{"id":"https://openalex.org/W7203473397","doi":"https://doi.org/10.48550/arxiv.2608.12549","title":"StrAD: A Streaming Method and Benchmark for Audio Description Generation for Long-form Videos","display_name":"StrAD: A Streaming Method and Benchmark for Audio Description Generation for Long-form Videos","publication_year":2026,"publication_date":"2026-08-12","ids":{"openalex":"https://openalex.org/W7203473397","doi":"https://doi.org/10.48550/arxiv.2608.12549"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.12549","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12549","pdf_url":"https://arxiv.org/pdf/2608.12549","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/2608.12549","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098820962","display_name":"Julian Spravil","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]},{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Spravil, Julian","raw_affiliation_strings":["AIS , Computer Science Institute VI , University of Bonn , Germany","Fraunhofer IAIS , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIS , Computer Science Institute VI , University of Bonn , Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Fraunhofer IAIS , Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020225503","display_name":"Sebastian Houben","orcid":"https://orcid.org/0000-0002-2036-419X","observed_orcids":["https://orcid.org/0000-0002-2036-419X"]},"institutions":[{"id":"https://openalex.org/I155417937","display_name":"Hochschule Bonn-Rhein-Sieg","ror":"https://ror.org/04m2anh63","country_code":"DE","type":"education","lineage":["https://openalex.org/I155417937"]},{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Houben, Sebastian","raw_affiliation_strings":["A2S , University of Applied Sciences Bonn -Rhein-Sieg , Germany","Fraunhofer IAIS , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A2S , University of Applied Sciences Bonn -Rhein-Sieg , Germany","institution_ids":["https://openalex.org/I155417937"]},{"raw_affiliation_string":"Fraunhofer IAIS , Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027761977","display_name":"Sven Behnke","orcid":"https://orcid.org/0000-0002-5040-7525","observed_orcids":["https://orcid.org/0000-0002-5040-7525"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Behnke, Sven","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.6371999979019165,"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":0.6371999979019165,"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":0.34790000319480896,"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":0.00559999980032444,"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/long-form-video","display_name":"long-form video","score":0.8650000095367432},{"id":"https://openalex.org/keywords/video-accessibility","display_name":"video accessibility","score":0.4659999907016754},{"id":"https://openalex.org/keywords/blind-and-low-vision-people","display_name":"blind and low vision people","score":0.8209999799728394},{"id":"https://openalex.org/keywords/zero-shot-prompting","display_name":"zero-shot prompting","score":0.5809999704360962},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9750000238418579},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.4790000021457672},{"id":"https://openalex.org/keywords/temporal-localization","display_name":"temporal localization","score":0.8230000138282776},{"id":"https://openalex.org/keywords/narrative-coherence","display_name":"narrative coherence","score":0.4180000126361847},{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8481000065803528},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.7081000208854675},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6926000118255615},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6506999731063843},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6014000177383423},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5333999991416931},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37610000371932983},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3328000009059906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.29750001430511475},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2815999984741211},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2608.12549","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12549","pdf_url":"https://arxiv.org/pdf/2608.12549","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":"pmh:oai:pub.h-brs.de:9783","doi":null,"is_oa":false,"landing_page_url":"https://pub.h-brs.de/frontdoor/index/index/docId/9783","pdf_url":null,"source":{"id":"https://openalex.org/S4306400385","display_name":"Publication Server of Bonn-Rhein-Sieg University of Applied Sciences (Bonn-Rhein-Sieg University of Applied Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I135140700","host_organization_name":"University of Bonn","host_organization_lineage":["https://openalex.org/I135140700"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN 2331-8422","raw_type":"preprint"},{"id":"doi:10.48550/arxiv.2608.12549","doi":"https://doi.org/10.48550/arxiv.2608.12549","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.12549","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.12549","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12549","pdf_url":"https://arxiv.org/pdf/2608.12549","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":0.4483775794506073,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203473397.pdf","grobid_xml":"https://content.openalex.org/works/W7203473397.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"content":[1],"is":[2,33,229],"the":[3,51,147,157,160,187,230,237],"dominant":[4],"medium":[5],"of":[6,41,74,143,159,196],"communication,":[7],"yet":[8],"without":[9,132,239],"audio":[10,28],"descriptions":[11],"(ADs),":[12],"it":[13],"remains":[14,179],"inaccessible":[15],"to":[16,37],"blind":[17],"and":[18,60,106,135,140,178,212],"low-vision":[19],"people.":[20],"ADs":[21,32,128,235],"narrate":[22],"context-relevant":[23],"visual":[24],"events":[25],"during":[26],"natural":[27],"pauses.":[29],"Manually":[30],"creating":[31],"expensive,":[34],"limiting":[35],"coverage":[36],"a":[38,87,124,171,193,250],"small":[39],"fraction":[40],"available":[42],"content.":[43],"Most":[44],"existing":[45,130],"automatic":[46,80],"AD":[47,91,111,221,247],"generation":[48,92,112,222,248],"methods":[49],"frame":[50],"task":[52,149],"as":[53,65,100,113],"video":[54,76,107,116],"clip":[55],"captioning,":[56],"requiring":[57],"ground-truth":[58,133,240],"timestamps":[59],"additional":[61],"context":[62],"cues":[63],"such":[64,99],"character":[66],"databases.":[67],"Current":[68],"benchmarks":[69],"reinforce":[70],"this":[71],"framing,":[72],"consisting":[73],"short":[75,103],"segments":[77],"paired":[78],"with":[79,123,150,164],"or":[81],"task-mismatched":[82],"annotations.":[83],"We":[84,109],"introduce":[85],"StrAD,":[86],"benchmark":[88],"for":[89,200,252],"long-form":[90],"on":[93,162,174,181,236,245],"full-length":[94,121],"videos":[95,122],"spanning":[96],"diverse":[97],"genres":[98],"movies,":[101],"documentaries,":[102],"films,":[104],"performances,":[105],"games.":[108],"reformulate":[110],"streaming":[114,189,232],"dense":[115],"captioning.":[117],"Our":[118],"approach":[119],"processes":[120],"sliding":[125],"window,":[126],"inserting":[127],"into":[129],"transcripts":[131],"timestamps,":[134,152],"supports":[136],"both":[137,206],"fine-tuned":[138,154],"models":[139],"zero-shot":[141,202],"prompting":[142],"vision-language":[144],"models.":[145],"On":[146,186],"segment-level":[148],"given":[151],"our":[153,201],"StrAD-FT":[155,191],"sets":[156],"state":[158],"art":[161],"CMD-AD":[163],"36.3":[165],"CIDEr":[166],"(+10.0":[167],"over":[168],"Shot-by-shot),":[169],"establishes":[170],"reference":[172],"point":[173],"StrAD":[175,242],"(51.0":[176],"CIDEr),":[177],"competitive":[180],"MAD-Eval":[182],"at":[183],"24.9":[184],"CIDEr.":[185],"full-video":[188,220,246],"task,":[190],"reaches":[192],"SODA":[194],"score":[195],"2.4":[197],"against":[198],"1.1":[199],"baseline":[203],"StrAD-Zero,":[204],"though":[205],"exhibit":[207],"limitations":[208],"in":[209,223],"temporal":[210],"localization":[211],"narrative":[213],"coherence.":[214],"While":[215],"prior":[216],"work":[217],"has":[218],"tackled":[219],"an":[224],"offline,":[225],"multi-stage":[226],"fashion,":[227],"ours":[228],"first":[231],"approach,":[233],"generating":[234],"fly":[238],"timestamps.":[241],"makes":[243],"progress":[244],"measurable,":[249],"prerequisite":[251],"scaling":[253],"accessibility.":[254]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-08-15T00:00:00"}
