{"id":"https://openalex.org/W7125906302","doi":"https://doi.org/10.1109/smc58881.2025.11343278","title":"BLaVe-CoT: Consistency-Aware Visual Question Answering for Blind and Low Vision Users","display_name":"BLaVe-CoT: Consistency-Aware Visual Question Answering for Blind and Low Vision Users","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125906302","doi":"https://doi.org/10.1109/smc58881.2025.11343278"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124132448","display_name":"Wanyin Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wanyin Cheng","raw_affiliation_strings":["Qufu Normal University,School of Cyber Science and Engineering,Qufu,China"],"affiliations":[{"raw_affiliation_string":"Qufu Normal University,School of Cyber Science and Engineering,Qufu,China","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093945276","display_name":"Zanxi Ruan","orcid":"https://orcid.org/0000-0002-7756-8249"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Zanxi Ruan","raw_affiliation_strings":["University of Verona,Department of Computer Science,Verona,Italy"],"affiliations":[{"raw_affiliation_string":"University of Verona,Department of Computer Science,Verona,Italy","institution_ids":["https://openalex.org/I119439378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5124132448"],"corresponding_institution_ids":["https://openalex.org/I202126657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72650439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2418","last_page":"2423"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9934999942779541,"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":0.9934999942779541,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0007999999797903001,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0007999999797903001,"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/question-answering","display_name":"Question answering","score":0.8414999842643738},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.7041000127792358},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.51419997215271},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5083000063896179},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.45750001072883606},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.400299996137619},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.37929999828338623},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.35120001435279846}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8414999842643738},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7041000127792358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.51419997215271},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47119998931884766},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38269999623298645},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38260000944137573},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35120001435279846},{"id":"https://openalex.org/C2983447183","wikidata":"https://www.wikidata.org/wiki/Q737460","display_name":"Low vision","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.42803213000297546,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2468256935","https://openalex.org/W2963622213","https://openalex.org/W2968097540","https://openalex.org/W3159433218","https://openalex.org/W3214203369","https://openalex.org/W4386065406","https://openalex.org/W4386075493","https://openalex.org/W4390872994","https://openalex.org/W4399199832","https://openalex.org/W4401114324","https://openalex.org/W4402754145","https://openalex.org/W4405974783","https://openalex.org/W4407049645","https://openalex.org/W4407346642","https://openalex.org/W4409720442","https://openalex.org/W4414109430"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"holds":[4],"great":[5],"potential":[6],"for":[7,175,189],"assisting":[8],"Blind":[9],"and":[10,33,55,87,128,156,163,185,196],"Low":[11],"Vision":[12],"(BLV)":[13],"users,":[14],"yet":[15],"real-world":[16],"usage":[17],"remains":[18],"challenging.":[19],"Due":[20],"to":[21,66,100,135,141,160,181],"visual":[22,50,164],"impairments,":[23],"BLV":[24,190],"users":[25,57],"often":[26],"take":[27],"blurry":[28],"or":[29,144],"poorly":[30],"framed":[31],"photos":[32],"face":[34,107],"difficulty":[35],"in":[36,61,72,105,167],"articulating":[37],"specific":[38],"questions":[39,51],"about":[40,102],"what":[41],"they":[42],"cannot":[43],"fully":[44],"see.":[45],"As":[46],"a":[47,76,84,96,117,131],"result,":[48],"their":[49],"are":[52],"frequently":[53],"ambiguous,":[54],"different":[56,73,145],"may":[58],"interpret":[59],"them":[60],"diverse":[62,113],"ways.":[63],"This":[64,170],"leads":[65],"multiple":[67],"valid":[68],"answers,":[69],"each":[70,123],"grounded":[71],"image":[74],"regionsposing":[75],"mismatch":[77],"with":[78],"conventional":[79],"VQA":[80,97,176],"systems":[81,177],"that":[82,178],"assume":[83],"single":[85],"answer":[86,103,124],"region.":[88],"To":[89,192],"bridge":[90],"this":[91],"gap,":[92],"we":[93,199],"present":[94],"BLaVe-CoT,":[95],"framework":[98],"designed":[99],"reason":[101],"consistency":[104],"the":[106,138,142,149,161,173,202],"of":[108],"ambiguity.":[109],"Our":[110],"method":[111],"proposes":[112],"candidate":[114],"answers":[115,139],"using":[116,126],"LoRA-tuned":[118],"BLIP-2":[119],"model,":[120],"then":[121],"grounds":[122],"spatially":[125],"PolyFormer,":[127],"finally":[129],"applies":[130],"chain-of-thought":[132],"reasoning":[133],"module":[134],"assess":[136],"whether":[137],"refer":[140],"same":[143],"regions.":[146],"Evaluated":[147],"on":[148],"VQA-AnswerTherapy":[150],"benchmark,":[151],"BLaVe-CoT":[152],"outperforms":[153],"previous":[154],"methods":[155],"proves":[157],"more":[158],"robust":[159],"ambiguity":[162],"noise":[165],"common":[166],"assistive":[168],"settings.":[169],"work":[171],"highlights":[172],"need":[174],"can":[179],"adapt":[180],"real":[182],"human":[183],"uncertainty":[184],"provide":[186],"inclusive":[187],"support":[188],"users.":[191],"foster":[193],"further":[194],"research":[195],"accessibility":[197],"applications,":[198],"have":[200],"made":[201],"code":[203],"publicly":[204],"available":[205],"at":[206],"https://github.com/Accecwan/BLaVe-CoT.":[207]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-29T00:00:00"}