443},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C193519340","wikidata":"https://www.wikidata.org/wiki/Q891179","display_name":"Data loss","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3675497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3675497","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41874996","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41874996","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7071972172","display_name":null,"funder_award_id":"2025ZB557","funder_id":"https://openalex.org/F4320327778","funder_display_name":"Jiangsu Provincial Medical Youth Talent"},{"id":"https://openalex.org/G8190281492","display_name":null,"funder_award_id":"BK20251442","funder_id":"https://openalex.org/F4320313574","funder_display_name":"Jiangsu Province Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320313574","display_name":"Jiangsu Province Postdoctoral Science Foundation","ror":null},{"id":"https://openalex.org/F4320327778","display_name":"Jiangsu Provincial Medical Youth Talent","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Noisy":[0],"Correspondence":[1],"(NC),":[2],"caused":[3],"by":[4],"mismatched":[5],"pairs":[6,51,109],"in":[7,141],"multimedia":[8],"datasets,":[9],"poses":[10],"major":[11],"challenges":[12],"for":[13],"cross-modal":[14],"retrieval,":[15],"especially":[16],"under":[17],"high":[18],"noise":[19,30,171],"levels.":[20],"Existing":[21],"solutions":[22],"often":[23],"suffer":[24],"from":[25],"substantial":[26],"performance":[27,153],"degradation":[28],"as":[29,60,111],"levels":[31],"increase.":[32],"To":[33,124],"address":[34],"this":[35],"issue,":[36],"we":[37],"propose":[38],"Pseudo-Text":[39],"guided":[40],"Robust":[41],"Learning":[42],"(PTRL),":[43],"a":[44,66,89,112,133],"novel":[45],"framework":[46],"designed":[47],"to":[48,71,93],"identify":[49],"noisy":[50,77,85],"and":[52,64,76,120,128,154,164,179],"enhance":[53],"model":[54,122],"robustness.":[55],"Specifically,":[56],"PTRL":[57,87,131,150],"leverages":[58],"pseudo-text":[59,90],"explicit":[61],"supervision":[62],"signals":[63],"introduces":[65],"new":[67],"data":[68,115,118],"division":[69],"criterion":[70],"accurately":[72],"distinguish":[73],"between":[74],"clean":[75],"pairs.":[78],"Instead":[79],"of":[80,97,114,144,160],"discarding":[81],"or":[82],"directly":[83],"using":[84],"data,":[86],"proposes":[88],"replacement":[91],"strategy":[92],"maintain":[94],"semantic":[95],"consistency":[96],"the":[98,142],"training":[99,127],"set,":[100],"thereby":[101],"facilitating":[102],"more":[103],"reliable":[104],"learning.":[105],"In":[106],"addition,":[107],"pseudo-text-image":[108],"serve":[110],"form":[113],"augmentation,":[116],"enriching":[117],"diversity":[119],"improving":[121],"generalization.":[123],"further":[125],"stabilize":[126],"mitigate":[129],"overfitting,":[130],"incorporates":[132],"robust":[134],"InfoNCE":[135],"loss":[136],"that":[137,149],"is":[138],"particularly":[139],"effective":[140],"presence":[143],"noise.":[145],"Extensive":[146],"experiments":[147],"demonstrate":[148],"achieves":[151],"state-of-the-art":[152],"robustness,":[155],"with":[156],"an":[157,169],"RSum":[158],"improvements":[159],"+60.1%":[161],"on":[162,166],"Flickr30K":[163],"+22.6%":[165],"MS-COCO":[167],"at":[168,184],"80%":[170],"level,":[172],"significantly":[173],"outperforming":[174],"existing":[175],"methods.":[176],"The":[177],"datasets":[178],"source":[180],"code":[181],"are":[182],"available":[183],"https://github.com/shidan0122/PTRL.git.":[185]},"counts_by_year":[],"updated_date":"2026-03-31T06:02:25.137627","created_date":"2026-03-25T00:00:00"}