{"id":"https://openalex.org/W4293112598","doi":"https://doi.org/10.1145/3526113.3545703","title":"CrossA11y: Identifying Video Accessibility Issues via Cross-modal Grounding","display_name":"CrossA11y: Identifying Video Accessibility Issues via Cross-modal Grounding","publication_year":2022,"publication_date":"2022-10-28","ids":{"openalex":"https://openalex.org/W4293112598","doi":"https://doi.org/10.1145/3526113.3545703"},"language":"en","primary_location":{"id":"doi:10.1145/3526113.3545703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526113.3545703","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526113.3545703","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 35th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3526113.3545703","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100435048","display_name":"Xingyu Liu","orcid":"https://orcid.org/0000-0002-6988-5471"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xingyu \"Bruce\" Liu","raw_affiliation_strings":["HCI Research, UCLA, United States"],"affiliations":[{"raw_affiliation_string":"HCI Research, UCLA, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100746359","display_name":"Ruolin Wang","orcid":"https://orcid.org/0000-0001-9327-3793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruolin Wang","raw_affiliation_strings":["HCI Research, UCLA, United States"],"affiliations":[{"raw_affiliation_string":"HCI Research, UCLA, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038972102","display_name":"Dingzeyu Li","orcid":"https://orcid.org/0000-0002-4222-8105"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dingzeyu Li","raw_affiliation_strings":["Adobe Research, United States"],"affiliations":[{"raw_affiliation_string":"Adobe Research, United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023204103","display_name":"Xiang Chen","orcid":"https://orcid.org/0000-0002-8527-1744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Anthony Chen","raw_affiliation_strings":["HCI Research, UCLA, United States"],"affiliations":[{"raw_affiliation_string":"HCI Research, UCLA, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014816733","display_name":"Amy Pavel","orcid":"https://orcid.org/0000-0002-3908-4366"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amy Pavel","raw_affiliation_strings":["Department of Computer Science, University of Texas, Austin, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas, Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100435048"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.7903,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.99306392,"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":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9854999780654907,"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":0.9598000049591064,"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":0.822341799736023},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.716550350189209},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6871404051780701},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6120225787162781},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5952301621437073},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5294575095176697},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5151854753494263},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4347851574420929},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4222673177719116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33955448865890503},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.066674143075943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822341799736023},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.716550350189209},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6871404051780701},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6120225787162781},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5952301621437073},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5294575095176697},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5151854753494263},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4347851574420929},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4222673177719116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33955448865890503},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.066674143075943},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3526113.3545703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526113.3545703","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526113.3545703","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 35th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2208.11144","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.11144","pdf_url":"https://arxiv.org/pdf/2208.11144","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"}],"best_oa_location":{"id":"doi:10.1145/3526113.3545703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526113.3545703","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526113.3545703","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 35th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293112598.pdf","grobid_xml":"https://content.openalex.org/works/W4293112598.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W289273921","https://openalex.org/W616265588","https://openalex.org/W1968326021","https://openalex.org/W1978098427","https://openalex.org/W1979702275","https://openalex.org/W2056573693","https://openalex.org/W2058432683","https://openalex.org/W2064420833","https://openalex.org/W2124250523","https://openalex.org/W2143845053","https://openalex.org/W2191301944","https://openalex.org/W2336188181","https://openalex.org/W2587602959","https://openalex.org/W2888994383","https://openalex.org/W2994818707","https://openalex.org/W3031838646","https://openalex.org/W3035635319","https://openalex.org/W3037309139","https://openalex.org/W3038896047","https://openalex.org/W3094385957","https://openalex.org/W3135367836","https://openalex.org/W3153005511","https://openalex.org/W3160237369","https://openalex.org/W3160281558","https://openalex.org/W3161575571","https://openalex.org/W3163602536","https://openalex.org/W3166396011","https://openalex.org/W3174873881","https://openalex.org/W3175300676","https://openalex.org/W3193568238","https://openalex.org/W3205898663","https://openalex.org/W3207801264","https://openalex.org/W4287645044","https://openalex.org/W4287704005","https://openalex.org/W4287757777","https://openalex.org/W4411426060","https://openalex.org/W6959340700"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Authors":[0],"make":[1],"their":[2],"videos":[3],"visually":[4],"accessible":[5,13],"by":[6,14,105],"adding":[7,15],"audio":[8,100,119],"descriptions":[9],"(AD),":[10],"and":[11,22,26,32,54,64,80,83,99,115,118,135,139],"auditorily":[12],"closed":[16],"captions":[17],"(CC).":[18],"However,":[19],"creating":[20],"AD":[21],"CC":[23],"is":[24],"challenging":[25],"tedious,":[27],"especially":[28],"for":[29,57,61,107],"non-professional":[30],"describers":[31],"captioners,":[33],"due":[34],"to":[35,49,129,157],"the":[36,51,137,145],"difficulty":[37],"of":[38,97,147],"identifying":[39],"accessibility":[40,85,96,120],"problems":[41],"in":[42,87,102,122],"videos.":[43,88],"A":[44],"video":[45,52,104,141],"author":[46],"will":[47],"have":[48],"watch":[50],"through":[53,149],"manually":[55],"check":[56],"inaccessible":[58],"information":[59],"frame-by-frame,":[60],"both":[62],"visual":[63,82,98,117],"auditory":[65,84],"modalities.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"present":[71],"CrossA11y,":[72],"a":[73,103,123,150],"system":[74],"that":[75],"helps":[76],"authors":[77],"efficiently":[78],"detect":[79],"address":[81],"issues":[86,121],"Using":[89],"cross-modal":[90],"grounding":[91],"analysis,":[92],"CrossA11y":[93,110,148],"automatically":[94],"measures":[95],"segments":[101,114],"checking":[106],"modality":[108],"asymmetries.":[109],"then":[111],"displays":[112],"these":[113],"surfaces":[116],"unified":[124],"interface,":[125],"making":[126],"it":[127],"intuitive":[128],"locate,":[130],"review,":[131],"script":[132],"AD/CC":[133],"in-place,":[134],"preview":[136],"described":[138],"captioned":[140],"immediately.":[142],"We":[143],"demonstrate":[144],"effectiveness":[146],"lab":[151],"study":[152],"with":[153],"11":[154],"participants,":[155],"comparing":[156],"existing":[158],"baseline.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}