{"id":"https://openalex.org/W4286790011","doi":"https://doi.org/10.1007/s42979-022-01322-7","title":"CAPTION: Caption Analysis with Proposed Terms, Image of Objects, and Natural Language Processing","display_name":"CAPTION: Caption Analysis with Proposed Terms, Image of Objects, and Natural Language Processing","publication_year":2022,"publication_date":"2022-07-23","ids":{"openalex":"https://openalex.org/W4286790011","doi":"https://doi.org/10.1007/s42979-022-01322-7"},"language":"en","primary_location":{"id":"doi:10.1007/s42979-022-01322-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-022-01322-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-022-01322-7.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"SN Computer Science","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/s42979-022-01322-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064690343","display_name":"Leonardo A. Ferreira","orcid":"https://orcid.org/0000-0002-9856-2460"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leonardo A. Ferreira","raw_affiliation_strings":["Department of Electrical Engineering, FEI University Center, Av. H.de A.C. Branco, SBC, S\u00e3o Paulo, SP, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, FEI University Center, Av. H.de A.C. Branco, SBC, S\u00e3o Paulo, SP, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004183326","display_name":"Douglas De Rizzo Meneghetti","orcid":"https://orcid.org/0000-0002-0478-467X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Douglas De Rizzo Meneghetti","raw_affiliation_strings":["Department of Electrical Engineering, FEI University Center, Av. H.de A.C. Branco, SBC, S\u00e3o Paulo, SP, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, FEI University Center, Av. H.de A.C. Branco, SBC, S\u00e3o Paulo, SP, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062433660","display_name":"Marcos Ant\u00f4nio Lopes","orcid":"https://orcid.org/0000-0002-1007-1721"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos Lopes","raw_affiliation_strings":["Linguistics Department, University of S\u00e3o Paulo, Av. Prof. Luciano Gualberto, 403, S\u00e3o Paulo, SP, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistics Department, University of S\u00e3o Paulo, Av. Prof. Luciano Gualberto, 403, S\u00e3o Paulo, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001663435","display_name":"Paulo E. Santos","orcid":"https://orcid.org/0000-0001-8484-0354"},"institutions":[{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Paulo E. Santos","raw_affiliation_strings":["Centre for Defence Engineering Research and Training, College of Science and Engineering, Flinders University, 1284 South Rd, Clovelly Park, SA, 5042, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8484-0354","affiliations":[{"raw_affiliation_string":"Centre for Defence Engineering Research and Training, College of Science and Engineering, Flinders University, 1284 South Rd, Clovelly Park, SA, 5042, Australia","institution_ids":["https://openalex.org/I169541294"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001663435"],"corresponding_institution_ids":["https://openalex.org/I169541294"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.4063,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.55442744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":"5","first_page":null,"last_page":null},"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":0.9990000128746033,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.8536661863327026},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7684038877487183},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6698203086853027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6519791483879089},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6329207420349121},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5729281306266785},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5512755513191223},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.54758620262146},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5417050123214722},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3656404912471771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3654051423072815},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17714735865592957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8536661863327026},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7684038877487183},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6698203086853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6519791483879089},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6329207420349121},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5729281306266785},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5512755513191223},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.54758620262146},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5417050123214722},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3656404912471771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3654051423072815},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17714735865592957},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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":1,"locations":[{"id":"doi:10.1007/s42979-022-01322-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-022-01322-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-022-01322-7.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"SN Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s42979-022-01322-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-022-01322-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-022-01322-7.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"SN Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G29316538","display_name":null,"funder_award_id":"(Code 001)","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"}],"funders":[{"id":"https://openalex.org/F4320320977","display_name":"Flinders University","ror":"https://ror.org/01kpzv902"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4286790011.pdf","grobid_xml":"https://content.openalex.org/works/W4286790011.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W845365781","https://openalex.org/W1536680647","https://openalex.org/W1933349210","https://openalex.org/W2088049833","https://openalex.org/W2102605133","https://openalex.org/W2117539524","https://openalex.org/W2160613239","https://openalex.org/W2193145675","https://openalex.org/W2277195237","https://openalex.org/W2553303224","https://openalex.org/W2557728737","https://openalex.org/W2561715562","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2611009517","https://openalex.org/W2797871332","https://openalex.org/W2803259101","https://openalex.org/W2883512601","https://openalex.org/W2888283061","https://openalex.org/W2896348597","https://openalex.org/W2897521618","https://openalex.org/W2939888942","https://openalex.org/W2952003359","https://openalex.org/W2963037989","https://openalex.org/W2963299740","https://openalex.org/W2964081807","https://openalex.org/W3015965768","https://openalex.org/W3028688913","https://openalex.org/W3034971973","https://openalex.org/W3090139544","https://openalex.org/W3098389804","https://openalex.org/W3104379732","https://openalex.org/W3106250896","https://openalex.org/W3107670916","https://openalex.org/W3116109061","https://openalex.org/W3119241671","https://openalex.org/W3135211941","https://openalex.org/W3196928338","https://openalex.org/W4230097545","https://openalex.org/W4288083516","https://openalex.org/W6639102338"],"related_works":["https://openalex.org/W2737719445","https://openalex.org/W2898210368","https://openalex.org/W2382480268","https://openalex.org/W1976518449","https://openalex.org/W2732837990","https://openalex.org/W4206198161","https://openalex.org/W2363366881","https://openalex.org/W2055598517","https://openalex.org/W4239098401","https://openalex.org/W2363276194"],"abstract_inverted_index":{"Abstract":[0],"This":[1,96],"paper":[2],"proposes":[3],"a":[4,46,115,125],"novel":[5],"algorithm,":[6],"called":[7],"CAPTION,":[8],"for":[9,25],"identifying":[10],"and":[11,59],"correcting":[12],"errors":[13],"in":[14,28,39,56,76,81,110],"automatically":[15],"generated":[16],"image":[17],"captions.":[18],"The":[19],"algorithm":[20],"combines":[21],"Deep":[22],"Learning":[23],"(DL)":[24],"object":[26],"detection":[27],"images":[29],"with":[30,71,119],"Natural":[31,120],"Language":[32,121],"Processing":[33,122],"techniques.":[34],"CAPTION":[35],"has":[36,103],"been":[37,105],"tested":[38],"the":[40,57,77,82],"following":[41],"three":[42],"tasks:":[43],"(1)":[44],"classify":[45],"caption":[47],"as":[48],"correct":[49],"or":[50],"not;":[51],"(2)":[52],"detect":[53],"wrong":[54],"words":[55],"caption,":[58],"(3)":[60],"suggest":[61],"text":[62],"corrections.":[63],"Results":[64],"show":[65],"that":[66],"our":[67],"method":[68],"is":[69],"superior":[70],"respect":[72],"to":[73],"others":[74],"evaluated":[75],"same":[78],"data":[79],"set":[80],"error":[83],"correction":[84],"task.":[85],"These":[86],"other":[87],"methods":[88,132],"are":[89],"generally":[90],"based":[91],"exclusively":[92],"on":[93],"DL":[94,118,131],"models.":[95],"work":[97],"shows":[98],"that,":[99],"although":[100],"semantics":[101],"still":[102],"not":[104],"used":[106],"at":[107],"its":[108],"fullest":[109],"this":[111],"type":[112],"of":[113,117],"task,":[114],"combination":[116],"tools":[123],"presents":[124],"better":[126],"overall":[127],"performance":[128],"than":[129],"using":[130],"alone.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}