{"id":"https://openalex.org/W4415524361","doi":"https://doi.org/10.1109/mlsp62443.2025.11204281","title":"Speaking Images. A Novel Framework for the Automated Self-Description of Artworks","display_name":"Speaking Images. A Novel Framework for the Automated Self-Description of Artworks","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524361","doi":"https://doi.org/10.1109/mlsp62443.2025.11204281"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204281","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/A5000678813","display_name":"Valentine Bernasconi","orcid":"https://orcid.org/0000-0002-9467-8896"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Valentine Bernasconi","raw_affiliation_strings":["University of Bologna,Virtual and Augmented Reality Lab,Bologna,Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna,Virtual and Augmented Reality Lab,Bologna,Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012845043","display_name":"Gustavo Marfia","orcid":"https://orcid.org/0000-0003-3058-8004"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gustavo Marfia","raw_affiliation_strings":["University of Bologna,Virtual and Augmented Reality Lab,Bologna,Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna,Virtual and Augmented Reality Lab,Bologna,Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000678813"],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42923152,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9556000232696533,"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/relation","display_name":"Relation (database)","score":0.6107000112533569},{"id":"https://openalex.org/keywords/cultural-artifact","display_name":"Cultural artifact","score":0.6096000075340271},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5368000268936157},{"id":"https://openalex.org/keywords/malleability","display_name":"Malleability","score":0.5103999972343445},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45489999651908875},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4250999987125397},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42260000109672546}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6107000112533569},{"id":"https://openalex.org/C115233962","wikidata":"https://www.wikidata.org/wiki/Q1791627","display_name":"Cultural artifact","level":2,"score":0.6096000075340271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5616000294685364},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5368000268936157},{"id":"https://openalex.org/C100980136","wikidata":"https://www.wikidata.org/wiki/Q4668956","display_name":"Malleability","level":4,"score":0.5103999972343445},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45489999651908875},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4117000102996826},{"id":"https://openalex.org/C519222250","wikidata":"https://www.wikidata.org/wiki/Q860372","display_name":"Digital art","level":3,"score":0.39469999074935913},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3937000036239624},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.3912000060081482},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C11012388","wikidata":"https://www.wikidata.org/wiki/Q170658","display_name":"Creativity","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C60671577","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural heritage","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.295199990272522},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2779344036","wikidata":"https://www.wikidata.org/wiki/Q11320476","display_name":"Digital content","level":2,"score":0.26969999074935913}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204281","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2970641574","https://openalex.org/W3153469116","https://openalex.org/W3165405144","https://openalex.org/W3184496276","https://openalex.org/W4319713790","https://openalex.org/W4361204578","https://openalex.org/W4378373043","https://openalex.org/W4380988311","https://openalex.org/W4382940191","https://openalex.org/W4386148430","https://openalex.org/W4386242492","https://openalex.org/W4388022760","https://openalex.org/W4389437528","https://openalex.org/W4390736652","https://openalex.org/W4392904491","https://openalex.org/W4394810480","https://openalex.org/W4395960521","https://openalex.org/W4396833426","https://openalex.org/W4401307360","https://openalex.org/W4402536165","https://openalex.org/W4402671575","https://openalex.org/W4406794071","https://openalex.org/W4408351875","https://openalex.org/W4415271252"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"breakthroughs":[1],"in":[2,13,55,63,131],"generative":[3],"AI":[4],"have":[5,26],"opened":[6],"the":[7,14,35,40,52,66,72,75,84,116,134,150],"door":[8],"to":[9,33,38,57,65,102,109,120],"new":[10,81],"research":[11],"perspectives":[12],"domain":[15],"of":[16,24,42,51,74,86,136,141,149,152],"art":[17,153],"and":[18,29,37,60,96,108,139],"cultural":[19,88,128],"heritage.":[20],"A":[21],"large":[22],"number":[23],"artifacts":[25,89],"been":[27],"digitized":[28,106],"solutions":[30],"are":[31],"needed":[32],"ease":[34],"access":[36],"highlight":[39],"content":[41],"digital":[43,53,137],"collections.":[44],"Such":[45],"innovations":[46],"develop":[47],"into":[48],"creative":[49,157],"explorations":[50],"image":[54],"relation":[56],"its":[58,122],"malleability":[59],"contemporary":[61],"interpretation,":[62],"confrontation":[64],"original":[67],"historical":[68],"object.":[69],"Based":[70],"on":[71],"concept":[73],"autonomous":[76],"image,":[77],"we":[78],"propose":[79],"a":[80,105,112],"framework":[82],"towards":[83],"production":[85],"self-explaining":[87],"using":[90],"open-source":[91],"large-language,":[92],"face":[93],"detection,":[94],"text-to-speech":[95],"audio-to-animation":[97],"models.":[98],"The":[99,124],"goal":[100],"is":[101],"start":[103],"from":[104],"artwork":[107],"automatically":[110],"assemble":[111],"short":[113],"video":[114],"where":[115],"main":[117],"character":[118],"animates":[119],"explain":[121],"content.":[123],"whole":[125],"process":[126],"questions":[127],"biases":[129],"encapsulated":[130],"large-language":[132],"models,":[133],"potential":[135],"images":[138],"deepfakes":[140],"artworks":[142],"for":[143],"educational":[144],"purposes,":[145],"along":[146],"with":[147],"concerns":[148],"field":[151],"history":[154],"regarding":[155],"such":[156],"diversions.":[158]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}
