{"id":"https://openalex.org/W2897588549","doi":"https://doi.org/10.1145/3234695.3241023","title":"Leveraging Pauses to Improve Video Captions","display_name":"Leveraging Pauses to Improve Video Captions","publication_year":2018,"publication_date":"2018-10-08","ids":{"openalex":"https://openalex.org/W2897588549","doi":"https://doi.org/10.1145/3234695.3241023","mag":"2897588549"},"language":"en","primary_location":{"id":"doi:10.1145/3234695.3241023","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3234695.3241023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International ACM SIGACCESS Conference on Computers and Accessibility","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091460837","display_name":"Michael Gower","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Michael Gower","raw_affiliation_strings":["IBM Research, Victoria, Canada"],"affiliations":[{"raw_affiliation_string":"IBM Research, Victoria, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064374781","display_name":"Brent Shiver","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brent Shiver","raw_affiliation_strings":["IBM Research, Austin, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Austin, USA","institution_ids":["https://openalex.org/I4210156936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010167485","display_name":"Charu Pandhi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charu Pandhi","raw_affiliation_strings":["IBM Research, Austin, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Austin, USA","institution_ids":["https://openalex.org/I4210156936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082013025","display_name":"Shari Trewin","orcid":"https://orcid.org/0000-0002-8621-3343"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shari Trewin","raw_affiliation_strings":["IBM Research, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091460837"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6494,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94056099,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"414","last_page":"416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9897000193595886,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/computer-science","display_name":"Computer science","score":0.8202718496322632},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7358989715576172},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.6891442537307739},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5952012538909912},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5282379984855652},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4356032609939575},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.4257059693336487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4186560809612274},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33293238282203674},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09301814436912537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202718496322632},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7358989715576172},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.6891442537307739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5952012538909912},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5282379984855652},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4356032609939575},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4257059693336487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4186560809612274},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33293238282203674},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09301814436912537},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3234695.3241023","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3234695.3241023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International ACM SIGACCESS Conference on Computers and Accessibility","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W228323234","https://openalex.org/W1495423537","https://openalex.org/W2049515993","https://openalex.org/W2338012757","https://openalex.org/W2472070765","https://openalex.org/W2535013011","https://openalex.org/W2747964575","https://openalex.org/W2765828580","https://openalex.org/W2796199965","https://openalex.org/W2969347649","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2936002343","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314"],"abstract_inverted_index":{"Currently,":[0],"video":[1],"sites":[2],"that":[3,85],"offer":[4],"automatic":[5],"speech":[6,52],"recognition":[7],"display":[8,74,90],"the":[9,40,55,73],"auto-generated":[10],"captions":[11,23,41],"as":[12,58],"arbitrarily":[13],"segmented":[14],"lines":[15,76],"of":[16,21,75,77,82,96,103],"unpunctuated":[17],"text.":[18],"This":[19],"method":[20],"displaying":[22],"can":[24,42],"be":[25,43],"detrimental":[26],"to":[27,88],"meaning,":[28],"especially":[29],"for":[30,62,67],"deaf":[31],"users":[32,83],"who":[33],"rely":[34],"almost":[35],"exclusively":[36],"on":[37],"captions.":[38,78],"However,":[39],"made":[44],"more":[45,68],"readable":[46],"by":[47,93],"automatically":[48],"detecting":[49],"pauses":[50],"in":[51],"and":[53,66,71],"using":[54],"pause":[56],"duration":[57],"a":[59,94],"determinant":[60],"both":[61],"inserting":[63],"simple":[64],"punctuation":[65],"meaningfully":[69],"segmenting":[70],"timing":[72],"A":[79],"small":[80],"sampling":[81],"suggests":[84],"such":[86],"adaptations":[87],"caption":[89],"are":[91,100],"preferred":[92],"majority":[95],"users,":[97],"whether":[98],"they":[99],"deaf,":[101],"hard":[102],"hearing":[104],"or":[105],"hearing.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
