{"id":"https://openalex.org/W4387993380","doi":"https://doi.org/10.1145/3586182.3615978","title":"Experiencing Visual Captions: Augmented Communication with Real-time Visuals using Large Language Models","display_name":"Experiencing Visual Captions: Augmented Communication with Real-time Visuals using Large Language Models","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4387993380","doi":"https://doi.org/10.1145/3586182.3615978"},"language":"en","primary_location":{"id":"doi:10.1145/3586182.3615978","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3586182.3615978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology","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/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"],"raw_orcid":"https://orcid.org/0000-0002-6988-5471","affiliations":[{"raw_affiliation_string":"HCI Research, UCLA, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vladimir Kirilyuk","orcid":"https://orcid.org/0000-0003-0619-4718"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vladimir Kirilyuk","raw_affiliation_strings":["Google, United States"],"raw_orcid":"https://orcid.org/0000-0003-0619-4718","affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057800027","display_name":"Xiuxiu Yuan","orcid":"https://orcid.org/0000-0002-9341-993X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiuxiu Yuan","raw_affiliation_strings":["Google, United States"],"raw_orcid":"https://orcid.org/0000-0002-9341-993X","affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018174867","display_name":"Peggy Chi","orcid":"https://orcid.org/0000-0001-8511-2834"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peggy Chi","raw_affiliation_strings":["Google Research, United States"],"raw_orcid":"https://orcid.org/0000-0001-8511-2834","affiliations":[{"raw_affiliation_string":"Google Research, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016503150","display_name":"Alex Olwal","orcid":"https://orcid.org/0000-0001-7772-0530"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Olwal","raw_affiliation_strings":["Google Inc., United States"],"raw_orcid":"https://orcid.org/0000-0001-7772-0530","affiliations":[{"raw_affiliation_string":"Google Inc., United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"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"],"raw_orcid":"https://orcid.org/0000-0002-8527-1744","affiliations":[{"raw_affiliation_string":"HCI Research, UCLA, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001822106","display_name":"Ruofei Du","orcid":"https://orcid.org/0000-0003-2471-9776"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruofei Du","raw_affiliation_strings":["Google, United States"],"raw_orcid":"https://orcid.org/0000-0003-2471-9776","affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100435048"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7065,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.72748036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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/T12031","display_name":"Speech and dialogue systems","score":0.9771999716758728,"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"}},{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9749000072479248,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8017350435256958},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6609139442443848},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6164425611495972},{"id":"https://openalex.org/keywords/proactivity","display_name":"Proactivity","score":0.5781681537628174},{"id":"https://openalex.org/keywords/visual-communication","display_name":"Visual communication","score":0.5759900808334351},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5420428514480591},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5370667576789856},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.5251414775848389},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5048933625221252},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4935489892959595},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4629804193973541},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35908252000808716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21671506762504578},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1123943030834198},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09439033269882202},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09211266040802002},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07740119099617004}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8017350435256958},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6609139442443848},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6164425611495972},{"id":"https://openalex.org/C142944206","wikidata":"https://www.wikidata.org/wiki/Q1786137","display_name":"Proactivity","level":2,"score":0.5781681537628174},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.5759900808334351},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5420428514480591},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5370667576789856},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.5251414775848389},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5048933625221252},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4935489892959595},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4629804193973541},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35908252000808716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21671506762504578},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1123943030834198},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09439033269882202},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09211266040802002},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07740119099617004},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3586182.3615978","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3586182.3615978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4366547453"],"related_works":["https://openalex.org/W2349447564","https://openalex.org/W3102876624","https://openalex.org/W2380748517","https://openalex.org/W2129041165","https://openalex.org/W2913923012","https://openalex.org/W2886679652","https://openalex.org/W2376364126","https://openalex.org/W2359744113","https://openalex.org/W1578442573","https://openalex.org/W2371947820"],"abstract_inverted_index":{"We":[0,40,72],"demonstrate":[1,105],"Visual":[2,18,42,77,120],"Captions,":[3],"a":[4,10,21,45],"real-time":[5],"system":[6,113],"that":[7,30],"integrates":[8],"with":[9,49,111,114],"video":[11],"conferencing":[12],"platform":[13],"to":[14,26,33],"enrich":[15],"verbal":[16],"communication.":[17],"Captions":[19,43,78,121],"leverages":[20],"fine-tuned":[22],"large":[23],"language":[24],"model":[25],"proactively":[27,62],"suggest":[28],"visuals":[29,69,87],"are":[31],"relevant":[32],"the":[34,37,74,84,90,112],"context":[35,91],"of":[36,52,76,86,92,97,117],"ongoing":[38],"conversation.":[39],"implemented":[41],"as":[44],"user-customizable":[46],"Chrome":[47],"plugin":[48],"three":[50,106],"levels":[51,116],"AI":[53,118],"proactivity:":[54],"Auto-display":[55],"(AI":[56,61,67],"autonomously":[57],"adds":[58],"visuals),":[59,64],"Auto-suggest":[60],"recommends":[63],"and":[65,82],"On-demand-suggest":[66],"suggests":[68],"when":[70],"prompted).":[71],"showcase":[73],"usage":[75],"in":[79],"open-vocabulary":[80],"settings,":[81],"how":[83],"addition":[85],"based":[88],"on":[89],"conversations":[93],"could":[94],"improve":[95],"comprehension":[96],"complex":[98],"or":[99],"unfamiliar":[100],"concepts.":[101],"In":[102],"addition,":[103],"we":[104],"approaches":[107],"people":[108],"can":[109],"interact":[110],"different":[115],"proactivity.":[119],"is":[122],"open-sourced":[123],"at":[124],"https://github.com/google/archat.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
