{"id":"https://openalex.org/W4405957202","doi":"https://doi.org/10.1109/iccv51701.2025.00918","title":"WalkVLM: Aid Visually Impaired People Walking by Vision Language Model","display_name":"WalkVLM: Aid Visually Impaired People Walking by Vision Language Model","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405957202","doi":"https://doi.org/10.1109/iccv51701.2025.00918"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.20903","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047493987","display_name":"Zhiqiang Yuan","orcid":"https://orcid.org/0000-0002-4957-1651"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Yuan","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738839","display_name":"Ting Zhang","orcid":"https://orcid.org/0000-0002-1899-1784"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Zhang","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yeshuang Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yeshuang Zhu","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057087002","display_name":"Jiapei Zhang","orcid":"https://orcid.org/0009-0004-2970-9416"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiapei Zhang","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ying Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Deng","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zexi Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zexi Jia","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peixiang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peixiang Luo","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyue Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyue Duan","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055646953","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0002-6002-291X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101924370","display_name":"Jinchao Zhang","orcid":"https://orcid.org/0009-0006-3863-9311"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinchao Zhang","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"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":null,"issue":null,"first_page":"9845","last_page":"9854"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.8804000020027161,"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":0.8804000020027161,"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/visually-impaired","display_name":"Visually impaired","score":0.7404764890670776},{"id":"https://openalex.org/keywords/impaired-vision","display_name":"Impaired Vision","score":0.4908931851387024},{"id":"https://openalex.org/keywords/physical-medicine-and-rehabilitation","display_name":"Physical medicine and rehabilitation","score":0.4403212070465088},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41026195883750916},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4012313187122345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.382928729057312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3505101799964905},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.24920204281806946},{"id":"https://openalex.org/keywords/optometry","display_name":"Optometry","score":0.21940934658050537},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.16469141840934753}],"concepts":[{"id":"https://openalex.org/C3020106864","wikidata":"https://www.wikidata.org/wiki/Q737460","display_name":"Visually impaired","level":2,"score":0.7404764890670776},{"id":"https://openalex.org/C2909902731","wikidata":"https://www.wikidata.org/wiki/Q737460","display_name":"Impaired Vision","level":2,"score":0.4908931851387024},{"id":"https://openalex.org/C99508421","wikidata":"https://www.wikidata.org/wiki/Q2678675","display_name":"Physical medicine and rehabilitation","level":1,"score":0.4403212070465088},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41026195883750916},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4012313187122345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.382928729057312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3505101799964905},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.24920204281806946},{"id":"https://openalex.org/C119767625","wikidata":"https://www.wikidata.org/wiki/Q618211","display_name":"Optometry","level":1,"score":0.21940934658050537},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.16469141840934753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.20903","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.20903","pdf_url":"https://arxiv.org/pdf/2412.20903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.20903","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.20903","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.20903","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.20903","pdf_url":"https://arxiv.org/pdf/2412.20903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Approximately":[0],"200":[1],"million":[2],"individuals":[3],"around":[4],"the":[5,29,167,185],"world":[6],"suffer":[7,97],"from":[8,98,124],"varying":[9],"degrees":[10],"of":[11,32,149,170,187],"visual":[12],"impairment,":[13],"making":[14],"it":[15,74],"crucial":[16],"to":[17,21,38,77,128,154,165,197],"leverage":[18],"AI":[19],"technology":[20],"offer":[22],"walking":[23,72,116,138,181],"assistance":[24],"for":[25,66,94,136,151,179,193],"these":[26],"people.":[27],"With":[28],"recent":[30],"progress":[31],"vision-language":[33],"models":[34],"(VLMs),":[35],"employing":[36],"VLMs":[37,95],"improve":[39],"this":[40,106,194],"field":[41],"has":[42],"emerged":[43],"as":[44],"a":[45,60,91,111,130,141,176],"popular":[46],"research":[47],"topic.":[48],"However,":[49],"most":[50],"existing":[51],"methods":[52],"are":[53],"studied":[54],"on":[55],"self-built":[56],"question-answering":[57],"datasets,":[58],"lacking":[59],"unified":[61],"training":[62,132],"and":[63,83,101,114,126,133,160,183,202],"testing":[64,134],"benchmark":[65,135,178],"walk":[67],"guidance.":[68],"Moreover,":[69],"in":[70,189],"blind":[71,137,180],"task,":[73],"is":[75,144],"necessary":[76],"perform":[78],"real-time":[79],"streaming":[80],"video":[81,191],"parsing":[82],"generate":[84,155],"concise":[85,156],"yet":[86],"informative":[87,158],"reminders,":[88],"which":[89,146],"poses":[90],"great":[92],"challenge":[93],"that":[96],"redundant":[99],"responses":[100],"low":[102],"inference":[103],"efficiency.":[104],"In":[105],"paper,":[107],"we":[108,173],"firstly":[109],"release":[110],"diverse,":[112],"extensive,":[113],"unbiased":[115],"awareness":[117],"dataset,":[118],"containing":[119],"12k":[120],"video-manual":[121],"annotation":[122],"pairs":[123],"Europe":[125],"Asia":[127],"provide":[129],"fair":[131],"task.":[139],"Furthermore,":[140],"WalkVLM":[142,188],"model":[143],"proposed,":[145],"employs":[147],"chain":[148],"thought":[150],"hierarchical":[152],"planning":[153],"but":[157],"reminders":[159],"utilizes":[161],"temporal-aware":[162],"adaptive":[163],"prediction":[164],"reduce":[166],"temporal":[168],"redundancy":[169],"reminders.":[171],"Finally,":[172],"have":[174],"established":[175],"solid":[177],"task":[182,195],"verified":[184],"advantages":[186],"stream":[190],"processing":[192],"compared":[196],"other":[198],"VLMs.":[199],"Our":[200],"dataset":[201],"code":[203],"will":[204],"be":[205],"released":[206],"at":[207],"anonymous":[208],"link":[209],"https://walkvlm2024.github.io.":[210]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}