{"id":"https://openalex.org/W4415708870","doi":"https://doi.org/10.1109/icme59968.2025.11208949","title":"Learning from Noisy Data Using Pretrained Vision-Language Representations","display_name":"Learning from Noisy Data Using Pretrained Vision-Language Representations","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708870","doi":"https://doi.org/10.1109/icme59968.2025.11208949"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5041748666","display_name":"Yuqi Liao","orcid":"https://orcid.org/0000-0002-4663-1815"},"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":"Yuqi Liao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067704952","display_name":"Aodong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aodong Li","raw_affiliation_strings":["DOCOMO Beijing Communications Laboratories Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DOCOMO Beijing Communications Laboratories Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028846060","display_name":"Yisha Chen","orcid":null},"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":"Yisha Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113604020","display_name":"Qianfang Xu","orcid":null},"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":"Qianfang Xu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101858238","display_name":"Jiarui Xie","orcid":"https://orcid.org/0000-0002-6186-4350"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiarui Xie","raw_affiliation_strings":["DOCOMO Beijing Communications Laboratories Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DOCOMO Beijing Communications Laboratories Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081842587","display_name":"Anxin Li","orcid":"https://orcid.org/0000-0002-0682-7178"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anxin Li","raw_affiliation_strings":["DOCOMO Beijing Communications Laboratories Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DOCOMO Beijing Communications Laboratories Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100771377","display_name":"Bo Xiao","orcid":"https://orcid.org/0000-0003-3392-3293"},"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":"Bo Xiao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"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":0.14899935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.5788999795913696,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.5788999795913696,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.18889999389648438,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.028699999675154686,"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":0.7063000202178955},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6018999814987183},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.5447999835014343},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5329999923706055},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49810001254081726},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46810001134872437},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.45489999651908875},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.3840999901294708},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827000021934509},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7063000202178955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6962000131607056},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5368000268936157},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5329999923706055},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49810001254081726},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46810001134872437},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.45489999651908875},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.35359999537467957},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25220000743865967},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1514928307","https://openalex.org/W2566079294","https://openalex.org/W2962762068","https://openalex.org/W2964274690","https://openalex.org/W2967052791","https://openalex.org/W3035682985","https://openalex.org/W3042609801","https://openalex.org/W3171635822","https://openalex.org/W3173874704","https://openalex.org/W3190486510","https://openalex.org/W3198675127","https://openalex.org/W3204785235","https://openalex.org/W4221161368","https://openalex.org/W4312249250","https://openalex.org/W4312305885","https://openalex.org/W4312440249","https://openalex.org/W4312601326","https://openalex.org/W4312766345","https://openalex.org/W4313014573","https://openalex.org/W4313135270","https://openalex.org/W4386071642","https://openalex.org/W4386075521","https://openalex.org/W4386076354","https://openalex.org/W4402660120","https://openalex.org/W4403942245"],"related_works":[],"abstract_inverted_index":{"Real-World":[0],"image":[1],"data":[2,23],"often":[3],"contains":[4],"complex":[5],"noise":[6,45,123,126,206],"patterns":[7],"that":[8,43,111],"compromise":[9],"the":[10,35,76,81,168,184,221],"generalization":[11],"capability":[12],"of":[13,37,47,62,70,78,83,143,152,158,167,186,200],"deep":[14],"learning":[15,20],"models.":[16,79],"Existing":[17],"methods":[18],"for":[19],"from":[21],"noisy":[22,175],"typically":[24],"rely":[25],"on":[26,129,202,212],"oversimplified":[27],"assumptions":[28],"about":[29],"labeling":[30],"noise,":[31,54],"failing":[32],"to":[33,57,96,119],"capture":[34],"complexity":[36],"real-world":[38,44,215],"noise.":[39,216],"Our":[40],"investigation":[41],"reveals":[42],"consists":[46],"both":[48,121,172],"out-of-domain":[49],"(OOD)":[50],"and":[51,115,124,141,164,174,207,220],"in-domain":[52],"(ID)":[53],"frequently":[55],"due":[56],"web":[58],"crawler":[59],"imprecision,":[60],"lack":[61],"domain":[63],"knowledge,":[64],"and/or":[65],"annotator":[66],"oversight.":[67],"Insufficient":[68],"consideration":[69],"either":[71],"part":[72],"can":[73],"negatively":[74],"affect":[75],"performance":[77,198],"Furthermore,":[80],"prevalence":[82],"sub-class":[84],"label":[85],"errors":[86],"in":[87,161,177],"images":[88],"with":[89,204,214],"similar":[90],"visual":[91],"appearances":[92],"presents":[93],"a":[94,105,153,178,208],"challenge":[95],"fine-grained":[97],"classification":[98],"tasks.":[99],"In":[100],"this":[101],"paper,":[102],"we":[103],"propose":[104],"novel":[106],"but":[107],"simple":[108],"denoising":[109],"framework":[110],"leverages":[112],"textual":[113],"labels":[114,160,176],"pretrained":[116],"vision-language":[117,147],"models":[118],"mitigate":[120],"OOD":[122,144],"ID":[125],"without":[127],"relying":[128],"restrictive":[130],"assumptions.":[131],"Specifically,":[132],"our":[133,187],"approach":[134],"comprises":[135],"three":[136],"sequential":[137],"stages:":[138],"1)":[139],"identification":[140,151],"exclusion":[142],"samples":[145],"using":[146,171],"similarity":[148],"distribution;":[149],"2)":[150],"clean":[154,173],"dataset":[155],"through":[156],"analysis":[157],"consistent":[159],"augmented":[162],"images;":[163],"3)":[165],"training":[166],"final":[169],"model":[170],"semi-supervised":[179],"manner.":[180],"Extensive":[181],"experiments":[182],"demonstrate":[183],"efficacy":[185],"proposed":[188],"method,":[189],"which":[190],"outperforms":[191],"state-of-the-art":[192],"approaches.":[193],"We":[194],"achieve":[195],"an":[196],"average":[197],"improvement":[199,211],"11%":[201],"datasets":[203,213],"synthetic":[205],"notable":[209],"6%":[210],"The":[217],"source":[218],"code":[219],"Appendix":[222],"are":[223],"available":[224],"at":[225],"https://github.com/LiaoYuqi2000/Multimodal-Lnl.":[226]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}