{"id":"https://openalex.org/W7129018100","doi":"https://doi.org/10.1145/3777490.3777491","title":"On The Automatic Image Captioning Task In Italian: A Human-Centric Approach","display_name":"On The Automatic Image Captioning Task In Italian: A Human-Centric Approach","publication_year":2026,"publication_date":"2026-01-21","ids":{"openalex":"https://openalex.org/W7129018100","doi":"https://doi.org/10.1145/3777490.3777491"},"language":null,"primary_location":{"id":"doi:10.1145/3777490.3777491","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777490.3777491","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Human Centred Artificial Intelligence - Education and Practice","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3777490.3777491","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040132962","display_name":"Valentina De Amicis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Valentina De Amicis","raw_affiliation_strings":["Technological University Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0009-0009-6839-592X","affiliations":[{"raw_affiliation_string":"Technological University Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083283778","display_name":"Rajesh Jaiswal","orcid":"https://orcid.org/0000-0002-4530-7079"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Rajesh Jaiswal","raw_affiliation_strings":["Technological University Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-4530-7079","affiliations":[{"raw_affiliation_string":"Technological University Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009919621","display_name":"Fernando P\u00e9rez-T\u00e9llez","orcid":"https://orcid.org/0000-0003-4978-2843"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Fernando Perez-Tellez","raw_affiliation_strings":["Technological University Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0003-4978-2843","affiliations":[{"raw_affiliation_string":"Technological University Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19787866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9914000034332275,"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":0.9914000034332275,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0007999999797903001,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9674000144004822},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5828999876976013},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5171999931335449},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.507099986076355},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4812000095844269},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.46889999508857727},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.45980000495910645},{"id":"https://openalex.org/keywords/compatibility","display_name":"Compatibility (geochemistry)","score":0.36899998784065247}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9674000144004822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760200023651123},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5828999876976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5752000212669373},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5726000070571899},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.46889999508857727},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C2778648169","wikidata":"https://www.wikidata.org/wiki/Q967768","display_name":"Compatibility (geochemistry)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C2987567764","wikidata":"https://www.wikidata.org/wiki/Q125421","display_name":"Second language","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3777490.3777491","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777490.3777491","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Human Centred Artificial Intelligence - Education and Practice","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3777490.3777491","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777490.3777491","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Human Centred Artificial Intelligence - Education and Practice","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.5217390060424805,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W2775113335","https://openalex.org/W2803259101","https://openalex.org/W2990751682","https://openalex.org/W3081796931","https://openalex.org/W3128307553","https://openalex.org/W3153332739","https://openalex.org/W3216130706","https://openalex.org/W4289654392","https://openalex.org/W4292615965","https://openalex.org/W4322761295","https://openalex.org/W4362700943","https://openalex.org/W4385872197","https://openalex.org/W4387235032","https://openalex.org/W4387912979","https://openalex.org/W4387954093"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Image":[1],"Captioning":[2],"(AIC)":[3],"combines":[4],"two":[5],"distinct":[6],"machine":[7],"learning":[8],"disciplines,":[9],"Computer":[10],"Vision":[11],"(CV)":[12],"and":[13,80,98,104,115,118,123,130,146,171,183,198,216,226],"Natural":[14],"Language":[15],"Processing":[16],"(NLP),":[17],"forming":[18],"a":[19,190],"challenging":[20],"research":[21,24,71],"landscape.":[22],"Much":[23],"has":[25],"been":[26],"carried":[27],"out":[28],"for":[29,48,63,157],"AIC":[30,60,221],"in":[31,208,220],"the":[32,37,64,109],"English":[33,40],"language":[34,41],"facilitated":[35],"by":[36],"availability":[38],"of":[39,53,69,92,108,112],"datasets.":[42,159],"However,":[43],"this":[44,54,70],"is":[45,56,193],"not":[46,144],"true":[47],"other":[49],"languages.":[50],"The":[51,67,95,132,140],"aim":[52],"work":[55],"to":[57,75,152,175,178,195],"investigate":[58,153],"existing":[59],"models\u2019":[61],"compatibility":[62],"Italian":[65],"language.":[66],"scope":[68],"will":[72],"be":[73,176,196],"aimed":[74],"reduced":[76],"complexity,":[77],"improved":[78],"efficiency,":[79],"readily":[81],"trainable":[82],"models":[83],"on":[84,106,137,214],"smaller":[85],"datasets":[86],"while":[87,223],"maintaining":[88],"an":[89],"acceptable":[90],"level":[91],"caption":[93,187],"quality.":[94],"popular":[96],"Show":[97],"Tell":[99],"encoder-decoder":[100],"model":[101,133],"was":[102,134],"selected":[103],"trained":[105],"subsets":[107],"MSCOCO-it":[110],"dataset":[111],"10k,":[113],"20k,":[114],"30k":[116],"with":[117,126],"without":[119],"human":[120],"validated":[121],"captions,":[122],"then":[124],"evaluated":[125],"BLEU-3/4,":[127],"METEOR,":[128],"ROUGE-L,":[129],"CIDEr.":[131],"also":[135],"tested":[136],"unseen":[138],"images.":[139],"evaluation":[141,192],"results":[142],"were":[143,147],"promising":[145],"below":[148],"50%.":[149],"We":[150],"intend":[151],"multimodal":[154],"augmentation":[155],"techniques":[156],"image-caption":[158],"To":[160],"enhance":[161],"interpretability,":[162],"explainable":[163],"AI":[164],"(XAI)":[165],"methods":[166],"such":[167],"as":[168],"attention":[169],"visualization":[170],"saliency":[172],"mapping":[173],"are":[174],"employed":[177],"reveal":[179],"which":[180],"image":[181],"regions":[182],"linguistic":[184],"features":[185],"influenced":[186],"generation.":[188],"Furthermore,":[189],"gender-aware":[191],"planned":[194],"researched":[197],"introduced,":[199],"assessing":[200],"whether":[201],"generated":[202],"captions":[203],"reproduce":[204],"gender":[205],"bias":[206],"present":[207],"training":[209],"data.":[210],"This":[211],"dual":[212],"focus":[213],"explainability":[215],"inclusivity":[217],"strengthens":[218],"trust":[219],"systems":[222],"supporting":[224],"fairer":[225],"more":[227],"transparent":[228],"applications.":[229]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-17T00:00:00"}