{"id":"https://openalex.org/W7138256216","doi":"https://doi.org/10.1609/aaai.v40i6.42410","title":"VisAssist: A Visually Impaired-Captured Video Question Answering Benchmark for Assistive Systems","display_name":"VisAssist: A Visually Impaired-Captured Video Question Answering Benchmark for Assistive Systems","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138256216","doi":"https://doi.org/10.1609/aaai.v40i6.42410"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i6.42410","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42410","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i6.42410","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129656088","display_name":"Qi Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Gao","raw_affiliation_strings":["School of Biomedical Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129666621","display_name":"Heng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Li","raw_affiliation_strings":["School of Biomedical Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129708232","display_name":"Yixin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Zhou","raw_affiliation_strings":["School of Biomedical Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063731332","display_name":"Meixuan Zhou","orcid":"https://orcid.org/0009-0002-1175-4118"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meixuan Zhou","raw_affiliation_strings":["School of Biomedical Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129647717","display_name":"Jieqiong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135742","display_name":"Shanghai First People's Hospital","ror":"https://ror.org/04a46mh28","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210135742"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieqiong Chen","raw_affiliation_strings":["Department of Ophthalmology, Shanghai General Hospital, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Ophthalmology, Shanghai General Hospital, China","institution_ids":["https://openalex.org/I4210135742"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101020962","display_name":"Xinyu Chai","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Chai","raw_affiliation_strings":["School of Biomedical Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"6","first_page":"4149","last_page":"4157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9517999887466431,"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":0.9517999887466431,"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":0.00989999994635582,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.009800000116229057,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.796500027179718},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5059999823570251},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4602999985218048},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.40119999647140503},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3560999929904938},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3138999938964844}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.796500027179718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7502999901771545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5365999937057495},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43149998784065247},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37310001254081726},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.26330000162124634}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i6.42410","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42410","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/42410","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/42410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i6.42410","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42410","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"VisAssist,":[2],"the":[3,106],"first":[4],"large-scale":[5],"video":[6],"question-answering":[7],"dataset":[8],"with":[9],"13,413":[10],"real-world":[11,102],"videos":[12],"captured":[13],"by":[14],"visually":[15],"impaired":[16],"users,":[17],"addressing":[18],"a":[19,100],"critical":[20],"gap":[21],"in":[22,42,64,111],"assistive":[23],"vision":[24],"research.":[25],"Unlike":[26],"existing":[27],"benchmarks":[28],"relying":[29],"on":[30],"third-person":[31],"footage,":[32],"VisAssist":[33],"provides":[34],"authentic":[35],"first-person":[36,70],"perspectives":[37],"that":[38],"uniquely":[39],"capture":[40,80],"challenges":[41],"blind":[43],"photography\u2014including":[44],"unconventional":[45],"framing,":[46],"motion":[47],"artifacts,":[48],"and":[49,86,104],"frequent":[50],"information":[51,77],"omission.":[52],"Benchmark":[53],"evaluations":[54],"of":[55],"SOTA":[56],"multimodal":[57],"models":[58],"reveal":[59],"systematic":[60],"limitations:":[61],"severe":[62],"deficiencies":[63],"spatial":[65],"reasoning":[66],"when":[67],"processing":[68],"dynamic":[69],"viewpoints,":[71],"an":[72],"inability":[73],"to":[74,83],"distinguish":[75],"missing":[76],"from":[78],"poor":[79],"quality":[81],"leading":[82],"hazardous":[84],"hallucinations,":[85],"fragile":[87],"text":[88],"understanding":[89],"especially":[90],"for":[91,108],"non-Latin":[92],"scripts":[93],"under":[94],"suboptimal":[95],"conditions.":[96],"This":[97],"work":[98],"establishes":[99],"vital":[101],"benchmark":[103],"underscores":[105],"need":[107],"specialized":[109],"architectures":[110],"visual":[112],"assistance":[113],"systems.":[114]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}
