{"id":"https://openalex.org/W7137806475","doi":"https://doi.org/10.1609/aaai.v40i11.37826","title":"ImageSet2Text: Describing Sets of Images Through Text","display_name":"ImageSet2Text: Describing Sets of Images Through Text","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137806475","doi":"https://doi.org/10.1609/aaai.v40i11.37826"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i11.37826","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37826","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i11.37826","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015978848","display_name":"Piera Riccio","orcid":"https://orcid.org/0000-0001-8602-8271"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Piera Riccio","raw_affiliation_strings":["University of Amsterdam"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042419669","display_name":"Francesco Galati","orcid":"https://orcid.org/0000-0001-6317-6298"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francesco Galati","raw_affiliation_strings":["Independent Researcher"],"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008919064","display_name":"Kajetan Schweighofer","orcid":"https://orcid.org/0009-0001-0482-2699"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Kajetan Schweighofer","raw_affiliation_strings":["Johannes Kepler University Linz"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University Linz","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129741413","display_name":"Noa Garcia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noa Garcia","raw_affiliation_strings":["The University of Osaka"],"affiliations":[{"raw_affiliation_string":"The University of Osaka","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129669267","display_name":"Nuria M Oliver","orcid":null},"institutions":[{"id":"https://openalex.org/I4387155719","display_name":"ELLIS Alicante","ror":"https://ror.org/002ye0093","country_code":null,"type":"nonprofit","lineage":["https://openalex.org/I4387155719"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Nuria M Oliver","raw_affiliation_strings":["ELLIS Alicante"],"affiliations":[{"raw_affiliation_string":"ELLIS Alicante","institution_ids":["https://openalex.org/I4387155719"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015978848"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01716418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"8731","last_page":"8739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.98089998960495,"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":0.98089998960495,"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":0.003000000026077032,"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":0.00279999990016222,"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/natural-language","display_name":"Natural language","score":0.5950999855995178},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5712000131607056},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5468999743461609},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5109000205993652},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5081999897956848},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.44510000944137573},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4059000015258789},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.35670000314712524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613999843597412},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5950999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827999711036682},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5712000131607056},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.536300003528595},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.34279999136924744},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i11.37826","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37826","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i11.37826","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37826","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,71,74,88],"era":[2],"of":[3,9,32,73,79,119],"large-scale":[4],"visual":[5],"data,":[6],"understanding":[7],"collections":[8,114],"images":[10],"is":[11],"a":[12,23,62,116],"challenging":[13],"yet":[14],"important":[15],"task.":[16],"To":[17],"this":[18],"end,":[19],"we":[20],"introduce":[21],"ImageSet2Text,":[22],"novel":[24],"method":[25],"to":[26,109],"automatically":[27],"generate":[28],"natural":[29],"language":[30,38],"descriptions":[31,76],"image":[33,56,113],"sets.":[34],"Based":[35],"on":[36],"large":[37,112],"models,":[39],"visual-question":[40],"answering":[41],"chains,":[42],"an":[43],"external":[44],"lexical":[45],"graph,":[46],"and":[47,58,82,96,106],"CLIP-based":[48],"verification,":[49],"ImageSet2Text":[50,102],"iteratively":[51],"extracts":[52],"key":[53],"concepts":[54],"from":[55],"subsets":[57],"organizes":[59],"them":[60],"into":[61],"structured":[63],"concept":[64],"graph.":[65],"We":[66,85],"conduct":[67],"extensive":[68],"experiments":[69],"evaluating":[70],"quality":[72],"generated":[75],"in":[77],"terms":[78],"accuracy,":[80],"completeness,":[81],"user":[83],"satisfaction.":[84],"also":[86],"examine":[87],"method's":[89],"behavior":[90],"through":[91],"ablation":[92],"studies,":[93],"scalability":[94],"assessments,":[95],"failure":[97],"analyses.":[98],"Results":[99],"demonstrate":[100],"that":[101],"combines":[103],"data-driven":[104],"AI":[105],"symbolic":[107],"representations":[108],"reliably":[110],"summarize":[111],"for":[115],"wide":[117],"range":[118],"applications.":[120]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}