{"id":"https://openalex.org/W4415539700","doi":"https://doi.org/10.1145/3746027.3755585","title":"Noise Self-Correction via Relation Propagation for Robust Cross-Modal Retrieval","display_name":"Noise Self-Correction via Relation Propagation for Robust Cross-Modal Retrieval","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539700","doi":"https://doi.org/10.1145/3746027.3755585"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755585","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5045021378","display_name":"R.Y. 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":"Ruoxuan Li","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0001-3316-2490","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111154303","display_name":"Xiangyu Wu","orcid":"https://orcid.org/0009-0005-5689-3818"},"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":"Xiangyu Wu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-5689-3818","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397623","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5245-3584"},"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":"Yang Yang","raw_affiliation_strings":["Nanjing University of Science and Technology, NanJing, China"],"raw_orcid":"https://orcid.org/0000-0002-5245-3584","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, NanJing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.26095627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4748","last_page":"4757"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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":0.9973999857902527,"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/ambiguity","display_name":"Ambiguity","score":0.5608999729156494},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5080999732017517},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5037999749183655},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48809999227523804},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43880000710487366},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4359999895095825},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.43160000443458557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3971000015735626},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3804999887943268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7020000219345093},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5608999729156494},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5037999749183655},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4359999895095825},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4108999967575073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40959998965263367},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3711000084877014},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3149999976158142},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29019999504089355},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755585","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2185175083","https://openalex.org/W4321488152","https://openalex.org/W4389257994"],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,25],"refers":[2],"to":[3,96,111,133],"identifying":[4],"semantically":[5],"relevant":[6],"data":[7],"across":[8],"different":[9],"modalities.":[10],"However,":[11],"annotation":[12],"errors":[13],"or":[14,42],"inherent":[15],"ambiguity":[16],"can":[17],"cause":[18],"semantic":[19],"inconsistency":[20],"in":[21],"sample":[22],"pairs,":[23],"degrading":[24],"performance.":[26],"Prior":[27],"efforts":[28],"either":[29],"relied":[30],"heavily":[31],"on":[32,73,151],"the":[33,113,123],"quality":[34,145],"of":[35,79,116],"explicitly":[36],"dividing":[37],"clean":[38],"and":[39,130,154],"noisy":[40,80],"subsets,":[41],"solely":[43],"leveraged":[44],"carefully":[45],"selected":[46],"single":[47],"anchor":[48],"information,":[49],"neglecting":[50],"relationships":[51,132],"among":[52],"diverse":[53],"neighbors.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"propose":[59],"a":[60,74,98,135],"novel":[61],"Graph-based":[62],"Label":[63],"Propagation":[64],"(GLP)":[65],"framework":[66],"that":[67,157],"learns":[68],"pseudo-labels":[69,125],"via":[70,91],"label":[71,121],"propagation":[72],"sparse":[75,99],"graph,":[76],"enabling":[77],"self-correction":[78],"labels.":[81],"Specifically,":[82],"each":[83],"modality's":[84],"instances":[85],"are":[86,103],"treated":[87],"as":[88],"nodes,":[89],"connected":[90],"k-nearest":[92],"neighbor":[93],"(kNN)":[94],"search":[95],"form":[97],"graph.":[100],"Pseudo-label":[101],"vectors":[102],"generated":[104],"for":[105],"all":[106],"nodes":[107],"within":[108],"one":[109],"modality":[110],"capture":[112],"matching":[114,137],"degree":[115],"inter-modal":[117,131],"nodes.":[118,149],"Through":[119],"iterative":[120],"propagation,":[122],"stabilized":[124],"implicitly":[126],"exploit":[127],"both":[128],"intra-":[129],"derive":[134],"reliable":[136],"degree.":[138],"A":[139],"dynamic":[140],"queue":[141],"further":[142],"enhances":[143],"graph":[144],"by":[146],"updating":[147],"high-quality":[148],"Experiments":[150],"Flickr30K,":[152],"MSCOCO,":[153],"CC120K":[155],"show":[156],"our":[158],"method":[159],"outperforms":[160],"state-of-the-art":[161],"approaches,":[162],"especially":[163],"under":[164],"high":[165],"noise.":[166],"Code":[167],"is":[168],"available":[169],"at":[170],"https://github.com/njustkmg/MM25-GLP.":[171]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}