{"id":"https://openalex.org/W7158618223","doi":"https://doi.org/10.48550/arxiv.2604.26873","title":"Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning","display_name":"Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning","publication_year":2026,"publication_date":"2026-04-29","ids":{"openalex":"https://openalex.org/W7158618223","doi":"https://doi.org/10.48550/arxiv.2604.26873"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.26873","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26873","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.26873","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134927045","display_name":"Zhuofan Lou","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lou, Zhuofan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134912642","display_name":"Shihang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134910554","display_name":"Fangle Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Fangle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123217467","display_name":"Shengjie Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Shengjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134916579","display_name":"Pingyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Pingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5134927045"],"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":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6498000025749207,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6498000025749207,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.05310000106692314,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.05249999836087227,"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/robustness","display_name":"Robustness (evolution)","score":0.6341999769210815},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6128000020980835},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.5960999727249146},{"id":"https://openalex.org/keywords/pedestrian-detection","display_name":"Pedestrian detection","score":0.5436999797821045},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4607999920845032},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.37940001487731934},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3336000144481659},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.31630000472068787}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7943000197410583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6935999989509583},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6341999769210815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6194000244140625},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6128000020980835},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.5960999727249146},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.5436999797821045},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4607999920845032},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.37940001487731934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C156201811","wikidata":"https://www.wikidata.org/wiki/Q5418360","display_name":"Evidential reasoning approach","level":4,"score":0.28690001368522644},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.26873","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26873","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.26873","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26873","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"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],"propose":[1],"UAPAR,":[2],"an":[3,89,104],"Uncertainty-Aware":[4],"Pedestrian":[5],"Attribute":[6],"Recognition":[7],"framework.":[8],"To":[9,54,97],"the":[10,17,112,124,144],"best":[11],"of":[12,115,153],"our":[13],"knowledge,":[14],"this":[15],"is":[16],"first":[18],"EDL-based":[19],"uncertainty-aware":[20],"framework":[21,146],"for":[22],"pedestrian":[23],"attribute":[24],"recognition":[25],"(PAR).":[26],"Unlike":[27],"conventional":[28],"deterministic":[29],"methods,":[30],"which":[31,84],"fail":[32],"to":[33,79,92,110],"assess":[34],"prediction":[35],"reliability":[36],"on":[37,123],"low-quality":[38],"samples,":[39],"UAPAR":[40,57,133],"effectively":[41],"identifies":[42],"unreliable":[43],"predictions":[44],"and":[45,75,128],"thus":[46],"enhances":[47],"system":[48],"robustness":[49],"in":[50],"complex":[51],"real-world":[52],"scenarios.":[53],"achieve":[55],"this,":[56],"incorporates":[58],"Evidential":[59],"Deep":[60],"Learning":[61],"(EDL)":[62],"into":[63],"a":[64,68],"CLIP-based":[65],"architecture.":[66],"Specifically,":[67],"Region-Aware":[69],"Evidence":[70],"Reasoning":[71],"module":[72],"employs":[73],"cross-attention":[74],"spatial":[76],"prior":[77],"masks":[78],"capture":[80],"fine-grained":[81],"local":[82],"features,":[83],"are":[85,151],"further":[86,98],"processed":[87],"by":[88],"evidence":[90],"head":[91],"estimate":[93],"attribute-wise":[94],"epistemic":[95],"uncertainty.":[96],"enhance":[99],"training":[100],"robustness,":[101],"we":[102],"develop":[103],"uncertainty-guided":[105],"dual-stage":[106],"curriculum":[107],"learning":[108],"strategy":[109],"alleviate":[111],"adverse":[113],"effects":[114],"severe":[116],"label":[117],"noise":[118],"during":[119],"training.":[120],"Extensive":[121],"experiments":[122],"PA100K,":[125],"PETA,":[126],"RAPv1,":[127],"RAPv2":[129],"datasets":[130],"demonstrate":[131],"that":[132,143,150],"achieves":[134],"competitive":[135],"or":[136,155],"superior":[137],"performance.":[138],"Furthermore,":[139],"qualitative":[140],"results":[141],"confirm":[142],"proposed":[145],"generates":[147],"uncertainty":[148],"estimates":[149],"predictive":[152],"challenging":[154],"erroneous":[156],"samples.":[157]},"counts_by_year":[],"updated_date":"2026-05-01T06:10:29.291645","created_date":"2026-05-01T00:00:00"}