{"id":"https://openalex.org/W7124416993","doi":"https://doi.org/10.1007/978-3-032-14495-9_7","title":"Seeing Through Words: A Zero-Shot Multimodal Audio Description System with Foundation Models","display_name":"Seeing Through Words: A Zero-Shot Multimodal Audio Description System with Foundation Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124416993","doi":"https://doi.org/10.1007/978-3-032-14495-9_7"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-14495-9_7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-14495-9_7","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5106442601","display_name":"Bogdan Mocanu","orcid":"https://orcid.org/0000-0001-8010-9943"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["FR","RO"],"is_corresponding":false,"raw_author_name":"Bogdan Mocanu","raw_affiliation_strings":["Department of Telecommunications, Faculty of ETTI, National University of Science and Technology \u201cPolitehnica\u201d Bucharest, Bucharest, Romania","SAMOVAR, T\u00e9l\u00e9com SudParis, Institut Polytechnique de Paris, 91120, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0001-8010-9943","affiliations":[{"raw_affiliation_string":"Department of Telecommunications, Faculty of ETTI, National University of Science and Technology \u201cPolitehnica\u201d Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"SAMOVAR, T\u00e9l\u00e9com SudParis, Institut Polytechnique de Paris, 91120, Palaiseau, France","institution_ids":["https://openalex.org/I4210145102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025204322","display_name":"Ruxandra \u021aapu","orcid":"https://orcid.org/0000-0003-3170-4150"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["FR","RO"],"is_corresponding":true,"raw_author_name":"Ruxandra Tapu","raw_affiliation_strings":["Department of Telecommunications, Faculty of ETTI, National University of Science and Technology \u201cPolitehnica\u201d Bucharest, Bucharest, Romania","SAMOVAR, T\u00e9l\u00e9com SudParis, Institut Polytechnique de Paris, 91120, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0003-3170-4150","affiliations":[{"raw_affiliation_string":"Department of Telecommunications, Faculty of ETTI, National University of Science and Technology \u201cPolitehnica\u201d Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"SAMOVAR, T\u00e9l\u00e9com SudParis, Institut Polytechnique de Paris, 91120, Palaiseau, France","institution_ids":["https://openalex.org/I4210145102"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025204322"],"corresponding_institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I61641377"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11398747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"85","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.8463000059127808,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.8463000059127808,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0608999989926815,"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/T11439","display_name":"Video Analysis and Summarization","score":0.01269999984651804,"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/narrative","display_name":"Narrative","score":0.5382000207901001},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4869999885559082},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4733000099658966},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4277999997138977},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3993000090122223},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3783999979496002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9097999930381775},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48559999465942383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47690001130104065},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-14495-9_7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-14495-9_7","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.596442699432373,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W27089656","https://openalex.org/W2522595994","https://openalex.org/W2601243251","https://openalex.org/W2789824578","https://openalex.org/W2963916161","https://openalex.org/W2969985801","https://openalex.org/W2970641574","https://openalex.org/W2987802279","https://openalex.org/W3034552680","https://openalex.org/W3216765867","https://openalex.org/W4214663214","https://openalex.org/W4288083805","https://openalex.org/W4385822293","https://openalex.org/W4399270736","https://openalex.org/W4402702917","https://openalex.org/W4402703105","https://openalex.org/W4402727693","https://openalex.org/W4405102071","https://openalex.org/W4411417376","https://openalex.org/W4413145905"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-01-19T04:01:09.351973","created_date":"2026-01-17T00:00:00"}
