{"id":"https://openalex.org/W4417232015","doi":"https://doi.org/10.1109/iccv51701.2025.01532","title":"Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation","display_name":"Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417232015","doi":"https://doi.org/10.1109/iccv51701.2025.01532"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.01020","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Junyu Xie","raw_affiliation_strings":["University of Oxford,Visual Geometry Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","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":["University of Oxford,Visual Geometry Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","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":["University of Oxford,Visual Geometry Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","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":["University of Oxford,Visual Geometry Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093382101","display_name":"Eshika Khandelwal","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Eshika Khandelwal","raw_affiliation_strings":["IIIT,CVIT,Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT,CVIT,Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"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/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":"G\u00fcl Varol","raw_affiliation_strings":["University of Oxford,Visual Geometry Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076097168","display_name":"Weidi Xie","orcid":"https://orcid.org/0000-0003-3804-2639"},"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":"Weidi Xie","raw_affiliation_strings":["University of Oxford,Visual Geometry Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","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":["University of Oxford,Visual Geometry Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16503","last_page":"16513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.3490999937057495,"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":0.3490999937057495,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.27219998836517334,"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/T11439","display_name":"Video Analysis and Summarization","score":0.05480000004172325,"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/context","display_name":"Context (archaeology)","score":0.43230000138282776},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.41659998893737793},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.3959999978542328},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.3677000105381012},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3555000126361847},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3366999924182892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8513000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4903999865055084},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3321000039577484},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.31049999594688416},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.267300009727478},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25119999051094055},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.01020","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.01020","pdf_url":"https://arxiv.org/pdf/2504.01020","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2504.01020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.01020","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.01020","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.01020","pdf_url":"https://arxiv.org/pdf/2504.01020","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Our":[0,62],"objective":[1],"is":[2,64],"the":[3,32,85,106],"automatic":[4,140],"generation":[5,144],"of":[6,35,84,108,129],"Audio":[7],"Descriptions":[8],"(ADs)":[9],"for":[10,154],"edited":[11],"video":[12,36],"material,":[13],"such":[14,51],"as":[15,31,52,142],"movies":[16],"and":[17,46,55,69,96,146],"TV":[18],"series.":[19],"To":[20,104],"achieve":[21,88],"this,":[22],"we":[23,111,132],"propose":[24,133],"a":[25,113,134],"two-stage":[26],"framework":[27],"that":[28,138],"leverages":[29],"\"shots\"":[30],"fundamental":[33],"units":[34],"understanding.":[37],"This":[38],"includes":[39],"extending":[40],"temporal":[41],"context":[42],"to":[43,58,124,149],"neighbouring":[44],"shots":[45],"incorporating":[47],"film":[48],"grammar":[49],"devices,":[50],"shot":[53],"scales":[54],"thread":[56],"structures,":[57],"guide":[59],"AD":[60,143],"generation.":[61],"method":[63],"compatible":[65],"with":[66],"both":[67],"open-source":[68],"proprietary":[70],"Visual-Language":[71],"Models":[72],"(VLMs),":[73],"integrating":[74],"expert":[75],"knowledge":[76],"from":[77],"add-on":[78],"modules":[79],"without":[80],"requiring":[81],"additional":[82],"training":[83],"VLMs.":[86],"We":[87],"state-of-the-art":[89],"performance":[90],"among":[91],"all":[92],"prior":[93],"training-free":[94],"approaches":[95],"even":[97],"surpass":[98],"fine-tuned":[99],"methods":[100],"on":[101],"several":[102],"benchmarks.":[103],"evaluate":[105],"quality":[107],"predicted":[109],"ADs,":[110],"introduce":[112],"new":[114],"evaluation":[115,136],"measure":[116],"--":[117,121],"an":[118],"action":[119],"score":[120],"specifically":[122],"targeted":[123],"assessing":[125],"this":[126],"important":[127],"aspect":[128],"AD.":[130],"Additionally,":[131],"novel":[135],"protocol":[137],"treats":[139],"frameworks":[141],"assistants":[145],"asks":[147],"them":[148],"generate":[150],"multiple":[151],"candidate":[152],"ADs":[153],"selection.":[155]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}