{"id":"https://openalex.org/W4405102071","doi":"https://doi.org/10.1007/978-981-96-0908-6_5","title":"AutoAD-Zero: A Training-Free Framework for\u00a0Zero-Shot Audio Description","display_name":"AutoAD-Zero: A Training-Free Framework for\u00a0Zero-Shot Audio Description","publication_year":2024,"publication_date":"2024-12-06","ids":{"openalex":"https://openalex.org/W4405102071","doi":"https://doi.org/10.1007/978-981-96-0908-6_5"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-96-0908-6_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-96-0908-6_5","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":"conference-paper","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/A5101281862","display_name":"Junyu Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Junyu Xie","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, Oxford, England"],"raw_orcid":"https://orcid.org/0009-0002-1123-493X","affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, Oxford, England","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075613881","display_name":"Tengda Han","orcid":"https://orcid.org/0000-0002-1874-9664"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tengda Han","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, Oxford, England"],"raw_orcid":"https://orcid.org/0000-0002-1874-9664","affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, Oxford, England","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030141879","display_name":"Max Bain","orcid":"https://orcid.org/0000-0002-2345-5441"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Max Bain","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, Oxford, England"],"raw_orcid":"https://orcid.org/0000-0002-2345-5441","affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, Oxford, England","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036002448","display_name":"Arsha Nagrani","orcid":"https://orcid.org/0000-0003-2190-9013"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arsha Nagrani","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, Oxford, England"],"raw_orcid":"https://orcid.org/0000-0003-2190-9013","affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, Oxford, England","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024292507","display_name":"G\u00fcl Varol","orcid":"https://orcid.org/0000-0002-8438-6152"},"institutions":[{"id":"https://openalex.org/I142631665","display_name":"\u00c9cole nationale des ponts et chauss\u00e9es","ror":"https://ror.org/02nwvxz07","country_code":"FR","type":"education","lineage":["https://openalex.org/I142631665","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]}],"countries":["FR","GB"],"is_corresponding":false,"raw_author_name":"G\u00fcl Varol","raw_affiliation_strings":["LIGM, \u00c9cole des Ponts ParisTech, Paris, France","Visual Geometry Group, University of Oxford, Oxford, England"],"raw_orcid":"https://orcid.org/0000-0002-8438-6152","affiliations":[{"raw_affiliation_string":"LIGM, \u00c9cole des Ponts ParisTech, Paris, France","institution_ids":["https://openalex.org/I142631665","https://openalex.org/I4210152518"]},{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, Oxford, England","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053549250","display_name":"Weidi Xie","orcid":"https://orcid.org/0009-0002-8609-6826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Weidi Xie","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","Visual Geometry Group, University of Oxford, Oxford, England"],"raw_orcid":"https://orcid.org/0009-0002-8609-6826","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, Oxford, England","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, Oxford, England"],"raw_orcid":"https://orcid.org/0000-0002-8945-8573","affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, Oxford, England","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101281862"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9937000274658203,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9900000095367432,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8223441243171692},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.8024401664733887},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5917978882789612},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4630783498287201},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3417041301727295},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.332541286945343},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06772682070732117},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.045834481716156006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223441243171692},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.8024401664733887},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5917978882789612},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4630783498287201},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3417041301727295},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.332541286945343},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06772682070732117},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.045834481716156006},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-96-0908-6_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-96-0908-6_5","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":[],"awards":[{"id":"https://openalex.org/G388094421","display_name":"Translating sign language with computer vision","funder_award_id":"ANR-21-CE23-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8161891803","display_name":null,"funder_award_id":"EP/T028572/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2078238240","https://openalex.org/W2120645068","https://openalex.org/W2884913105","https://openalex.org/W2914699769","https://openalex.org/W2963541336","https://openalex.org/W2963919999","https://openalex.org/W2969985801","https://openalex.org/W3034552680","https://openalex.org/W3095481265","https://openalex.org/W3107806026","https://openalex.org/W3174770825","https://openalex.org/W3198377975","https://openalex.org/W3216765867","https://openalex.org/W3217340782","https://openalex.org/W4205991051","https://openalex.org/W4221143046","https://openalex.org/W4312310776","https://openalex.org/W4312463400","https://openalex.org/W4312480274","https://openalex.org/W4312651322","https://openalex.org/W4385822293","https://openalex.org/W4386066097","https://openalex.org/W4386076487","https://openalex.org/W4390873481","https://openalex.org/W4390874338","https://openalex.org/W4392904756","https://openalex.org/W4402703105","https://openalex.org/W4402716166","https://openalex.org/W4402727693","https://openalex.org/W4402727919","https://openalex.org/W6600238479","https://openalex.org/W6600648412","https://openalex.org/W6600927616","https://openalex.org/W6601141708","https://openalex.org/W6601695987","https://openalex.org/W6602628784","https://openalex.org/W6607262404","https://openalex.org/W6629651325","https://openalex.org/W6629736473"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
