{"id":"https://openalex.org/W4410919274","doi":"https://doi.org/10.1145/3706370.3731641","title":"See Through My Eyes: Using Multimodal Large Language Model for Describing Rendered Environments to Blind People","display_name":"See Through My Eyes: Using Multimodal Large Language Model for Describing Rendered Environments to Blind People","publication_year":2025,"publication_date":"2025-05-31","ids":{"openalex":"https://openalex.org/W4410919274","doi":"https://doi.org/10.1145/3706370.3731641"},"language":"en","primary_location":{"id":"doi:10.1145/3706370.3731641","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3706370.3731641","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3706370.3731641","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM International Conference on Interactive Media Experiences","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3706370.3731641","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093665521","display_name":"Angelo Coronado","orcid":"https://orcid.org/0009-0009-2810-979X"},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Angelo Coronado","raw_affiliation_strings":["Federal University of Goias (UFG), Goiania, Brazil, and Advanced Knowledge Center for Immersive Technologies (AKCIT), Goiania, Brazil"],"raw_orcid":"https://orcid.org/0009-0009-2810-979X","affiliations":[{"raw_affiliation_string":"Federal University of Goias (UFG), Goiania, Brazil, and Advanced Knowledge Center for Immersive Technologies (AKCIT), Goiania, Brazil","institution_ids":["https://openalex.org/I68106152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017640974","display_name":"S\u00e9rgio T. Carvalho","orcid":"https://orcid.org/0000-0002-4191-5173"},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Sergio T Carvalho","raw_affiliation_strings":["Federal University of Goi\u00e1s (UFG), Goi\u00e2nia, Brazil, and Advanced Knowledge Center for Immersive Technologies (AKCIT), Goiania, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-4191-5173","affiliations":[{"raw_affiliation_string":"Federal University of Goi\u00e1s (UFG), Goi\u00e2nia, Brazil, and Advanced Knowledge Center for Immersive Technologies (AKCIT), Goiania, Brazil","institution_ids":["https://openalex.org/I68106152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084516848","display_name":"Luciana de Oliveira Berretta","orcid":"https://orcid.org/0000-0003-1857-8989"},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Luciana Berretta","raw_affiliation_strings":["Federal University of Goi\u00e1s, Goi\u00e2nia, Brazil, and Advanced Knowledge Center for Immersive Technologies (AKCIT), Goiania, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-1857-8989","affiliations":[{"raw_affiliation_string":"Federal University of Goi\u00e1s, Goi\u00e2nia, Brazil, and Advanced Knowledge Center for Immersive Technologies (AKCIT), Goiania, Brazil","institution_ids":["https://openalex.org/I68106152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I68106152"],"apc_list":null,"apc_paid":null,"fwci":4.7221,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93654765,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"451","last_page":"457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9959999918937683,"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"}},"topics":[{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9959999918937683,"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"}},{"id":"https://openalex.org/T12481","display_name":"Digital Accessibility for Disabilities","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/3307","display_name":"Human Factors and Ergonomics"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.988099992275238,"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/computer-science","display_name":"Computer science","score":0.7411869168281555},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.47581034898757935},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41819286346435547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3958001732826233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3478390574455261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3269040286540985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411869168281555},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.47581034898757935},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41819286346435547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3958001732826233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3478390574455261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3269040286540985}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3706370.3731641","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3706370.3731641","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3706370.3731641","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM International Conference on Interactive Media Experiences","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3706370.3731641","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3706370.3731641","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3706370.3731641","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM International Conference on Interactive Media Experiences","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410919274.pdf","grobid_xml":"https://content.openalex.org/works/W4410919274.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2097256182","https://openalex.org/W2746864141","https://openalex.org/W2747544877","https://openalex.org/W2773691412","https://openalex.org/W2972795682","https://openalex.org/W3030405946","https://openalex.org/W3094724619","https://openalex.org/W4293060318","https://openalex.org/W4386632332","https://openalex.org/W4387793260","https://openalex.org/W4389519254","https://openalex.org/W4401943422","https://openalex.org/W4402957947","https://openalex.org/W4403576901","https://openalex.org/W4404698642"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Extended":[0,81],"Reality":[1,82],"(XR)":[2],"is":[3,54,64,173,197],"quickly":[4],"expanding":[5],"\"as":[6],"the":[7,32,75,148,154,158,167,191,195,209],"next":[8],"major":[9],"technology":[10],"wave":[11],"in":[12,37,60,74,113,194],"personal":[13],"computing\".Nevertheless,":[14],"this":[15,84,106],"expansion":[16],"and":[17,80,150,185,188],"adoption":[18],"could":[19],"also":[20,55],"exclude":[21],"certain":[22],"disabled":[23,68],"users,":[24,69],"particularly":[25],"people":[26,47,205],"with":[27,48,166],"visual":[28,49],"impairment":[29],"(VIP).According":[30],"to":[31,57,66,132,176,198,207],"World":[33],"Health":[34],"Organization":[35],"(WHO)":[36],"their":[38],"2019":[39],"publication,":[40],"there":[41],"were":[42,130,145],"at":[43],"least":[44],"2.2":[45],"billion":[46],"impairment,":[50],"a":[51,103,121,141,162],"number":[52],"that":[53,111,157,164],"estimated":[56],"have":[58],"increased":[59],"recent":[61],"years.Therefore,":[62],"it":[63,172],"important":[65],"include":[67],"especially":[70],"visually":[71,100,137,203],"impaired":[72,101,138,204],"people,":[73],"design":[76],"of":[77,170],"Head-Mounted":[78],"Displays":[79],"environments.Indeed,":[83],"objective":[85],"can":[86,98],"be":[87],"pursued":[88],"by":[89,202],"incorporating":[90],"Multimodal":[91],"Large":[92],"Language":[93],"Model":[94],"(MLLM)":[95],"technology,":[96],"which":[97],"assist":[99],"people.As":[102],"case":[104],"study,":[105],"study":[107],"employs":[108],"different":[109],"prompts":[110,129],"result":[112],"environment":[114],"descriptions":[115],"from":[116,183],"an":[117],"MLLM":[118],"integrated":[119],"into":[120],"virtual":[122],"reality":[123],"(VR)":[124],"escape":[125],"room.Therefore,":[126],"six":[127],"potential":[128],"engineered":[131],"generate":[133],"valuable":[134],"outputs":[135,144,179,201],"for":[136],"users":[139],"inside":[140],"VR":[142],"environment.These":[143],"evaluated":[146],"using":[147],"G-Eval,":[149],"VIEScore":[151],"metrics.Even":[152],"though,":[153],"results":[155],"show":[156],"prompt":[159,212],"patterns":[160],"provided":[161],"description":[163],"aligns":[165],"user's":[168],"point":[169],"view,":[171],"highly":[174],"recommended":[175],"evaluate":[177,199],"these":[178,200],"through":[180],"\"expected":[181],"outputs\"":[182],"Orientation":[184],"Mobility":[186],"Specialists,":[187],"Sighted":[189],"Guides.Furthermore,":[190],"subsequent":[192],"step":[193],"process":[196],"themselves":[206],"identify":[208],"most":[210],"effective":[211],"pattern.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}