{"id":"https://openalex.org/W7202216552","doi":"https://doi.org/10.48550/arxiv.2608.09765","title":"REFRAMED: Towards Realistic Audio Description Generation for Movies","display_name":"REFRAMED: Towards Realistic Audio Description Generation for Movies","publication_year":2026,"publication_date":"2026-08-10","ids":{"openalex":"https://openalex.org/W7202216552","doi":"https://doi.org/10.48550/arxiv.2608.09765"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.09765","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09765","pdf_url":"https://arxiv.org/pdf/2608.09765","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.09765","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122942276","display_name":"Igor Sterner","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sterner, Igor","raw_affiliation_strings":["School of Informatics University of Edinburgh United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041024491","display_name":"Mirella Lapata","orcid":"https://orcid.org/0000-0002-2107-1516","observed_orcids":["https://orcid.org/0000-0002-2107-1516"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lapata, Mirella","raw_affiliation_strings":["School of Informatics University of Edinburgh United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083233594","display_name":"Alex Lascarides Y","orcid":"https://orcid.org/0000-0003-1704-1864","observed_orcids":["https://orcid.org/0000-0003-1704-1864"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lascarides, Alex","raw_affiliation_strings":["School of Informatics University of Edinburgh United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054936589","display_name":"Frank Keller","orcid":"https://orcid.org/0000-0002-8242-4362","observed_orcids":["https://orcid.org/0000-0002-8242-4362"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Keller, Frank","raw_affiliation_strings":["School of Informatics University of Edinburgh United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6762999892234802,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6762999892234802,"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":0.31470000743865967,"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":0.0044999998062849045,"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/accessibility-for-visually-impaired-users","display_name":"accessibility for visually impaired users","score":0.7350000143051147},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.7039999961853027},{"id":"https://openalex.org/keywords/video-understanding","display_name":"video understanding","score":0.628000020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230000138282776},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7196999788284302},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.698199987411499},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.46639999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4456999897956848},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.09765","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09765","pdf_url":"https://arxiv.org/pdf/2608.09765","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.09765","doi":"https://doi.org/10.48550/arxiv.2608.09765","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.09765","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.09765","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09765","pdf_url":"https://arxiv.org/pdf/2608.09765","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.4104533791542053,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G5730701950","display_name":null,"funder_award_id":"EP/W002876/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8005586940","display_name":"Exploiting narrative structure in the generation of audio description of video","funder_award_id":"2923920","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202216552.pdf","grobid_xml":"https://content.openalex.org/works/W7202216552.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4409248290","https://openalex.org/W4413145905","https://openalex.org/W7214305279","https://openalex.org/W7207754973","https://openalex.org/W7203473397","https://openalex.org/W2078238240","https://openalex.org/W4402727693","https://openalex.org/W2914699769","https://openalex.org/W7133221555","https://openalex.org/W4411112979"],"abstract_inverted_index":{"Audio":[0],"Description":[1],"(AD)":[2],"is":[3,24,42],"a":[4,25,98,124,154,205],"verbal":[5],"narration":[6],"of":[7,66,101,127,196],"key":[8],"visual":[9],"content":[10,63],"in":[11,35,56,104],"videos,":[12],"enabling":[13],"access":[14],"for":[15,92,208],"visually":[16],"impaired":[17],"audiences.":[18],"Unlike":[19],"standard":[20],"video":[21,211],"captioning,":[22],"AD":[23,54,102,139,165,181],"structured":[26],"editorial":[27],"task:":[28],"descriptions":[29,67],"must":[30,38,107],"be":[31],"inserted":[32],"into":[33],"gaps":[34,174],"dialogue":[36,173],"and":[37,64,82,85,113,143,148,175,183,202],"convey":[39],"only":[40],"what":[41,110],"needed":[43],"to":[44,73,111,115],"understand":[45],"the":[46,62,71,87],"narrative":[47,94],"being":[48],"told.":[49],"However,":[50],"existing":[51],"approaches":[52],"formulate":[53],"generation":[55,103],"an":[57],"artificial":[58],"setting":[59],"where":[60],"both":[61],"timing":[65],"are":[68],"pre-specified,":[69],"reducing":[70],"task":[72],"clip-level":[74],"captioning.":[75],"They":[76],"further":[77],"rely":[78],"on":[79,210],"noisy":[80],"transcription":[81],"alignment":[83],"pipelines,":[84],"lack":[86],"rich":[88],"parallel":[89],"data":[90],"required":[91],"modeling":[93],"context.":[95],"We":[96,151],"introduce":[97],"new":[99,206],"formulation":[100],"which":[105],"models":[106],"jointly":[108],"decide":[109],"describe":[112],"when":[114],"do":[116],"it.":[117],"To":[118],"support":[119],"this,":[120],"we":[121],"present":[122],"REFRAMED,":[123],"high-quality":[125],"dataset":[126,201],"2,023":[128],"videos":[129],"that":[130,159,171,187],"span":[131],"3,302":[132],"scenes":[133],"from":[134],"206":[135],"movies,":[136],"with":[137,163,168,179],"professional":[138,146],"transcripts":[140],"(both":[141],"American":[142],"British":[144],"versions),":[145],"subtitles":[147],"aligned":[149],"screenplays.":[150],"also":[152],"provide":[153],"manually":[155],"curated":[156],"challenge":[157],"set":[158],"pairs":[160],"full":[161],"movies":[162],"multiple":[164],"references,":[166],"together":[167],"evaluation":[169],"protocols":[170],"leverage":[172],"multi-reference":[176],"comparisons.":[177],"Experiments":[178],"state-of-the-art":[180],"systems":[182],"multimodal":[184],"LLMs":[185],"show":[186],"they":[188],"outperform":[189],"trivial":[190],"baselines":[191],"but":[192],"fall":[193],"far":[194],"short":[195],"expert":[197],"human":[198],"performance.":[199],"Our":[200],"benchmark":[203],"establish":[204],"foundation":[207],"research":[209],"understanding.":[212]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-12T00:00:00"}