{"id":"https://openalex.org/W3185239128","doi":"https://doi.org/10.3390/jimaging7080123","title":"Towards Generating and Evaluating Iconographic Image Captions of Artworks","display_name":"Towards Generating and Evaluating Iconographic Image Captions of Artworks","publication_year":2021,"publication_date":"2021-07-23","ids":{"openalex":"https://openalex.org/W3185239128","doi":"https://doi.org/10.3390/jimaging7080123","mag":"3185239128","pmid":"https://pubmed.ncbi.nlm.nih.gov/34460759"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging7080123","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging7080123","pdf_url":"https://www.mdpi.com/2313-433X/7/8/123/pdf?version=1627348458","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/7/8/123/pdf?version=1627348458","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008204423","display_name":"Eva Cetini\u0107","orcid":"https://orcid.org/0000-0002-5330-1259"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]},{"id":"https://openalex.org/I4210123216","display_name":"Ru\u0111er Bo\u0161kovi\u0107 Institute","ror":"https://ror.org/02mw21745","country_code":"HR","type":"facility","lineage":["https://openalex.org/I4210123216"]}],"countries":["GB","HR"],"is_corresponding":true,"raw_author_name":"Eva Cetinic","raw_affiliation_strings":["Department of Computer Science, Durham University, Durham DH1 3LE, UK","Rudjer Boskovic Insitute, Bijenicka Cesta 54, 10000 Zagreb, Croatia"],"raw_orcid":"https://orcid.org/0000-0002-5330-1259","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Durham University, Durham DH1 3LE, UK","institution_ids":["https://openalex.org/I190082696"]},{"raw_affiliation_string":"Rudjer Boskovic Insitute, Bijenicka Cesta 54, 10000 Zagreb, Croatia","institution_ids":["https://openalex.org/I4210123216"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5008204423"],"corresponding_institution_ids":["https://openalex.org/I190082696","https://openalex.org/I4210123216"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":1.9397,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.88151842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"7","issue":"8","first_page":"123","last_page":"123"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9905999898910522,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9753000140190125,"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":0.952770471572876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8391506671905518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6175943613052368},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5595372915267944},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5298240780830383},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48001331090927124},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4749608039855957},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4444126486778259},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42232733964920044},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34516650438308716},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.13952124118804932}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.952770471572876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391506671905518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6175943613052368},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5595372915267944},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5298240780830383},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48001331090927124},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4749608039855957},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4444126486778259},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42232733964920044},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34516650438308716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13952124118804932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":6,"locations":[{"id":"doi:10.3390/jimaging7080123","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging7080123","pdf_url":"https://www.mdpi.com/2313-433X/7/8/123/pdf?version=1627348458","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:34460759","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34460759","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":null},{"id":"pmh:oai:doaj.org/article:41992b590a3942e3aff51442aa0c701d","is_oa":true,"landing_page_url":"https://doaj.org/article/41992b590a3942e3aff51442aa0c701d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 7, Iss 8, p 123 (2021)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:7438975","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC8404909","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"","raw_type":"Text"},{"id":"pmh:oai:fulir.irb.hr:7156","is_oa":true,"landing_page_url":"http://fulir.irb.hr/7156/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400095","display_name":"Institutional Repository  of the Ru\u0111er Bo\u0161kovi\u0107 Institute (Ru\u0111er Bo\u0161kovi\u0107 Institute)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123216","host_organization_name":"Ru\u0111er Bo\u0161kovi\u0107 Institute","host_organization_lineage":["https://openalex.org/I4210123216"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8404909","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8404909","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/jimaging7080123","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging7080123","pdf_url":"https://www.mdpi.com/2313-433X/7/8/123/pdf?version=1627348458","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3185239128.pdf","grobid_xml":"https://content.openalex.org/works/W3185239128.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W300217873","https://openalex.org/W417108357","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2520188521","https://openalex.org/W2613718673","https://openalex.org/W2727403735","https://openalex.org/W2766086266","https://openalex.org/W2785151601","https://openalex.org/W2884238566","https://openalex.org/W2886641317","https://openalex.org/W2897923591","https://openalex.org/W2903416914","https://openalex.org/W2921176416","https://openalex.org/W2927066960","https://openalex.org/W2948676181","https://openalex.org/W2953106684","https://openalex.org/W2954598292","https://openalex.org/W2954882165","https://openalex.org/W2963370915","https://openalex.org/W2964086488","https://openalex.org/W2965570799","https://openalex.org/W2966715458","https://openalex.org/W2969862959","https://openalex.org/W2970231061","https://openalex.org/W2970608575","https://openalex.org/W2975501350","https://openalex.org/W2980726482","https://openalex.org/W2982212456","https://openalex.org/W2984215311","https://openalex.org/W2989596775","https://openalex.org/W2997591391","https://openalex.org/W3001951800","https://openalex.org/W3003361016","https://openalex.org/W3012716110","https://openalex.org/W3017681319","https://openalex.org/W3035835911","https://openalex.org/W3049038876","https://openalex.org/W3090449556","https://openalex.org/W3098967712","https://openalex.org/W3103959651","https://openalex.org/W3126406835","https://openalex.org/W3127724266","https://openalex.org/W3128777808","https://openalex.org/W3130295820","https://openalex.org/W3131146974","https://openalex.org/W3133717587","https://openalex.org/W3135367836","https://openalex.org/W3143866280","https://openalex.org/W3153469116","https://openalex.org/W3209274285","https://openalex.org/W6639102338","https://openalex.org/W6682631176","https://openalex.org/W6727229076","https://openalex.org/W6749987803","https://openalex.org/W6773533942"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W4388002133","https://openalex.org/W3009270862"],"abstract_inverted_index":{"To":[0],"automatically":[1],"generate":[2,256],"accurate":[3,89],"and":[4,32,104,175,192,204,216,243],"meaningful":[5,257],"textual":[6],"descriptions":[7,90,98],"of":[8,18,37,48,61,65,74,78,91,99,109,122,127,134,142,181,212,246],"images":[9,93,144],"is":[10,42,71,84,94,112,130,159,197,225],"an":[11],"ongoing":[12],"research":[13],"challenge.":[14],"Recently,":[15],"a":[16,139,156,163,205,261],"lot":[17],"progress":[19],"has":[20],"been":[21,56],"made":[22,57],"by":[23,137,161,227],"adopting":[24],"multimodal":[25],"deep":[26],"learning":[27],"approaches":[28],"for":[29,69],"integrating":[30],"vision":[31],"language.":[33],"However,":[34],"the":[35,59,66,72,85,149,170,179,184,213,217,229,237,244,253,265],"task":[36],"developing":[38],"image":[39,174,201,281],"captioning":[40,157,202],"models":[41,276],"most":[43],"commonly":[44,240],"addressed":[45],"using":[46,189,199],"datasets":[47,77],"natural":[49,280],"images,":[50,183],"while":[51],"not":[52],"many":[53],"contributions":[54],"have":[55],"in":[58,178,270],"domain":[60,180],"artwork":[62,92,123,143,182],"images.":[63,124],"One":[64],"main":[67],"reasons":[68],"that":[70,87,252,259],"lack":[73],"large-scale":[75,140],"art":[76,233,266],"adequate":[79],"image-text":[80],"pairs.":[81],"Another":[82],"reason":[83],"fact":[86],"generating":[88],"particularly":[95,269],"challenging":[96],"because":[97],"artworks":[100],"are":[101,187],"more":[102],"complex":[103,171],"can":[105,255],"include":[106],"multiple":[107],"levels":[108],"interpretation.":[110],"It":[111],"therefore":[113],"also":[114],"especially":[115],"difficult":[116],"to":[117,131,169,220,222,231,235,264,272],"effectively":[118],"evaluate":[119],"generated":[120,185,214,241],"captions":[121,186,215,242,258,273],"The":[125,195,210,248],"aim":[126],"this":[128,154],"work":[129],"address":[132],"some":[133],"those":[135],"challenges":[136],"utilizing":[138],"dataset":[141,234],"annotated":[145],"with":[146],"concepts":[147],"from":[148,275],"Iconclass":[150],"classification":[151],"system.":[152],"Using":[153],"dataset,":[155],"model":[158,230,254],"developed":[160],"fine-tuning":[162],"transformer-based":[164],"vision-language":[165],"pretrained":[166],"model.":[167],"Due":[168],"relations":[172],"between":[173,239],"text":[176],"pairs":[177],"evaluated":[188],"several":[190],"quantitative":[191],"qualitative":[193],"approaches.":[194],"performance":[196],"assessed":[198],"standard":[200],"metrics":[203],"recently":[206],"introduced":[207],"reference-free":[208],"metric.":[209],"quality":[211],"model's":[218],"capacity":[219],"generalize":[221],"new":[223],"data":[224],"explored":[226],"employing":[228],"another":[232],"compare":[236],"relation":[238],"genre":[245],"artworks.":[247],"overall":[249],"results":[250],"suggest":[251],"indicate":[260],"stronger":[262],"relevance":[263],"historical":[267],"context,":[268],"comparison":[271],"obtained":[274],"trained":[277],"only":[278],"on":[279],"datasets.":[282]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
