{"id":"https://openalex.org/W4399759139","doi":"https://doi.org/10.1145/3726302.3730302","title":"LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data","display_name":"LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4399759139","doi":"https://doi.org/10.1145/3726302.3730302"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730302","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730302","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730302","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015638199","display_name":"Grigor Bezirganyan","orcid":"https://orcid.org/0000-0003-0428-1973"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210142724","display_name":"Centrale Marseille","ror":"https://ror.org/040baw385","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210142724"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Grigor Bezirganyan","raw_affiliation_strings":["Doctoral School in Mathematics and Computer Science, Aix-Marseille University, Marseille, France and CNRS, Marseille, France"],"raw_orcid":"https://orcid.org/0000-0003-0428-1973","affiliations":[{"raw_affiliation_string":"Doctoral School in Mathematics and Computer Science, Aix-Marseille University, Marseille, France and CNRS, Marseille, France","institution_ids":["https://openalex.org/I4210142724","https://openalex.org/I1294671590","https://openalex.org/I21491767"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102864036","display_name":"Sana Sellami","orcid":"https://orcid.org/0000-0001-8302-3053"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210142724","display_name":"Centrale Marseille","ror":"https://ror.org/040baw385","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210142724"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sana Sellami","raw_affiliation_strings":["Aix-Marseille University, Marseille, France and CNRS, Marseille, France"],"raw_orcid":"https://orcid.org/0000-0001-8302-3053","affiliations":[{"raw_affiliation_string":"Aix-Marseille University, Marseille, France and CNRS, Marseille, France","institution_ids":["https://openalex.org/I4210142724","https://openalex.org/I1294671590","https://openalex.org/I21491767"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091872345","display_name":"Laure Berti\u2010\u00c9quille","orcid":"https://orcid.org/0000-0002-8046-0570"},"institutions":[{"id":"https://openalex.org/I4210097770","display_name":"Acteurs, Ressources et Territoires dans le D\u00e9veloppement","ror":"https://ror.org/00f5hap04","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I131077856","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210097770","https://openalex.org/I4210150854","https://openalex.org/I4405261681"]},{"id":"https://openalex.org/I4210166444","display_name":"Institut de Recherche pour le D\u00e9veloppement","ror":"https://ror.org/05q3vnk25","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1327553481","https://openalex.org/I154202486","https://openalex.org/I2799535048","https://openalex.org/I2802818602","https://openalex.org/I4210088668","https://openalex.org/I4210090127","https://openalex.org/I4210113730","https://openalex.org/I4210131494","https://openalex.org/I4210166444","https://openalex.org/I4405257220"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laure Berti-\u00c9quille","raw_affiliation_strings":["IRD, Montpellier, France and ESPACE-DEV, Montpellier, France"],"raw_orcid":"https://orcid.org/0000-0002-8046-0570","affiliations":[{"raw_affiliation_string":"IRD, Montpellier, France and ESPACE-DEV, Montpellier, France","institution_ids":["https://openalex.org/I4210097770","https://openalex.org/I4210166444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058109847","display_name":"S\u00e9bastien Fournier","orcid":"https://orcid.org/0000-0002-1611-0744"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210142724","display_name":"Centrale Marseille","ror":"https://ror.org/040baw385","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210142724"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Fournier","raw_affiliation_strings":["Aix-Marseille University, Marseille, France and CNRS, Marseille, France"],"raw_orcid":"https://orcid.org/0000-0002-1611-0744","affiliations":[{"raw_affiliation_string":"Aix-Marseille University, Marseille, France and CNRS, Marseille, France","institution_ids":["https://openalex.org/I4210142724","https://openalex.org/I1294671590","https://openalex.org/I21491767"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015638199"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210142724"],"apc_list":null,"apc_paid":null,"fwci":5.9986,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95061472,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3782","last_page":"3791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9958000183105469,"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/T10028","display_name":"Topic Modeling","score":0.9958000183105469,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9851999878883362,"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/T11309","display_name":"Music and Audio Processing","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/benchmarking","display_name":"Benchmarking","score":0.8609539270401001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8089225888252258},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6741390824317932},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6430035829544067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6308419704437256},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5951584577560425},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.415897935628891},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36731815338134766}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8609539270401001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089225888252258},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6741390824317932},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6430035829544067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6308419704437256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5951584577560425},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.415897935628891},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36731815338134766},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3726302.3730302","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730302","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730302","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.09864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09864","pdf_url":"https://arxiv.org/pdf/2406.09864","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-04823375v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04823375","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIGIR'25 : 48th international ACM SIGIR conference on research and development in information retrieval, Jul 2025, Padua, Italy. Association for Computing Machinery, pp.3782-3791, 2025, 979-8-4007-1592-1. ⟨10.1145/3726302.3730302⟩","raw_type":"Proceedings"},{"id":"pmh:oai:HAL:hal-05282191v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05282191","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, Jul 2025, Padua, Italy. pp.3782-3791, ⟨10.1145/3726302.3730302⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730302","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730302","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730302","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399759139.pdf","grobid_xml":"https://content.openalex.org/works/W4399759139.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2052666245","https://openalex.org/W2111959010","https://openalex.org/W2187089797","https://openalex.org/W2747874407","https://openalex.org/W2948153973","https://openalex.org/W2963341956","https://openalex.org/W2990138404","https://openalex.org/W2992429266","https://openalex.org/W3102100346","https://openalex.org/W3104448368","https://openalex.org/W3111980464","https://openalex.org/W3164731060","https://openalex.org/W3168463823","https://openalex.org/W4224926219","https://openalex.org/W4283800180","https://openalex.org/W4303647871","https://openalex.org/W4386302153","https://openalex.org/W4393156830","https://openalex.org/W4412272069","https://openalex.org/W6890025973"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W4399363378","https://openalex.org/W4380075502","https://openalex.org/W3197494161","https://openalex.org/W3011727199","https://openalex.org/W4390452972"],"abstract_inverted_index":{"Multimodal":[0],"Deep":[1,154],"Learning":[2],"enhances":[3],"decision-making":[4],"by":[5],"integrating":[6],"diverse":[7],"information":[8],"sources,":[9],"such":[10],"as":[11,108],"texts,":[12],"images,":[13],"audio,":[14,40],"and":[15,42,70,91,97,101,136,156,164,171,176,180,201,212,216],"videos.":[16],"To":[17],"develop":[18],"trustworthy":[19,179,200],"multimodal":[20,37,182],"approaches,":[21],"it":[22],"is":[23,105,144],"essential":[24],"to":[25,95,169,197],"understand":[26],"how":[27],"uncertainty":[28,94,149],"impacts":[29],"these":[30],"models.":[31],"We":[32,186],"propose":[33],"LUMA,":[34],"a":[35,109],"unique":[36],"dataset,":[38],"featuring":[39],"image,":[41],"textual":[43],"data":[44,72],"from":[45,52,66],"50":[46],"classes,":[47],"specifically":[48],"designed":[49],"for":[50,115,133,206,214],"learning":[51,184,204],"uncertain":[53],"data.":[54],"It":[55],"extends":[56],"the":[57,75,85,113,120,124,127,129,173,189,194,218],"well-known":[58],"CIFAR":[59],"10/100":[60],"dataset":[61,83,121,163,191,219],"with":[62,122],"audio":[63,68],"samples":[64],"extracted":[65],"three":[67,148],"corpora,":[69],"text":[71],"generated":[73],"using":[74],"Gemma-7B":[76],"Large":[77],"Language":[78],"Model":[79],"(LLM).":[80],"The":[81,210],"LUMA":[82,104,190],"enables":[84],"controlled":[86],"injection":[87],"of":[88,93,119,126,131,178],"varying":[89],"types":[90],"degrees":[92],"achieve":[96],"tailor":[98],"specific":[99],"experiments":[100],"benchmarking":[102,177],"initiatives.":[103],"also":[106,145],"available":[107],"Python":[110],"package":[111],"including":[112],"functions":[114],"generating":[116],"multiple":[117],"variants":[118],"controlling":[123],"diversity":[125],"data,":[128],"amount":[130],"noise":[132],"each":[134],"modality,":[135],"adding":[137],"out-of-distribution":[138],"samples.":[139],"A":[140],"baseline":[141],"pre-trained":[142],"model":[143],"provided":[146],"alongside":[147],"quantification":[150],"methods:":[151],"Monte-Carlo":[152],"Dropout,":[153],"Ensemble,":[155],"Reliable":[157],"Conflictive":[158],"Multi-View":[159],"Learning.":[160],"This":[161],"comprehensive":[162],"its":[165],"tools":[166],"are":[167],"intended":[168],"promote":[170],"support":[172],"development,":[174],"evaluation,":[175],"robust":[181,202],"deep":[183],"approaches.":[185],"anticipate":[187],"that":[188],"will":[192],"help":[193],"research":[195],"community":[196],"design":[198],"more":[199],"machine":[203],"approaches":[205],"safety":[207],"critical":[208],"applications.":[209],"code":[211],"instructions":[213],"downloading":[215],"processing":[217],"can":[220],"be":[221],"found":[222],"at:":[223],"https://github.com/bezirganyan/LUMA.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-13T08:25:38.343686","created_date":"2025-10-10T00:00:00"}