{"id":"https://openalex.org/W4412888136","doi":"https://doi.org/10.18653/v1/2025.findings-acl.838","title":"MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching","display_name":"MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888136","doi":"https://doi.org/10.18653/v1/2025.findings-acl.838"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.838","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.838","pdf_url":"https://aclanthology.org/2025.findings-acl.838.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.838.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011479082","display_name":"Fabian David Schmidt","orcid":"https://orcid.org/0009-0007-9841-2941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabian David Schmidt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070253689","display_name":"Florian Schneider","orcid":"https://orcid.org/0000-0002-7052-8404"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Schneider","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021287757","display_name":"Chris Biemann","orcid":"https://orcid.org/0000-0002-8449-9624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Biemann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079336821","display_name":"Goran Glava\u009a\u0161","orcid":"https://orcid.org/0000-0002-1301-6314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goran Glava\u0161","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16285","last_page":"16312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9818000197410583,"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":0.9818000197410583,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9585000276565552,"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":0.9448999762535095,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7485844492912292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7157576084136963},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6943453550338745},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6144613027572632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5229842662811279},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5184645056724548},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41623321175575256},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32324451208114624},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1633094847202301},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11683106422424316},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08073267340660095},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07964766025543213},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06510165333747864}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7485844492912292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157576084136963},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6943453550338745},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6144613027572632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5229842662811279},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5184645056724548},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41623321175575256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32324451208114624},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1633094847202301},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11683106422424316},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08073267340660095},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07964766025543213},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06510165333747864},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.838","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.838","pdf_url":"https://aclanthology.org/2025.findings-acl.838.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.838","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.838","pdf_url":"https://aclanthology.org/2025.findings-acl.838.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888136.pdf","grobid_xml":"https://content.openalex.org/works/W4412888136.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Existing":[0],"multilingual":[1,39,58,160,173],"vision-language":[2,15,40],"(VL)":[3],"benchmarks":[4,61],"often":[5],"only":[6],"cover":[7],"a":[8,37,65,134,169],"handful":[9],"of":[10,13,67,117,172,191,202],"languages.Consequently,":[11],"evaluations":[12],"large":[14],"models":[16,144],"(LVLMs)":[17],"predominantly":[18],"target":[19],"high-resource":[20],"languages,":[21,86,112],"underscoring":[22],"the":[23,56,189,192,196,203],"need":[24],"for":[25,28,110],"evaluation":[26],"data":[27],"lowresource":[29],"languages.To":[30],"address":[31],"this":[32],"limitation,":[33],"we":[34,163],"introduce":[35],"MVL-SIB,":[36],"massively":[38],"benchmark":[41,64],"that":[42,77,99,126,142,165],"evaluates":[43],"both":[44],"cross-modal":[45,81,118],"and":[46,119,195,211],"text-only":[47,120],"topical":[48,121],"matching":[49,83,122],"across":[50],"205":[51],"languages-over":[52],"100":[53],"more":[54,137],"than":[55,90,138],"most":[57],"existing":[59],"VL":[60,100,161,174],"encompass.We":[62],"then":[63],"range":[66],"open-weight":[68,127],"LVLMs":[69,78,103,128],"together":[70],"with":[71,136,158],"GPT-4o(mini)":[72],"on":[73,92,156],"MVL-SIB.Our":[74],"results":[75],"reveal":[76],"struggle":[79],"in":[80,84,102,176],"topic":[82,135,190],"lower-resource":[85,111],"performing":[87],"no":[88],"better":[89],"chance":[91],"languages":[93],"like":[94],"N'Koo.Our":[95],"analysis":[96],"further":[97,124],"reveals":[98],"support":[101,109],"declines":[104],"disproportionately":[105],"relative":[106],"to":[107,200],"textual":[108],"as":[113,168],"evidenced":[114],"by":[115],"comparison":[116],"performance.We":[123],"observe":[125],"do":[129],"not":[130,146],"benefit":[131],"from":[132,218],"representing":[133],"one":[139,201,216],"image,":[140],"suggesting":[141],"these":[143],"are":[145],"yet":[147],"fully":[148],"effective":[149],"at":[150],"handling":[151],"multiimage":[152],"tasks.By":[153],"correlating":[154],"performance":[155],"MVL-SIB":[157,166],"other":[159],"benchmarks,":[162],"highlight":[164],"serves":[167],"comprehensive":[170],"probe":[171],"understanding":[175],"LVLMs.":[177],"1":[178,182],"*":[179],"Equal":[180],"contribution.":[181],"Code:":[183],"https://github.com/floschne/mvl-sibImages-To-Sentences":[184],"(I2S)Which":[185],"sentence":[186,217],"best":[187],"matches":[188],"images?The":[193],"images":[194],"sentences":[197],"each":[198],"belong":[199],"following":[204],"topics:":[205],"\"entertainment\",":[206],"\"geography\",":[207],"\"health\",":[208],"\"politics\",":[209],"\"science":[210],"technology\",":[212],"\"sports\",":[213],"or":[214,222],"\"travel\".Choose":[215],"A,":[219],"B,":[220],"C,":[221],"D.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}