{"id":"https://openalex.org/W4293567540","doi":"https://doi.org/10.1145/3503161.3548003","title":"Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning","display_name":"Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4293567540","doi":"https://doi.org/10.1145/3503161.3548003"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548003","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548003","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.12526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101488662","display_name":"Yabing Wang","orcid":"https://orcid.org/0000-0001-7231-1260"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yabing Wang","raw_affiliation_strings":["Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008417257","display_name":"Jianfeng Dong","orcid":"https://orcid.org/0000-0001-5244-3274"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Dong","raw_affiliation_strings":["Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033661176","display_name":"Tianxiang Liang","orcid":"https://orcid.org/0009-0004-6794-9381"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianxiang Liang","raw_affiliation_strings":["Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058828501","display_name":"Minsong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minsong Zhang","raw_affiliation_strings":["Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114723550","display_name":"Rui Cai","orcid":"https://orcid.org/0009-0006-2823-3051"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Cai","raw_affiliation_strings":["Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106406563","display_name":"Xun Wang","orcid":"https://orcid.org/0000-0001-5566-4689"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Wang","raw_affiliation_strings":["Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101488662"],"corresponding_institution_ids":["https://openalex.org/I75059550"],"apc_list":null,"apc_paid":null,"fwci":1.3731,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.87369616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"422","last_page":"433"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9970999956130981,"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":0.9955999851226807,"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":0.8680280447006226},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6505307555198669},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6146899461746216},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5871348977088928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5763452053070068},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5022833347320557},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4826003313064575},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45978477597236633},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4570671319961548},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3672525882720947},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3571314811706543},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16043445467948914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8680280447006226},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6505307555198669},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6146899461746216},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5871348977088928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763452053070068},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5022833347320557},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4826003313064575},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45978477597236633},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4570671319961548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3672525882720947},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3571314811706543},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16043445467948914},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548003","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548003","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2208.12526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.12526","pdf_url":"https://arxiv.org/pdf/2208.12526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2208.12526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.12526","pdf_url":"https://arxiv.org/pdf/2208.12526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W1982795953","https://openalex.org/W2108598243","https://openalex.org/W2142540378","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2251765408","https://openalex.org/W2407145437","https://openalex.org/W2418300416","https://openalex.org/W2425121537","https://openalex.org/W2549139847","https://openalex.org/W2552579943","https://openalex.org/W2596164567","https://openalex.org/W2606473278","https://openalex.org/W2616994964","https://openalex.org/W2749708282","https://openalex.org/W2753311918","https://openalex.org/W2774267535","https://openalex.org/W2778100917","https://openalex.org/W2885775891","https://openalex.org/W2886641317","https://openalex.org/W2892181857","https://openalex.org/W2896234464","https://openalex.org/W2896457183","https://openalex.org/W2923476781","https://openalex.org/W2948859046","https://openalex.org/W2955273087","https://openalex.org/W2956018683","https://openalex.org/W2956959730","https://openalex.org/W2962824887","https://openalex.org/W2963524571","https://openalex.org/W2963909453","https://openalex.org/W2965458216","https://openalex.org/W2973088264","https://openalex.org/W2974497444","https://openalex.org/W2975813532","https://openalex.org/W2984008963","https://openalex.org/W2988823324","https://openalex.org/W2989322838","https://openalex.org/W2991118492","https://openalex.org/W2997786945","https://openalex.org/W2998356391","https://openalex.org/W3015354748","https://openalex.org/W3028831795","https://openalex.org/W3033518368","https://openalex.org/W3035265375","https://openalex.org/W3035309251","https://openalex.org/W3035356601","https://openalex.org/W3035688398","https://openalex.org/W3038033387","https://openalex.org/W3043840704","https://openalex.org/W3091184187","https://openalex.org/W3091588028","https://openalex.org/W3097619042","https://openalex.org/W3102566412","https://openalex.org/W3102887392","https://openalex.org/W3107973541","https://openalex.org/W3111552341","https://openalex.org/W3115711567","https://openalex.org/W3119510203","https://openalex.org/W3126337491","https://openalex.org/W3130796238","https://openalex.org/W3135367836","https://openalex.org/W3152619510","https://openalex.org/W3152798676","https://openalex.org/W3153232703","https://openalex.org/W3163874900","https://openalex.org/W3166037607","https://openalex.org/W3166396011","https://openalex.org/W3166893724","https://openalex.org/W3168640669","https://openalex.org/W3168851777","https://openalex.org/W3171668871","https://openalex.org/W3171927989","https://openalex.org/W3173223111","https://openalex.org/W3173449436","https://openalex.org/W3173666333","https://openalex.org/W3174010726","https://openalex.org/W3174364033","https://openalex.org/W3175888430","https://openalex.org/W3177654849","https://openalex.org/W3182937942","https://openalex.org/W3184203741","https://openalex.org/W3201519611","https://openalex.org/W3205408642","https://openalex.org/W3206019042","https://openalex.org/W3206597437","https://openalex.org/W3207042189","https://openalex.org/W3207410886","https://openalex.org/W3207603991","https://openalex.org/W3207608362","https://openalex.org/W3209275363","https://openalex.org/W4210900713","https://openalex.org/W4211053420","https://openalex.org/W4212841753","https://openalex.org/W4213286388","https://openalex.org/W4225547367","https://openalex.org/W4225564601","https://openalex.org/W4283797848","https://openalex.org/W4285345750","https://openalex.org/W4287245501","https://openalex.org/W4299579390","https://openalex.org/W4312305353"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2375873920","https://openalex.org/W2384362569","https://openalex.org/W3151736118","https://openalex.org/W2146114872","https://openalex.org/W2142795561","https://openalex.org/W2392060890","https://openalex.org/W4362495644"],"abstract_inverted_index":{"Despite":[0],"the":[1,5,21,77,108,117,124,136,140,159,167],"recent":[2,185],"developments":[3],"in":[4,119],"field":[6],"of":[7,23,139],"cross-modal":[8,35,152],"retrieval,":[9],"there":[10],"has":[11],"been":[12],"less":[13],"research":[14],"focusing":[15],"on":[16,147],"low-resource":[17,39,55],"languages":[18],"due":[19],"to":[20,49,65,89,99,103,133],"lack":[22],"manually":[24],"annotated":[25],"datasets.":[26],"In":[27,175],"this":[28,42],"paper,":[29],"we":[30,44,83,122],"propose":[31],"a":[32,85,96,179,184,196],"noise-robust":[33,91],"cross-lingual":[34],"retrieval":[36,78,153],"method":[37,88,164,203],"for":[38,54],"languages.":[40,56],"To":[41,80],"end,":[43],"use":[45],"Machine":[46],"Translation":[47],"(MT)":[48],"construct":[50],"pseudo-parallel":[51],"sentence":[52],"pairs":[53],"However,":[57],"as":[58],"MT":[59],"is":[60,204],"not":[61],"perfect,":[62],"it":[63],"tends":[64],"introduce":[66,84],"noise":[67,137],"during":[68],"translation,":[69],"rendering":[70],"textual":[71,141],"embeddings":[72],"corrupted":[73],"and":[74,111,130,150,158,187,211],"thereby":[75],"compromising":[76],"performance.":[79],"alleviate":[81],"this,":[82],"multi-view":[86],"self-distillation":[87],"learn":[90],"target-language":[92],"representations,":[93],"which":[94],"employs":[95],"cross-attention":[97],"module":[98],"generate":[100],"soft":[101],"pseudo-targets":[102],"provide":[104],"direct":[105],"supervision":[106],"from":[107,183],"similarity-based":[109],"view":[110],"feature-based":[112],"view.":[113],"Besides,":[114],"inspired":[115],"by":[116],"back-translation":[118],"unsupervised":[120],"MT,":[121],"minimize":[123],"semantic":[125],"discrepancies":[126],"between":[127],"origin":[128],"sentences":[129,132],"back-translated":[131],"further":[134],"improve":[135],"robustness":[138],"encoder.":[142],"Extensive":[143],"experiments":[144],"are":[145,213],"conducted":[146],"three":[148],"video-text":[149],"image-text":[151],"benchmarks":[154],"across":[155],"different":[156],"languages,":[157],"results":[160],"demonstrate":[161],"that":[162,201],"our":[163,193,202],"significantly":[165],"improves":[166],"overall":[168],"performance":[169,198],"without":[170],"using":[171],"extra":[172],"human-labeled":[173],"data.":[174],"addition,":[176],"equipped":[177],"with":[178,206],"pre-trained":[180],"visual":[181],"encoder":[182],"vision":[186],"language":[188],"pre-training":[189,208],"framework,":[190],"i.e.,":[191],"CLIP,":[192],"model":[194],"achieves":[195],"significant":[197],"gain,":[199],"showing":[200],"compatible":[205],"popular":[207],"models.":[209],"Code":[210],"data":[212],"available":[214],"at":[215],"https://github.com/HuiGuanLab/nrccr.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}