{"id":"https://openalex.org/W4415524650","doi":"https://doi.org/10.1109/mlsp62443.2025.11204333","title":"The Cow of Rembrandt Analyzing Artistic Prompt Interpretation in Text-to-Image Models","display_name":"The Cow of Rembrandt Analyzing Artistic Prompt Interpretation in Text-to-Image Models","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524650","doi":"https://doi.org/10.1109/mlsp62443.2025.11204333"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204333","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":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2434/1189255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062638440","display_name":"Alfio Ferrara","orcid":"https://orcid.org/0000-0002-4991-4984"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alfio Ferrara","raw_affiliation_strings":["Universit&#x00E0; degli Studi di Milano,Department of Computer Science,Milan,Italy,20133"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E0; degli Studi di Milano,Department of Computer Science,Milan,Italy,20133","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040872559","display_name":"Sergio Picascia","orcid":"https://orcid.org/0000-0001-6863-0082"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sergio Picascia","raw_affiliation_strings":["Universit&#x00E0; degli Studi di Milano,Department of Computer Science,Milan,Italy,20133"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E0; degli Studi di Milano,Department of Computer Science,Milan,Italy,20133","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092596150","display_name":"Elisabetta Rocchetti","orcid":null},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisabetta Rocchetti","raw_affiliation_strings":["Universit&#x00E0; degli Studi di Milano,Department of Computer Science,Milan,Italy,20133"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E0; degli Studi di Milano,Department of Computer Science,Milan,Italy,20133","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062638440"],"corresponding_institution_ids":["https://openalex.org/I189158943"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32061328,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T14254","display_name":"Digital Media and Visual Art","score":0.9319999814033508,"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"}},{"id":"https://openalex.org/T12632","display_name":"Visual Culture and Art Theory","score":0.9283000230789185,"subfield":{"id":"https://openalex.org/subfields/1213","display_name":"Visual Arts and Performing Arts"},"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/style","display_name":"Style (visual arts)","score":0.6157000064849854},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5530999898910522},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.5437999963760376},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5333999991416931},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4912000000476837},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4318000078201294},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.4092000126838684},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.39010000228881836}],"concepts":[{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6157000064849854},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5333999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5188999772071838},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4912000000476837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.448199987411499},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4318000078201294},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.4092000126838684},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32120001316070557},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2888000011444092},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204333","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:air.unimi.it:2434/1189255","is_oa":true,"landing_page_url":"https://hdl.handle.net/2434/1189255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400516","display_name":"Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189158943","host_organization_name":"University of Milan","host_organization_lineage":["https://openalex.org/I189158943"],"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":null,"raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"pmh:oai:air.unimi.it:2434/1189255","is_oa":true,"landing_page_url":"https://hdl.handle.net/2434/1189255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400516","display_name":"Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189158943","host_organization_name":"University of Milan","host_organization_lineage":["https://openalex.org/I189158943"],"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":null,"raw_type":"info:eu-repo/semantics/bookPart"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W2099167491","https://openalex.org/W2901791883","https://openalex.org/W2986779468","https://openalex.org/W3199400376","https://openalex.org/W4289600032","https://openalex.org/W4312933868","https://openalex.org/W4366734343","https://openalex.org/W4385569875","https://openalex.org/W4388729738","https://openalex.org/W4402817070","https://openalex.org/W4408810164"],"related_works":[],"abstract_inverted_index":{"Text-to-image":[0],"diffusion":[1,50,69,109],"models":[2,27,51,70,110,161],"have":[3],"demonstrated":[4],"remarkable":[5],"capabilities":[6],"in":[7,36,86],"generating":[8,77],"artistic":[9,121,165],"content":[10,33,44,72,129],"by":[11,100],"learning":[12],"from":[13],"billions":[14],"of":[15,24,114,147,157],"images,":[16],"including":[17],"popular":[18],"artworks.":[19,78],"However,":[20],"the":[21,119,148,172],"fundamental":[22],"question":[23],"how":[25,66,158],"these":[26],"internally":[28,162],"represent":[29,163],"concepts,":[30],"such":[31],"as":[32],"and":[34,45,73,123,140,174],"style":[35,46,74,124,136],"paintings,":[37],"remains":[38],"unexplored.":[39],"Traditional":[40],"computer":[41],"vision":[42],"assumes":[43],"are":[47],"orthogonal,":[48],"but":[49],"receive":[52],"no":[53],"explicit":[54,168],"guidance":[55],"about":[56],"this":[57,62],"distinction":[58],"during":[59],"training.":[60],"In":[61,126],"work,":[63],"we":[64],"investigate":[65],"transformer-based":[67],"text-to-image":[68],"encode":[71],"concepts":[75,166],"when":[76],"We":[79,170],"leverage":[80],"cross-attention":[81],"heatmaps":[82],"to":[83,89,95,154],"attribute":[84],"pixels":[85],"generated":[87],"images":[88],"specific":[90,120],"prompt":[91,122],"tokens,":[92],"enabling":[93],"us":[94],"isolate":[96],"image":[97],"regions":[98,134],"influenced":[99],"content-describing":[101],"versus":[102],"style-describing":[103],"tokens.":[104],"Our":[105],"findings":[106],"reveal":[107],"that":[108],"demonstrate":[111],"varying":[112],"degrees":[113],"content-style":[115,149],"separation":[116],"depending":[117],"on":[118],"requested.":[125],"many":[127],"cases,":[128],"tokens":[130,137],"primarily":[131],"influence":[132],"object-related":[133],"while":[135],"affect":[138],"background":[139],"texture":[141],"areas,":[142],"suggesting":[143],"an":[144,178],"emergent":[145],"understanding":[146,156],"distinction.":[150],"These":[151],"insights":[152],"contribute":[153],"our":[155],"large-scale":[159],"generative":[160],"complex":[164],"without":[167],"supervision.":[169],"share":[171],"code":[173],"dataset,":[175],"together":[176],"with":[177],"exploratory":[179],"tool":[180],"for":[181],"visualizing":[182],"attention":[183],"maps":[184],"at":[185],"https://github.com/umilISLab/artistic-prompt-interpretation.":[186]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}
