{"id":"https://openalex.org/W4393970683","doi":"https://doi.org/10.1145/3640543.3645154","title":"Utilizing a Dense Video Captioning Technique for Generating Image Descriptions of Comics for People with Visual Impairments","display_name":"Utilizing a Dense Video Captioning Technique for Generating Image Descriptions of Comics for People with Visual Impairments","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4393970683","doi":"https://doi.org/10.1145/3640543.3645154"},"language":"en","primary_location":{"id":"doi:10.1145/3640543.3645154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640543.3645154","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640543.3645154","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3640543.3645154","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074496388","display_name":"Suhyun Kim","orcid":"https://orcid.org/0009-0008-1690-2777"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Suhyun Kim","raw_affiliation_strings":["The Department of Artificial Intelligence Convergence, Ewha Womans University, Korea, Republic of"],"raw_orcid":"https://orcid.org/0009-0008-1690-2777","affiliations":[{"raw_affiliation_string":"The Department of Artificial Intelligence Convergence, Ewha Womans University, Korea, Republic of","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091331018","display_name":"S.-H. Lee","orcid":"https://orcid.org/0009-0005-8700-7217"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Semin Lee","raw_affiliation_strings":["The Department of Artificial Intelligence Convergence, Ewha Womans University, Korea, Republic of"],"raw_orcid":"https://orcid.org/0009-0005-8700-7217","affiliations":[{"raw_affiliation_string":"The Department of Artificial Intelligence Convergence, Ewha Womans University, Korea, Republic of","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008278563","display_name":"Kyungok Kim","orcid":"https://orcid.org/0009-0005-9728-3856"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungok Kim","raw_affiliation_strings":["The Department of Artificial Intelligence Convergence, Ewha Womans University, Korea, Republic of"],"raw_orcid":"https://orcid.org/0009-0005-9728-3856","affiliations":[{"raw_affiliation_string":"The Department of Artificial Intelligence Convergence, Ewha Womans University, Korea, Republic of","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058167732","display_name":"Uran Oh","orcid":"https://orcid.org/0000-0002-7832-6313"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Uran Oh","raw_affiliation_strings":["Computer Science and Engineering, Ewha Womans University, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0002-7832-6313","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Ewha Womans University, Korea, Republic of","institution_ids":["https://openalex.org/I138925566"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074496388"],"corresponding_institution_ids":["https://openalex.org/I138925566"],"apc_list":null,"apc_paid":null,"fwci":0.4762,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60100098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"750","last_page":"760"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9891999959945679,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9882000088691711,"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":0.890148401260376},{"id":"https://openalex.org/keywords/comics","display_name":"Comics","score":0.8352365493774414},{"id":"https://openalex.org/keywords/clarity","display_name":"CLARITY","score":0.8020262718200684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7870357036590576},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5486276745796204},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5265679359436035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46811121702194214},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.44498682022094727},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4317702054977417},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3359484076499939}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.890148401260376},{"id":"https://openalex.org/C529099274","wikidata":"https://www.wikidata.org/wiki/Q1004","display_name":"Comics","level":2,"score":0.8352365493774414},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.8020262718200684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870357036590576},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5486276745796204},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5265679359436035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46811121702194214},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.44498682022094727},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4317702054977417},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3359484076499939},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3640543.3645154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640543.3645154","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640543.3645154","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3640543.3645154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640543.3645154","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640543.3645154","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1010102630","display_name":null,"funder_award_id":"RS-2022-00155966","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G1224021760","display_name":null,"funder_award_id":"No. RS-2022-00155966","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G1235097852","display_name":null,"funder_award_id":"IITP-2023-2020-0-01460","funder_id":"https://openalex.org/F4320324891","funder_display_name":"Iran Telecommunication Research Center"},{"id":"https://openalex.org/G1529969831","display_name":null,"funder_award_id":"RS-2022-00155966","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6014928966","display_name":null,"funder_award_id":"IITP-2023-2020-0-01460","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6060633543","display_name":null,"funder_award_id":"IITP-2023-2020-0-01460","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6919652826","display_name":null,"funder_award_id":"RS-2022-00155966","funder_id":"https://openalex.org/F4320321365","funder_display_name":"Ewha Womans University"}],"funders":[{"id":"https://openalex.org/F4320321365","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393970683.pdf","grobid_xml":"https://content.openalex.org/works/W4393970683.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1861492603","https://openalex.org/W2250539671","https://openalex.org/W2289988710","https://openalex.org/W2325920097","https://openalex.org/W2588822708","https://openalex.org/W2600463316","https://openalex.org/W2739107216","https://openalex.org/W2748163013","https://openalex.org/W2896108493","https://openalex.org/W2963524571","https://openalex.org/W2963753226","https://openalex.org/W2963916161","https://openalex.org/W2981785182","https://openalex.org/W2981800437","https://openalex.org/W2998746484","https://openalex.org/W3010564927","https://openalex.org/W3095951396","https://openalex.org/W3160237369","https://openalex.org/W3193568238","https://openalex.org/W3205021045","https://openalex.org/W4225005370","https://openalex.org/W4225117586","https://openalex.org/W4292092736","https://openalex.org/W4304098906","https://openalex.org/W4386066097","https://openalex.org/W4386066385"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"To":[0,38,73],"improve":[1,70],"the":[2,26,45,75,85,151,155,187],"accessibility":[3],"of":[4,8,11,49,77,87,90,121,135,165,176,180],"visual":[5,110,170],"figures,":[6],"auto-generation":[7],"text":[9,88,116],"description":[10],"individual":[12],"images":[13,51,122],"has":[14],"been":[15],"studied.":[16],"However,":[17],"it":[18,159],"cannot":[19],"be":[20,29,62,126],"directly":[21],"applied":[22],"to":[23,69,81,125],"comics":[24],"as":[25,31],"descriptions":[27,46,89,117,174,197],"can":[28,61],"redundant":[30],"similar":[32],"scenes":[33],"appear":[34],"in":[35,133,163],"a":[36,94,102,199],"row.":[37],"address":[39],"this":[40,65],"issue,":[41],"we":[42,92,189],"propose":[43],"generating":[44,194],"per":[47,119,131],"group":[48,120,173],"related":[50],"and":[52,67,80,101,141,182],"demonstrate":[53],"how":[54],"an":[55],"dense":[56],"captioning":[57],"technique":[58],"for":[59,64,143,193,201],"videos":[60],"utilized":[63],"purpose":[66],"ways":[68],"its":[71],"performance.":[72],"assess":[74],"effectiveness":[76],"our":[78],"approach":[79],"identify":[82],"factors":[83],"affecting":[84],"quality":[86],"comics,":[91],"conducted":[93],"preliminary":[95],"study":[96,105],"with":[97,106,109,169],"3":[98],"sighted":[99,144],"evaluators":[100],"main":[103],"user":[104],"12":[107],"participants":[108],"impairments.":[111],"The":[112],"results":[113],"show":[114],"that":[115],"generated":[118,130],"are":[123],"perceived":[124],"better":[127,161],"than":[128],"those":[129],"image":[132],"terms":[134,164],"accuracy,":[136],"clarity,":[137],"understandability,":[138],"length,":[139],"informativeness":[140],"preference":[142],"groups,":[145],"when":[146,154],"annotator":[147,156],"is":[148,157],"human.":[149],"In":[150],"same":[152],"conditions,":[153],"AI,":[158],"exhibited":[160],"performance":[162],"length.":[166],"Also,":[167],"people":[168],"impairments":[171],"prefer":[172],"because":[175],"conciseness,":[177],"smooth":[178],"connectivity":[179],"sentences,":[181],"non-repetitive":[183],"features.":[184],"Based":[185],"on":[186],"findings,":[188],"provide":[190],"design":[191],"recommendations":[192],"accessible":[195],"comic":[196],"at":[198],"scale":[200],"blind":[202],"users.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}