{"id":"https://openalex.org/W7138836482","doi":"https://doi.org/10.1145/3772363.3798744","title":"ViDscribe: Multimodal AI for Customizing Audio Description and Question Answering in Online Videos","display_name":"ViDscribe: Multimodal AI for Customizing Audio Description and Question Answering in Online Videos","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7138836482","doi":"https://doi.org/10.1145/3772363.3798744","pmid":"https://pubmed.ncbi.nlm.nih.gov/42117046"},"language":"en","primary_location":{"id":"doi:10.1145/3772363.3798744","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772363.3798744","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3772363.3798744","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117294161","display_name":"Maryam S Cheema","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryam S Cheema","raw_affiliation_strings":["Arizona State University, Tempe, Arizona, USA"],"raw_orcid":"https://orcid.org/0009-0009-0556-8029","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, Arizona, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130086187","display_name":"Sina Elahimanesh","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sina Elahimanesh","raw_affiliation_strings":["Saarland University, Saarbr\u00fccken, Saarland, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7251-6661","affiliations":[{"raw_affiliation_string":"Saarland University, Saarbr\u00fccken, Saarland, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129783647","display_name":"Pooyan Fazli","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pooyan Fazli","raw_affiliation_strings":["Arizona State University, Tempe, Arizona, USA"],"raw_orcid":"https://orcid.org/0000-0002-2625-8216","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, Arizona, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043917822","display_name":"Hasti Seifi","orcid":"https://orcid.org/0000-0001-6437-0463"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hasti Seifi","raw_affiliation_strings":["Arizona State University, Tempe, Arizona, USA"],"raw_orcid":"https://orcid.org/0000-0001-6437-0463","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, Arizona, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28262975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2026","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.6273999810218811,"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":0.6273999810218811,"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":0.07769999653100967,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.04910000041127205,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/personalization","display_name":"Personalization","score":0.7954999804496765},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7911999821662903},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.49570000171661377},{"id":"https://openalex.org/keywords/online-video","display_name":"Online video","score":0.4641000032424927},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.45840001106262207},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38609999418258667},{"id":"https://openalex.org/keywords/user-engagement","display_name":"User engagement","score":0.3846000134944916},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.3781000077724457}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7954999804496765},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7911999821662903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7495999932289124},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4763999879360199},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.46970000863075256},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4302999973297119},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C2984870255","wikidata":"https://www.wikidata.org/wiki/Q5196451","display_name":"User engagement","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3785000145435333},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3643999993801117},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C2776566319","wikidata":"https://www.wikidata.org/wiki/Q3495514","display_name":"Interactive video","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3772363.3798744","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772363.3798744","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmid:42117046","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42117046","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Extended abstracts on Human factors in computing systems. CHI Conference","raw_type":null},{"id":"pmh:oai:arXiv.org:2603.14662","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.14662","pdf_url":"https://arxiv.org/pdf/2603.14662","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":"pmh:oai:pubmedcentral.nih.gov:13157971","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13157971/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13157971/pdf/nihms-2172699.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Ext Abstr Hum Factors Computing Syst","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3772363.3798744","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772363.3798744","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.691899836063385,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G6287431198","display_name":null,"funder_award_id":"R01EY034562","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337350","display_name":"National Eye Institute","ror":"https://ror.org/03wkg3b53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Advances":[0],"in":[1,52],"multimodal":[2],"large":[3],"language":[4],"models":[5],"enable":[6],"automatic":[7],"video":[8,128],"narration":[9],"and":[10,25,41,48,72,96,109,116],"question":[11],"answering":[12],"(VQA),":[13],"offering":[14],"scalable":[15],"alternatives":[16],"to":[17,37,119],"labor-intensive,":[18],"human-authored":[19],"audio":[20],"descriptions":[21],"(ADs)":[22],"for":[23,77,130],"blind":[24],"low":[26],"vision":[27],"(BLV)":[28],"viewers.":[29],"However,":[30],"prior":[31],"AI-driven":[32],"AD":[33],"systems":[34],"rarely":[35],"adapt":[36],"the":[38,123],"diverse":[39],"needs":[40],"preferences":[42],"of":[43,69,125],"BLV":[44,87,131],"individuals":[45],"across":[46],"videos":[47],"are":[49],"typically":[50],"evaluated":[51],"controlled,":[53],"single-session":[54],"settings.":[55],"We":[56],"present":[57],"ViDscribe,":[58],"a":[59,73,81],"web-based":[60],"platform":[61],"that":[62,110],"integrates":[63],"AI-generated":[64],"ADs":[65,112],"with":[66,85,94,106],"six":[67],"types":[68],"user":[70],"customizations":[71],"conversational":[74],"VQA":[75,97],"interface":[76],"YouTube":[78],"videos.":[79],"Through":[80],"longitudinal,":[82],"in-the-wild":[83],"study":[84],"eight":[86],"participants,":[88],"we":[89],"examine":[90],"how":[91],"users":[92],"engage":[93],"customization":[95],"features":[98,108],"over":[99],"time.":[100],"Our":[101],"results":[102],"show":[103],"sustained":[104],"engagement":[105],"both":[107],"customized":[111],"improve":[113],"effectiveness,":[114],"enjoyment,":[115],"immersion":[117],"compared":[118],"default":[120],"ADs,":[121],"highlighting":[122],"value":[124],"personalized,":[126],"interactive":[127],"access":[129],"users.":[132]},"counts_by_year":[],"updated_date":"2026-07-05T07:55:05.734416","created_date":"2026-03-20T00:00:00"}