{"id":"https://openalex.org/W4385471890","doi":"https://doi.org/10.1145/3604951.3605516","title":"Gauging the Limitations of Natural Language Supervised Text-Image Metrics Learning by Iconclass Visual Concepts","display_name":"Gauging the Limitations of Natural Language Supervised Text-Image Metrics Learning by Iconclass Visual Concepts","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385471890","doi":"https://doi.org/10.1145/3604951.3605516"},"language":"en","primary_location":{"id":"doi:10.1145/3604951.3605516","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604951.3605516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050564431","display_name":"Kai Labusch","orcid":"https://orcid.org/0000-0002-7275-5483"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Berlin State Library","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Kai Labusch","raw_affiliation_strings":["Berlin State Library, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7275-5483","affiliations":[{"raw_affiliation_string":"Berlin State Library, Germany","institution_ids":["https://openalex.org/I2802918869"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060385793","display_name":"Clemens Neudecker","orcid":"https://orcid.org/0000-0001-5293-8322"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Berlin State Library","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Clemens Neudecker","raw_affiliation_strings":["Berlin State Library, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5293-8322","affiliations":[{"raw_affiliation_string":"Berlin State Library, Germany","institution_ids":["https://openalex.org/I2802918869"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050564431"],"corresponding_institution_ids":["https://openalex.org/I2802918869"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0790243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9948999881744385,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9921000003814697,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6853035688400269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6616244316101074},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6602705717086792},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6259651780128479},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.584287166595459},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.552449643611908},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5238266587257385},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.5168136358261108},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.48823001980781555},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.4628225266933441},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.45100322365760803},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45066770911216736},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16627666354179382},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12580370903015137},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.09219592809677124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6853035688400269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6616244316101074},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6602705717086792},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6259651780128479},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.584287166595459},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.552449643611908},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5238266587257385},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.5168136358261108},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.48823001980781555},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.4628225266933441},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.45100322365760803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45066770911216736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16627666354179382},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12580370903015137},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.09219592809677124},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3604951.3605516","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604951.3605516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W67023151","https://openalex.org/W417108357","https://openalex.org/W2250384498","https://openalex.org/W2485363636","https://openalex.org/W2970256816","https://openalex.org/W4292828275","https://openalex.org/W4312504063"],"related_works":["https://openalex.org/W4255837520","https://openalex.org/W2387011115","https://openalex.org/W4234808182","https://openalex.org/W2382043075","https://openalex.org/W2809151339","https://openalex.org/W2360673138","https://openalex.org/W2809370583","https://openalex.org/W2333722679","https://openalex.org/W4255628145","https://openalex.org/W2093320919"],"abstract_inverted_index":{"Identification":[0],"of":[1,11,30,36,50,56],"images":[2],"that":[3,63,69,86,90,101,108],"are":[4,65,96,102],"close":[5],"to":[6,46,105],"each":[7],"other":[8,78],"in":[9,121],"terms":[10],"their":[12],"iconographical":[13],"meaning":[14],"requires":[15],"an":[16],"applicable":[17],"distance":[18],"measure":[19,29],"for":[20,117],"text-image":[21],"or":[22],"image-image":[23],"pairs.":[24],"To":[25],"obtain":[26],"such":[27],"a":[28,34,47,114],"distance,":[31],"we":[32],"finetune":[33],"group":[35],"contrastive":[37],"loss":[38],"based":[39],"text-to-image":[40,122],"similarity":[41,123],"models":[42,76],"(MS-CLIP)":[43],"with":[44],"respect":[45],"large":[48],"number":[49],"Iconclass":[51,67],"visual":[52,79,88],"concepts":[53,68,80,89],"by":[54,74],"means":[55],"natural":[57],"language":[58],"supervised":[59],"learning.":[60,124],"We":[61,84],"show":[62],"there":[64],"certain":[66],"actually":[70],"can":[71,91,112],"be":[72,82,92],"learned":[73,93],"the":[75,87],"whereas":[77],"cannot":[81],"learned.":[83],"hypothesize":[85],"more":[94,103],"easily":[95],"intrinsically":[97],"different":[98],"from":[99],"those":[100],"difficult":[104],"learn":[106],"and":[107],"these":[109],"qualitative":[110],"differences":[111],"provide":[113],"valuable":[115],"orientation":[116],"future":[118],"research":[119],"directions":[120]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}