{"id":"https://openalex.org/W4414511109","doi":"https://doi.org/10.1007/s00521-025-11672-x","title":"Improving image captioning descriptiveness by ranking and LLM-based fusion","display_name":"Improving image captioning descriptiveness by ranking and LLM-based fusion","publication_year":2025,"publication_date":"2025-09-25","ids":{"openalex":"https://openalex.org/W4414511109","doi":"https://doi.org/10.1007/s00521-025-11672-x"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-025-11672-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11672-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11672-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"Neural Computing 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/s00521-025-11672-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065319505","display_name":"Luigi Celona","orcid":"https://orcid.org/0000-0002-5925-2646"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Luigi Celona","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milano-Bicocca, viale Sarca, 336, 20126, Milano, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5925-2646","affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milano-Bicocca, viale Sarca, 336, 20126, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013570285","display_name":"Simone Bianco","orcid":"https://orcid.org/0000-0002-7070-1545"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Bianco","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milano-Bicocca, viale Sarca, 336, 20126, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milano-Bicocca, viale Sarca, 336, 20126, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092231001","display_name":"Marco Donzella","orcid":null},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Donzella","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milano-Bicocca, viale Sarca, 336, 20126, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milano-Bicocca, viale Sarca, 336, 20126, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053344554","display_name":"Paolo Napoletano","orcid":"https://orcid.org/0000-0001-9112-0574"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Napoletano","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milano-Bicocca, viale Sarca, 336, 20126, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milano-Bicocca, viale Sarca, 336, 20126, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065319505"],"corresponding_institution_ids":["https://openalex.org/I66752286"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":2.7942,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.91613365,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"37","issue":"32","first_page":"27279","last_page":"27299"},"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":0.9959999918937683,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9761999845504761,"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/closed-captioning","display_name":"Closed captioning","score":0.9840999841690063},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.5447999835014343},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5332000255584717},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49410000443458557},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4925000071525574},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.48190000653266907},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9840999841690063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363999724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6632000207901001},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5974000096321106},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3472000062465668},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.33719998598098755},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32170000672340393},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00521-025-11672-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11672-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11672-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"Neural Computing and Applications","raw_type":"journal-article"},{"id":"pmh:oai:boa.unimib.it:10281/568682","is_oa":false,"landing_page_url":"https://hdl.handle.net/10281/568682","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s00521-025-11672-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11672-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11672-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414511109.pdf","grobid_xml":"https://content.openalex.org/works/W4414511109.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2137807925","https://openalex.org/W2185175083","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2962735233","https://openalex.org/W2962843773","https://openalex.org/W2986670728","https://openalex.org/W2988793532","https://openalex.org/W3091588028","https://openalex.org/W3173937618","https://openalex.org/W3174151851","https://openalex.org/W3176641147","https://openalex.org/W3177224328","https://openalex.org/W4312922092","https://openalex.org/W4365395065","https://openalex.org/W4372337842","https://openalex.org/W4391092966","https://openalex.org/W4393859682","https://openalex.org/W4394625850","https://openalex.org/W4401043827","https://openalex.org/W4402715874","https://openalex.org/W4402753771","https://openalex.org/W4402754015","https://openalex.org/W4402754212","https://openalex.org/W4403012121","https://openalex.org/W4404645960","https://openalex.org/W4408979777","https://openalex.org/W4409368286","https://openalex.org/W6898793548"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"State-of-the-art":[1],"(SoTA)":[2],"image":[3,85,226],"captioning":[4,50,95,259],"models":[5,51,111],"are":[6,139,201],"often":[7,39],"trained":[8],"on":[9,155],"the":[10,57,63,89,113,117,135,148,156,163,178,195,212,221,229,235,246,253],"MicroSoft":[11],"Common":[12],"Objects":[13],"in":[14,168],"Context":[15],"(MS-COCO)":[16],"dataset,":[17],"which":[18,60,130],"contains":[19],"human-annotated":[20],"captions":[21,38,86,90,138,196,251],"with":[22,207],"an":[23,106],"average":[24],"length":[25],"of":[26,165,170,214,225,240,248,255],"approximately":[27],"ten":[28],"tokens.":[29],"Although":[30],"effective":[31],"for":[32,252],"general":[33,65],"scene":[34],"understanding,":[35],"these":[36,191],"short":[37],"fail":[40],"to":[41,53,79,115,146,177,190],"capture":[42],"complex":[43],"scenes":[44],"and":[45,82,120,158,173,181,223,234,237,258],"convey":[46],"detailed":[47,151],"information.":[48],"Moreover,":[49],"tend":[52],"exhibit":[54],"bias":[55],"toward":[56],"\u201caverage\u201d":[58],"caption,":[59],"captures":[61],"only":[62],"more":[64,83,150,205,249],"aspects,":[66],"thus":[67],"overlooking":[68],"finer":[69],"details.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74,131],"present":[75],"a":[76,125,142],"novel":[77],"approach":[78,167],"generate":[80,116],"richer":[81],"informative":[84,238],"by":[87,198],"combining":[88,211],"generated":[91],"from":[92,112],"different":[93],"SoTA":[94,216],"models.":[96,260],"Our":[97],"proposed":[98],"method":[99,219],"requires":[100],"no":[101],"additional":[102,188],"model":[103,200],"training:":[104],"given":[105],"image,":[107],"it":[108],"leverages":[109],"pretrained":[110],"literature":[114],"initial":[118],"captions,":[119,227],"then":[121],"ranks":[122],"them":[123],"using":[124,141],"newly":[126],"introduced":[127],"image-text-based":[128],"metric,":[129],"name":[132],"BLIPScore.":[133],"Subsequently,":[134],"top":[136],"two":[137],"fused":[140],"Large":[143],"Language":[144],"Model":[145],"produce":[147],"final,":[149],"description.":[152],"Experimental":[153],"results":[154],"MS-COCO":[157],"Flickr30k":[159],"test":[160],"sets":[161],"demonstrate":[162],"effectiveness":[164],"our":[166,199,218],"terms":[169],"caption-image":[171],"alignment":[172],"hallucination":[174],"reduction":[175],"according":[176],"ALOHa,":[179],"CAPTURE,":[180],"Polos":[182],"metrics.":[183],"A":[184],"subjective":[185],"study":[186],"lends":[187],"support":[189],"results,":[192],"suggesting":[193],"that":[194],"produced":[197],"generally":[202],"perceived":[203],"as":[204],"consistent":[206],"human":[208],"judgment.":[209],"By":[210],"strengths":[213],"diverse":[215],"models,":[217],"enhances":[220],"quality":[222],"appeal":[224],"bridging":[228],"gap":[230],"between":[231],"automated":[232],"systems":[233],"rich":[236],"nature":[239],"human-generated":[241],"descriptions.":[242],"This":[243],"advance":[244],"enables":[245],"generation":[247],"suitable":[250],"training":[254],"both":[256],"vision-language":[257]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}