{"id":"https://openalex.org/W4366547453","doi":"https://doi.org/10.1145/3544548.3581566","title":"Visual Captions: Augmenting Verbal Communication with On-the-fly Visuals","display_name":"Visual Captions: Augmenting Verbal Communication with On-the-fly Visuals","publication_year":2023,"publication_date":"2023-04-19","ids":{"openalex":"https://openalex.org/W4366547453","doi":"https://doi.org/10.1145/3544548.3581566"},"language":"en","primary_location":{"id":"doi:10.1145/3544548.3581566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3544548.3581566","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 2023 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3544548.3581566","any_repository_has_fulltext":null},"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":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103214653","display_name":"Vladimir Kirilyuk","orcid":"https://orcid.org/0000-0001-6646-5714"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vladimir Kirilyuk","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057800027","display_name":"Xiuxiu Yuan","orcid":"https://orcid.org/0000-0002-9341-993X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiuxiu Yuan","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016503150","display_name":"Alex Olwal","orcid":"https://orcid.org/0000-0001-7772-0530"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Olwal","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018174867","display_name":"Peggy Chi","orcid":"https://orcid.org/0000-0001-8511-2834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peggy Chi","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"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":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001822106","display_name":"Ruofei Du","orcid":"https://orcid.org/0000-0003-2471-9776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruofei Du","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100435048"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":65.7853,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.99919725,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9919999837875366,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9909999966621399,"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/closed-captioning","display_name":"Closed captioning","score":0.8178962469100952},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7611484527587891},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6001185774803162},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5127659440040588},{"id":"https://openalex.org/keywords/visual-communication","display_name":"Visual communication","score":0.492631733417511},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4785217046737671},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4729582667350769},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4724576771259308},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4682130813598633},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.46736595034599304},{"id":"https://openalex.org/keywords/zoom","display_name":"Zoom","score":0.4252853989601135},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3242991268634796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26055002212524414},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09283378720283508}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8178962469100952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7611484527587891},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6001185774803162},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5127659440040588},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.492631733417511},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4785217046737671},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4729582667350769},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4724576771259308},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4682130813598633},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46736595034599304},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.4252853989601135},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3242991268634796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26055002212524414},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09283378720283508},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.0},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3544548.3581566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3544548.3581566","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 2023 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3544548.3581566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3544548.3581566","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 2023 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W622110004","https://openalex.org/W1967082914","https://openalex.org/W1996090298","https://openalex.org/W2001835519","https://openalex.org/W2014192586","https://openalex.org/W2014621385","https://openalex.org/W2017889037","https://openalex.org/W2023315202","https://openalex.org/W2027680682","https://openalex.org/W2029258298","https://openalex.org/W2036024905","https://openalex.org/W2059216172","https://openalex.org/W2104210067","https://openalex.org/W2106887634","https://openalex.org/W2171507389","https://openalex.org/W2322726446","https://openalex.org/W2467945436","https://openalex.org/W2761204358","https://openalex.org/W2796357535","https://openalex.org/W2808352493","https://openalex.org/W2899011499","https://openalex.org/W2918497321","https://openalex.org/W2941108211","https://openalex.org/W2941918768","https://openalex.org/W2942226338","https://openalex.org/W2963761103","https://openalex.org/W2970641574","https://openalex.org/W2978052557","https://openalex.org/W3031036608","https://openalex.org/W3036167779","https://openalex.org/W3037793211","https://openalex.org/W3083624084","https://openalex.org/W3093699630","https://openalex.org/W3093732029","https://openalex.org/W3093814436","https://openalex.org/W3095259422","https://openalex.org/W3113988938","https://openalex.org/W3121838348","https://openalex.org/W3135367836","https://openalex.org/W3205351373","https://openalex.org/W3206173835","https://openalex.org/W4225113883","https://openalex.org/W4281485151","https://openalex.org/W4283388932","https://openalex.org/W4300309873","https://openalex.org/W4310556944","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W3102876624","https://openalex.org/W2380748517","https://openalex.org/W2129041165","https://openalex.org/W2913923012","https://openalex.org/W2376364126","https://openalex.org/W2886679652","https://openalex.org/W2359744113","https://openalex.org/W1578442573","https://openalex.org/W2128460375","https://openalex.org/W1982768556"],"abstract_inverted_index":{"Video":[0],"conferencing":[1,96],"solutions":[2],"like":[3],"Zoom,":[4],"Google":[5],"Meet,":[6],"and":[7,17,68,126],"Microsoft":[8],"Teams":[9],"are":[10],"becoming":[11],"increasingly":[12],"popular":[13],"for":[14],"facilitating":[15],"conversations,":[16],"recent":[18],"advancements":[19],"such":[20,57],"as":[21],"live":[22],"captioning":[23],"help":[24,137],"people":[25],"better":[26],"understand":[27],"each":[28],"other.":[29],"We":[30,118],"believe":[31],"that":[32,91],"the":[33,39,54],"addition":[34],"of":[35,41,47,56,72,81],"visuals":[36,114],"based":[37],"on":[38],"context":[40],"conversations":[42],"could":[43],"further":[44],"improve":[45,138],"comprehension":[46],"complex":[48],"or":[49],"unfamiliar":[50],"concepts.":[51],"To":[52],"explore":[53],"potential":[55],"capabilities,":[58],"we":[59],"conducted":[60],"a":[61,70,78,88,94,105,122],"formative":[62],"study":[63,124,130],"through":[64,140],"remote":[65],"interviews":[66],"(N=10)":[67],"crowdsourced":[69],"dataset":[71],"over":[73],"1500":[74],"sentence-visual":[75],"pairs":[76],"across":[77],"wide":[79],"range":[80],"contexts.":[82],"These":[83],"insights":[84],"informed":[85],"Visual":[86,102,134],"Captions,":[87],"real-time":[89],"system":[90],"integrates":[92],"with":[93],"video":[95],"platform":[97],"to":[98,110],"enrich":[99],"verbal":[100],"communication.":[101],"Captions":[103,135],"leverages":[104],"fine-tuned":[106],"large":[107],"language":[108],"model":[109],"proactively":[111],"suggest":[112],"relevant":[113],"in":[115,143],"open-vocabulary":[116],"conversations.":[117],"present":[119],"findings":[120],"from":[121],"lab":[123],"(N=26)":[125],"an":[127],"in-the-wild":[128],"case":[129],"(N=10),":[131],"demonstrating":[132],"how":[133],"can":[136],"communication":[139],"visual":[141],"augmentation":[142],"various":[144],"scenarios.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
