{"id":"https://openalex.org/W4390768707","doi":"https://doi.org/10.1007/s11042-023-17977-0","title":"Cascaded transformer-based networks for wikipedia large-scale image-caption matching","display_name":"Cascaded transformer-based networks for wikipedia large-scale image-caption matching","publication_year":2024,"publication_date":"2024-01-09","ids":{"openalex":"https://openalex.org/W4390768707","doi":"https://doi.org/10.1007/s11042-023-17977-0"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-023-17977-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-023-17977-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-023-17977-0.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11042-023-17977-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007125882","display_name":"Nicola Messina","orcid":"https://orcid.org/0000-0003-3011-2487"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Nicola Messina","raw_affiliation_strings":["Institute of Information Science and Technologies, National Research Council, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy"],"raw_orcid":"https://orcid.org/0000-0003-3011-2487","affiliations":[{"raw_affiliation_string":"Institute of Information Science and Technologies, National Research Council, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy","institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036992475","display_name":"Davide Alessandro Coccomini","orcid":"https://orcid.org/0000-0002-0755-6154"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Alessandro Coccomini","raw_affiliation_strings":["Institute of Information Science and Technologies, National Research Council, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0755-6154","affiliations":[{"raw_affiliation_string":"Institute of Information Science and Technologies, National Research Council, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy","institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082069715","display_name":"Andrea Esuli","orcid":"https://orcid.org/0000-0002-5725-4322"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Esuli","raw_affiliation_strings":["Institute of Information Science and Technologies, National Research Council, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5725-4322","affiliations":[{"raw_affiliation_string":"Institute of Information Science and Technologies, National Research Council, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy","institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047189288","display_name":"Fabrizio Falchi","orcid":"https://orcid.org/0000-0001-6258-5313"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabrizio Falchi","raw_affiliation_strings":["Institute of Information Science and Technologies, National Research Council, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6258-5313","affiliations":[{"raw_affiliation_string":"Institute of Information Science and Technologies, National Research Council, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy","institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007125882"],"corresponding_institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210155236"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.1643,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36824931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"83","issue":"23","first_page":"62915","last_page":"62935"},"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/T10028","display_name":"Topic Modeling","score":0.991100013256073,"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":0.9853000044822693,"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":0.9333834648132324},{"id":"https://openalex.org/keywords/encyclopedia","display_name":"Encyclopedia","score":0.5560666918754578},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.525388777256012},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4239945709705353},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4219723343849182},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4174032211303711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4017552137374878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9333834648132324},{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.5560666918754578},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.525388777256012},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4239945709705353},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4219723343849182},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4174032211303711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4017552137374878},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11042-023-17977-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-023-17977-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-023-17977-0.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},{"id":"pmh:oai:dnet:people______::0296aa22b6321e742547df94f88faaa7","is_oa":true,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::0296aa22b6321e742547df94f88faaa7","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Multimedia tools and applications (2024). doi:10.1007/s11042-023-17977-0","raw_type":"http://purl.org/coar/resource_type/c_6501"},{"id":"pmh:oai:zenodo.org:13913555","is_oa":true,"landing_page_url":"https://doi.org/10.1007/S11042-023-17977-0","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Multimedia Tools and Applications, 83, 62915\u201362935, (2024-01-09)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s11042-023-17977-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-023-17977-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-023-17977-0.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3674335838","display_name":null,"funder_award_id":"951911","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G6147754526","display_name":null,"funder_award_id":"B53D21008060008","funder_id":"https://openalex.org/F4320326084","funder_display_name":"Regione Toscana"}],"funders":[{"id":"https://openalex.org/F4320326084","display_name":"Regione Toscana","ror":null},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390768707.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1947481528","https://openalex.org/W2584992898","https://openalex.org/W2809734421","https://openalex.org/W2886641317","https://openalex.org/W2905544595","https://openalex.org/W2962739339","https://openalex.org/W2962788341","https://openalex.org/W2981586349","https://openalex.org/W2985951359","https://openalex.org/W3034655362","https://openalex.org/W3035390927","https://openalex.org/W3048588868","https://openalex.org/W3092820619","https://openalex.org/W3107503524","https://openalex.org/W3129130113","https://openalex.org/W3151130473","https://openalex.org/W3156892778","https://openalex.org/W3159619744","https://openalex.org/W3160179442","https://openalex.org/W3173220247","https://openalex.org/W3186068393","https://openalex.org/W3213100861","https://openalex.org/W3213148312","https://openalex.org/W4303444819","https://openalex.org/W4303444943","https://openalex.org/W4312933868","https://openalex.org/W4385569915","https://openalex.org/W4385612782","https://openalex.org/W4386065803","https://openalex.org/W6600424091","https://openalex.org/W6600654476","https://openalex.org/W6602331431","https://openalex.org/W6630860771"],"related_works":["https://openalex.org/W2348562996","https://openalex.org/W4387776128","https://openalex.org/W4244686159","https://openalex.org/W3159833212","https://openalex.org/W3010321750","https://openalex.org/W3007654203","https://openalex.org/W4206178588","https://openalex.org/W4287635093","https://openalex.org/W3094491777","https://openalex.org/W3214715529"],"abstract_inverted_index":{"Abstract":[0],"With":[1,182],"the":[2,64,74,91,98,110,115,132,146,151,159,175,188,197,206],"increasing":[3],"importance":[4],"of":[5,34,36,67,81,114,127,168],"multimedia":[6],"and":[7,21,53,57,112,139,150,170],"multilingual":[8],"data":[9,149],"in":[10,39,85,120,187,201],"online":[11,121],"encyclopedias,":[12],"novel":[13,65],"methods":[14],"are":[15],"needed":[16],"to":[17,55,104,137,184,205],"fill":[18],"domain":[19],"gaps":[20],"automatically":[22],"connect":[23],"different":[24],"modalities":[25],"for":[26],"increased":[27],"accessibility.":[28],"For":[29],"example,":[30],"Wikipedia":[31,71],"is":[32,214],"composed":[33],"millions":[35],"pages":[37,72],"written":[38,84],"multiple":[40,86],"languages.":[41],"Images,":[42],"when":[43],"present,":[44],"often":[45],"lack":[46],"textual":[47],"context,":[48],"thus":[49],"remaining":[50],"conceptually":[51],"floating":[52],"harder":[54],"find":[56],"manage.":[58],"In":[59],"this":[60,106],"work,":[61],"we":[62,191],"tackle":[63],"task":[66,107],"associating":[68],"images":[69,169],"from":[70],"with":[73,203,209],"correct":[75],"caption":[76],"among":[77],"a":[78,125,142,165],"large":[79,166],"pool":[80,167],"available":[82,216],"ones":[83],"languages,":[87],"as":[88],"required":[89],"by":[90,97,131],"image-caption":[92],"matching":[93],"Kaggle":[94],"challenge":[95,189],"organized":[96],"Wikimedia":[99],"Foundation.":[100],"A":[101],"system":[102],"able":[103,136],"perform":[105],"would":[108],"improve":[109],"accessibility":[111],"completeness":[113],"underlying":[116],"multi-modal":[117],"knowledge":[118],"graph":[119],"encyclopedias.":[122],"We":[123,153],"propose":[124],"cascade":[126],"two":[128],"models":[129],"powered":[130],"recent":[133],"Transformer":[134],"networks":[135],"efficiently":[138],"effectively":[140,163],"infer":[141],"relevance":[143],"score":[144],"between":[145],"query":[147],"image":[148],"captions.":[152],"verify":[154],"through":[155],"extensive":[156],"experiments":[157],"that":[158],"proposed":[160],"cascaded":[161],"approach":[162],"handles":[164],"captions":[171],"while":[172],"maintaining":[173],"bounded":[174],"overall":[176],"computational":[177],"complexity":[178],"at":[179,217],"inference":[180],"time.":[181],"respect":[183,204],"other":[185],"approaches":[186],"leaderboard,":[190],"can":[192],"achieve":[193],"remarkable":[194],"improvements":[195],"over":[196],"previous":[198],"proposals":[199],"(+8%":[200],"nDCG@5":[202],"sixth":[207],"position)":[208],"constrained":[210],"resources.":[211],"The":[212],"code":[213],"publicly":[215],"https://tinyurl.com/wiki-imcap":[218],".":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
