{"id":"https://openalex.org/W4387793681","doi":"https://doi.org/10.1145/3597638.3608402","title":"The Potential of a Visual Dialogue Agent In a Tandem Automated Audio Description System for Videos","display_name":"The Potential of a Visual Dialogue Agent In a Tandem Automated Audio Description System for Videos","publication_year":2023,"publication_date":"2023-10-19","ids":{"openalex":"https://openalex.org/W4387793681","doi":"https://doi.org/10.1145/3597638.3608402"},"language":"en","primary_location":{"id":"doi:10.1145/3597638.3608402","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597638.3608402","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597638.3608402","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 25th International ACM SIGACCESS Conference on Computers and Accessibility","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3597638.3608402","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031239936","display_name":"Abigale Stangl","orcid":"https://orcid.org/0000-0003-2761-1429"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abigale Stangl","raw_affiliation_strings":["Human Centered Design and Engineering, University of Washington, United States"],"raw_orcid":"https://orcid.org/0000-0003-2761-1429","affiliations":[{"raw_affiliation_string":"Human Centered Design and Engineering, University of Washington, United States","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037643790","display_name":"Shasta Ihorn","orcid":"https://orcid.org/0000-0002-4255-578X"},"institutions":[{"id":"https://openalex.org/I71838634","display_name":"San Francisco State University","ror":"https://ror.org/05ykr0121","country_code":"US","type":"education","lineage":["https://openalex.org/I71838634"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shasta Ihorn","raw_affiliation_strings":["Department of Psychology, San Francisco State University, United States"],"raw_orcid":"https://orcid.org/0000-0002-4255-578X","affiliations":[{"raw_affiliation_string":"Department of Psychology, San Francisco State University, United States","institution_ids":["https://openalex.org/I71838634"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012215333","display_name":"Yue-Ting Siu","orcid":"https://orcid.org/0000-0002-9478-1391"},"institutions":[{"id":"https://openalex.org/I4210135104","display_name":"Education Northwest","ror":"https://ror.org/036qcnh52","country_code":"US","type":"education","lineage":["https://openalex.org/I4210135104"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue-Ting Siu","raw_affiliation_strings":["Northwest Center for Assistive Technology Training (CATT-NW), United States"],"raw_orcid":"https://orcid.org/0000-0002-9478-1391","affiliations":[{"raw_affiliation_string":"Northwest Center for Assistive Technology Training (CATT-NW), United States","institution_ids":["https://openalex.org/I4210135104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004623327","display_name":"Aditya Bodi","orcid":"https://orcid.org/0009-0008-2653-0129"},"institutions":[{"id":"https://openalex.org/I71838634","display_name":"San Francisco State University","ror":"https://ror.org/05ykr0121","country_code":"US","type":"education","lineage":["https://openalex.org/I71838634"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Bodi","raw_affiliation_strings":["Department of Computer Science, San Francisco State University, United States"],"raw_orcid":"https://orcid.org/0009-0008-2653-0129","affiliations":[{"raw_affiliation_string":"Department of Computer Science, San Francisco State University, United States","institution_ids":["https://openalex.org/I71838634"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073713705","display_name":"Mar Castanon","orcid":"https://orcid.org/0009-0009-7996-901X"},"institutions":[{"id":"https://openalex.org/I71838634","display_name":"San Francisco State University","ror":"https://ror.org/05ykr0121","country_code":"US","type":"education","lineage":["https://openalex.org/I71838634"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mar Castanon","raw_affiliation_strings":["Department of Computer Science, San Francisco State University, United States"],"raw_orcid":"https://orcid.org/0009-0009-7996-901X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, San Francisco State University, United States","institution_ids":["https://openalex.org/I71838634"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001497856","display_name":"Lothar Narins","orcid":"https://orcid.org/0009-0004-4030-7186"},"institutions":[{"id":"https://openalex.org/I71838634","display_name":"San Francisco State University","ror":"https://ror.org/05ykr0121","country_code":"US","type":"education","lineage":["https://openalex.org/I71838634"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lothar D Narins","raw_affiliation_strings":["Department of Computer Science, San Francisco State University, United States"],"raw_orcid":"https://orcid.org/0009-0004-4030-7186","affiliations":[{"raw_affiliation_string":"Department of Computer Science, San Francisco State University, United States","institution_ids":["https://openalex.org/I71838634"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076251624","display_name":"Ilmi Yoon","orcid":"https://orcid.org/0000-0002-2418-5287"},"institutions":[{"id":"https://openalex.org/I71838634","display_name":"San Francisco State University","ror":"https://ror.org/05ykr0121","country_code":"US","type":"education","lineage":["https://openalex.org/I71838634"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilmi Yoon","raw_affiliation_strings":["Department of Computer Science, San Francisco State University, United States"],"raw_orcid":"https://orcid.org/0000-0002-2418-5287","affiliations":[{"raw_affiliation_string":"Department of Computer Science, San Francisco State University, United States","institution_ids":["https://openalex.org/I71838634"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":25.4105,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.99515361,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9975000023841858,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7890691161155701},{"id":"https://openalex.org/keywords/tandem","display_name":"Tandem","score":0.6028296947479248},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5601741671562195},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5006182193756104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38572168350219727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890691161155701},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.6028296947479248},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5601741671562195},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5006182193756104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38572168350219727},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3597638.3608402","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597638.3608402","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597638.3608402","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 25th International ACM SIGACCESS Conference on Computers and Accessibility","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3597638.3608402","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597638.3608402","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597638.3608402","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 25th International ACM SIGACCESS Conference on Computers and Accessibility","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.8100000023841858,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387793681.pdf","grobid_xml":"https://content.openalex.org/works/W4387793681.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W148637812","https://openalex.org/W289273921","https://openalex.org/W1530372808","https://openalex.org/W1605176579","https://openalex.org/W1831066781","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1979290264","https://openalex.org/W1990689692","https://openalex.org/W2037759571","https://openalex.org/W2056573693","https://openalex.org/W2056625975","https://openalex.org/W2078238240","https://openalex.org/W2084015864","https://openalex.org/W2108598243","https://openalex.org/W2124250523","https://openalex.org/W2139501017","https://openalex.org/W2277195237","https://openalex.org/W2295423240","https://openalex.org/W2484248039","https://openalex.org/W2508429489","https://openalex.org/W2549139847","https://openalex.org/W2745461083","https://openalex.org/W2747572960","https://openalex.org/W2767361967","https://openalex.org/W2789636240","https://openalex.org/W2801961308","https://openalex.org/W2830342271","https://openalex.org/W2884093133","https://openalex.org/W2896457183","https://openalex.org/W2942103387","https://openalex.org/W2952132648","https://openalex.org/W2963524571","https://openalex.org/W2966715458","https://openalex.org/W2969876226","https://openalex.org/W2978734845","https://openalex.org/W2979226788","https://openalex.org/W2991429212","https://openalex.org/W2998746484","https://openalex.org/W3006834244","https://openalex.org/W3010521570","https://openalex.org/W3032743533","https://openalex.org/W3094385957","https://openalex.org/W3097796514","https://openalex.org/W3097815361","https://openalex.org/W3160237369","https://openalex.org/W3160281558","https://openalex.org/W3162205072","https://openalex.org/W3162317218","https://openalex.org/W3163602536","https://openalex.org/W3164652469","https://openalex.org/W3207136799","https://openalex.org/W3216765867","https://openalex.org/W4213288197","https://openalex.org/W4281490909","https://openalex.org/W4288083516","https://openalex.org/W4288083805","https://openalex.org/W4293584584","https://openalex.org/W4300435436","https://openalex.org/W4307137007","https://openalex.org/W4307472389","https://openalex.org/W4308264370","https://openalex.org/W4362679702","https://openalex.org/W4366548995","https://openalex.org/W4387793209"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4323262585","https://openalex.org/W2023186083","https://openalex.org/W4211086969","https://openalex.org/W2890607860","https://openalex.org/W2025127327","https://openalex.org/W2798825245","https://openalex.org/W2519652201"],"abstract_inverted_index":{"The":[0],"relentless":[1],"pace":[2],"of":[3,89,142,151,164,167,179,182,191],"video":[4],"production":[5],"exacerbates":[6],"the":[7,80,87,154,165,177,192],"digital":[8,193],"accessibility":[9],"gap":[10],"that":[11,65,131,195],"individuals":[12,77],"who":[13],"are":[14,144],"blind":[15],"or":[16,51,97],"low":[17],"vision":[18],"(BLV)":[19],"face":[20],"on":[21],"a":[22,60,185],"daily":[23],"basis,":[24],"resulting":[25],"in":[26,105,112,120,146,162,184,199],"disproportionate":[27],"exclusion":[28],"from":[29],"community":[30],"opportunities":[31],"and":[32,68,116,170,202],"risk":[33],"management.":[34],"Whereas":[35],"previous":[36],"automated":[37,203],"audio":[38],"description":[39,49],"(AD)":[40],"systems":[41],"provide":[42],"single-tool":[43],"approaches":[44],"for":[45,159,205],"delivering":[46,52,90],"minimum":[47],"viable":[48],"(MVD)":[50],"on-demand":[53,69,93],"visual":[54],"question":[55],"answering":[56],"(VQA),":[57],"we":[58],"present":[59],"tandem":[61,81,155,186],"AI-based":[62],"AD":[63,133,168],"tool":[64,102],"combines":[66],"MVD":[67,91],"VQA.":[70],"A":[71,148],"user":[72,114],"study":[73],"with":[74,95,127,153],"26":[75],"BLV":[76],"explored":[78],"how":[79,176],"system":[82,156,160,187],"may":[83,135],"be":[84,136],"used":[85,104,119,145],"under":[86],"conditions":[88,108,123],"and/or":[92],"VQA":[94],"AI-only":[96,107,122,132],"human-in-the-loop":[98],"support.":[99],"When":[100,118],"each":[101],"was":[103],"isolation,":[106],"scored":[109],"significantly":[110],"lower":[111],"both":[113,140,180],"enjoyment":[115],"comprehension.":[117],"tandem,":[121],"matched":[124],"outcomes":[125],"delivered":[126],"human-in-the-loop,":[128],"which":[129],"suggests":[130],"tools":[134,143,183,204],"most":[137],"effective":[138],"when":[139],"types":[141,181],"tandem.":[147],"multimodal":[149],"analysis":[150],"interactions":[152],"revealed":[157],"areas":[158],"improvement":[161],"terms":[163],"timing":[166],"delivery":[169],"accurate":[171],"content":[172],"delivery.":[173],"We":[174],"discuss":[175],"use":[178],"can":[188],"mitigate":[189],"some":[190],"frictions":[194],"have":[196],"plagued":[197],"efforts":[198],"machine":[200],"learning":[201],"accessibility.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}