{"id":"https://openalex.org/W7141662892","doi":"https://doi.org/10.1109/icce67443.2026.11449885","title":"A Multimodal Visually Impaired Navigation Interface Based on Environmental Perception and Visual Language Model","display_name":"A Multimodal Visually Impaired Navigation Interface Based on Environmental Perception and Visual Language Model","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7141662892","doi":"https://doi.org/10.1109/icce67443.2026.11449885"},"language":null,"primary_location":{"id":"doi:10.1109/icce67443.2026.11449885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce67443.2026.11449885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Consumer Electronics (ICCE)","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/A5101997848","display_name":"Yunlong Fan","orcid":"https://orcid.org/0000-0002-5975-593X"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu-Hsiang Fan","raw_affiliation_strings":["National Taipei University of Technology,Department of Computer Science and Information Engineering,Taipei,Taiwan,106"],"affiliations":[{"raw_affiliation_string":"National Taipei University of Technology,Department of Computer Science and Information Engineering,Taipei,Taiwan,106","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130769843","display_name":"Huei-Yung Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Huei-Yung Lin","raw_affiliation_strings":["National Taipei University of Technology,Department of Computer Science and Information Engineering,Taipei,Taiwan,106"],"affiliations":[{"raw_affiliation_string":"National Taipei University of Technology,Department of Computer Science and Information Engineering,Taipei,Taiwan,106","institution_ids":["https://openalex.org/I118292597"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101997848"],"corresponding_institution_ids":["https://openalex.org/I118292597"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.9085867,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.8810999989509583,"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":0.8810999989509583,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.02239999920129776,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.014800000004470348,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visually-impaired","display_name":"Visually impaired","score":0.5697000026702881},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.492900013923645},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4855000078678131},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4056999981403351},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.35040000081062317},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.3474000096321106},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.325300008058548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5791000127792358},{"id":"https://openalex.org/C3020106864","wikidata":"https://www.wikidata.org/wiki/Q737460","display_name":"Visually impaired","level":2,"score":0.5697000026702881},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.492900013923645},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49129998683929443},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4611000120639801},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42089998722076416},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3474000096321106},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3093000054359436},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3066999912261963},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28119999170303345},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2781372952","wikidata":"https://www.wikidata.org/wiki/Q737460","display_name":"Visual impairment","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce67443.2026.11449885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce67443.2026.11449885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Consumer Electronics (ICCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1612997784","https://openalex.org/W2562093525","https://openalex.org/W2767980198","https://openalex.org/W2792585818","https://openalex.org/W2805440904","https://openalex.org/W2898231767","https://openalex.org/W3013602055","https://openalex.org/W3025381604","https://openalex.org/W4210549882","https://openalex.org/W4225985704","https://openalex.org/W4312426743","https://openalex.org/W4387872611","https://openalex.org/W4390099685","https://openalex.org/W4402215899","https://openalex.org/W4402716047","https://openalex.org/W4405785137","https://openalex.org/W4405785760","https://openalex.org/W4408222706"],"related_works":[],"abstract_inverted_index":{"Visually":[0],"impaired":[1],"people":[2],"often":[3],"face":[4],"significant":[5],"challenges":[6],"in":[7],"navigation":[8,44,101,141],"due":[9],"to":[10,31,115],"limited":[11],"spatial":[12,133],"awareness":[13],"and":[14,54,71,74,89,95,106,135],"the":[15,47,58,107,125,140],"lack":[16],"of":[17,60],"semantic":[18,80,96,131],"guidance.":[19,97],"Conventional":[20],"assistive":[21],"tools":[22],"commonly":[23],"rely":[24],"on":[25],"fixed":[26],"infrastructure,":[27],"making":[28],"them":[29],"inadequate":[30],"provide":[32],"real-time,":[33],"context-aware":[34],"support.":[35],"In":[36],"this":[37],"work,":[38],"we":[39],"propose":[40],"a":[41],"human-AI":[42],"collaborative":[43],"approach":[45],"for":[46,79,91],"visually":[48],"impaired.":[49],"It":[50,83],"leverages":[51],"multimodal":[52],"perception":[53],"language":[55,76,112],"reasoning":[56],"without":[57],"need":[59],"additional":[61],"environmental":[62],"setup.":[63],"The":[64,120],"system":[65,127],"integrates":[66],"speech":[67],"input/output":[68],"module,":[69],"localization":[70],"mapping":[72],"technique,":[73],"large":[75],"models":[77,87],"(LLMs)":[78],"path":[81],"planning.":[82],"further":[84],"incorporates":[85],"visual-language":[86],"(VLMs)":[88],"YOLO-World":[90],"real-time":[92],"scene":[93],"understanding":[94],"Users":[98],"specify":[99],"their":[100],"goals":[102],"via":[103],"voice":[104],"commands,":[105],"interface":[108],"responds":[109],"with":[110],"natural":[111],"instructions":[113],"synthesized":[114],"speech,":[116],"enabling":[117],"informed":[118],"decision-making.":[119],"experimental":[121],"results":[122],"demonstrate":[123],"that":[124],"proposed":[126],"has":[128],"achieved":[129],"effective":[130],"understanding,":[132],"perception,":[134],"interactive":[136],"guidance,":[137],"significantly":[138],"enhancing":[139],"efficiency.":[142],"Code":[143],"is":[144],"available":[145],"at":[146],"https://github.com/Kana-Fan/VIPAS.":[147]},"counts_by_year":[],"updated_date":"2026-03-29T06:01:01.467347","created_date":"2026-03-28T00:00:00"}
