{"id":"https://openalex.org/W4415524476","doi":"https://doi.org/10.1109/mlsp62443.2025.11204345","title":"Multimodal Artwork Topic Modeling via Fine-Tuned Clip and Knowledge-Driven Prompts","display_name":"Multimodal Artwork Topic Modeling via Fine-Tuned Clip and Knowledge-Driven Prompts","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524476","doi":"https://doi.org/10.1109/mlsp62443.2025.11204345"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5025272747","display_name":"Raffaele Scaringi","orcid":"https://orcid.org/0000-0001-7512-7661"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Raffaele Scaringi","raw_affiliation_strings":["University of Bari Aldo Moro,Department of Computer Science,Italy"],"affiliations":[{"raw_affiliation_string":"University of Bari Aldo Moro,Department of Computer Science,Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008205801","display_name":"Giovanni Stea","orcid":"https://orcid.org/0000-0001-5310-6763"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Stea","raw_affiliation_strings":["University of Bari Aldo Moro,Department of Computer Science,Italy"],"affiliations":[{"raw_affiliation_string":"University of Bari Aldo Moro,Department of Computer Science,Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103191427","display_name":"Nicola Fanelli","orcid":"https://orcid.org/0009-0007-6602-7504"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Fanelli","raw_affiliation_strings":["University of Bari Aldo Moro,Department of Computer Science,Italy"],"affiliations":[{"raw_affiliation_string":"University of Bari Aldo Moro,Department of Computer Science,Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047012566","display_name":"Gennaro Vessio","orcid":"https://orcid.org/0000-0002-0883-2691"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gennaro Vessio","raw_affiliation_strings":["University of Bari Aldo Moro,Department of Computer Science,Italy"],"affiliations":[{"raw_affiliation_string":"University of Bari Aldo Moro,Department of Computer Science,Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050227787","display_name":"Giovanna Castellano","orcid":"https://orcid.org/0000-0002-6489-8628"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanna Castellano","raw_affiliation_strings":["University of Bari Aldo Moro,Department of Computer Science,Italy"],"affiliations":[{"raw_affiliation_string":"University of Bari Aldo Moro,Department of Computer Science,Italy","institution_ids":["https://openalex.org/I5561750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025272747"],"corresponding_institution_ids":["https://openalex.org/I5561750"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41473687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9466999769210815,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9466999769210815,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14254","display_name":"Digital Media and Visual Art","score":0.9401000142097473,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/cosine-similarity","display_name":"Cosine similarity","score":0.572700023651123},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5467000007629395},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5103999972343445},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5091000199317932},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4577000141143799},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.38440001010894775},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.3831000030040741},{"id":"https://openalex.org/keywords/cultural-heritage","display_name":"Cultural heritage","score":0.3614000082015991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7843999862670898},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.572700023651123},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5467000007629395},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5091000199317932},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46619999408721924},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4521999955177307},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42399999499320984},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C60671577","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural heritage","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.33059999346733093},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.32429999113082886},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C2775953033","wikidata":"https://www.wikidata.org/wiki/Q5276060","display_name":"Digital curation","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.257099986076355}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ricerca.uniba.it:11586/553220","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/11204345","pdf_url":null,"source":{"id":"https://openalex.org/S4377196296","display_name":"CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5561750","host_organization_name":"University of Bari Aldo Moro","host_organization_lineage":["https://openalex.org/I5561750"],"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/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2174706414","https://openalex.org/W2948676181","https://openalex.org/W3045464143","https://openalex.org/W3100651519","https://openalex.org/W3153469116","https://openalex.org/W3167565311","https://openalex.org/W3180353325","https://openalex.org/W3201906559","https://openalex.org/W4224325745","https://openalex.org/W4231510805","https://openalex.org/W4306377799","https://openalex.org/W4386075580","https://openalex.org/W4390873312","https://openalex.org/W4405740141","https://openalex.org/W4409262788","https://openalex.org/W4410772988"],"related_works":[],"abstract_inverted_index":{"We":[0,37],"propose":[1],"a":[2,33,41],"novel":[3],"multimodal":[4,65],"topic":[5,115],"modeling":[6],"framework":[7,108],"to":[8,26,70,90,99],"extract":[9],"and":[10,29,75,117,123,132,147],"explain":[11],"latent":[12,72],"themes":[13],"in":[14,112,141],"extensive":[15],"collections":[16],"of":[17,114],"digitized":[18],"artworks.":[19],"Our":[20,107],"approach":[21],"leverages":[22],"CLIP's":[23],"contrastive":[24],"pre-training":[25],"encode":[27],"images":[28],"textual":[30,87,101,124],"metadata":[31],"into":[32],"shared":[34],"semantic":[35],"space.":[36],"fine-tune":[38],"CLIP":[39],"on":[40,104],"domain-specific":[42],"dataset":[43],"built":[44],"from":[45],"<tex":[46],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[47],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathcal{A}rt":[48],"\\mathcal{G}raph$</tex>,":[49],"an":[50],"art-domain":[51],"knowledge":[52],"graph":[53],"containing":[54],"over":[55],"100k":[56],"artworks":[57],"enriched":[58],"with":[59,79,85],"curated":[60],"metadata.":[61],"Using":[62],"the":[63,93],"resulting":[64],"embeddings,":[66],"we":[67,96],"perform":[68],"clustering":[69],"uncover":[71],"visual":[73,122],"topics":[74],"associate":[76],"each":[77],"cluster":[78],"descriptive":[80],"terms":[81,113],"via":[82],"cosine":[83],"similarity":[84],"templated":[86],"prompts.":[88],"Finally,":[89],"further":[91],"interpret":[92],"discovered":[94],"topics,":[95],"employ":[97],"LLaVA":[98],"generate":[100],"summaries":[102],"based":[103],"representative":[105],"images.":[106],"demonstrates":[109],"promising":[110],"performance":[111],"coherence":[116],"diversity,":[118],"evaluated":[119],"through":[120],"both":[121],"metrics.":[125],"The":[126],"method":[127],"is":[128],"unsupervised,":[129],"easily":[130],"adaptable,":[131],"provides":[133],"interpretable":[134],"outputs,":[135],"making":[136],"it":[137],"suitable":[138],"for":[139],"applications":[140],"digital":[142],"humanities,":[143],"cultural":[144],"heritage":[145],"analysis,":[146],"content-based":[148],"art":[149],"retrieval.":[150]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}