{"id":"https://openalex.org/W4415708433","doi":"https://doi.org/10.1109/icme59968.2025.11210027","title":"FOCUS: Fine-grained Optimization with Semantic Guided Understanding for Pedestrian Attributes Recognition","display_name":"FOCUS: Fine-grained Optimization with Semantic Guided Understanding for Pedestrian Attributes Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708433","doi":"https://doi.org/10.1109/icme59968.2025.11210027"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210027","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012249897","display_name":"Hongyan An","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyan An","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027279261","display_name":"Kuan Zhu","orcid":"https://orcid.org/0000-0002-1670-944X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuan Zhu","raw_affiliation_strings":["Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102751274","display_name":"Xin He","orcid":"https://orcid.org/0000-0001-8229-8143"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin He","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085707125","display_name":"Haiyun Guo","orcid":"https://orcid.org/0000-0001-9241-6211"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyun Guo","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102990950","display_name":"Chaoyang Zhao","orcid":"https://orcid.org/0000-0002-0341-0166"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoyang Zhao","raw_affiliation_strings":["Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100782002","display_name":"Ming Tang","orcid":"https://orcid.org/0000-0001-8669-4186"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Tang","raw_affiliation_strings":["Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111918240","display_name":"Jinqiao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiao Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]}]}],"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":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6765999794006348,"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":0.6765999794006348,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08709999918937683,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.05400000140070915,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6237000226974487},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5728999972343445},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.567799985408783},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5648000240325928},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5379999876022339},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4471000134944916},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.4471000134944916},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.39250001311302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997999787330627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6614000201225281},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6237000226974487},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5728999972343445},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.567799985408783},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5648000240325928},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5379999876022339},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48429998755455017},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210027","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322857","display_name":"Aeronautical Science Foundation of China","ror":"https://ror.org/02wq41p38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2111025459","https://openalex.org/W2896249043","https://openalex.org/W2963365374","https://openalex.org/W3155080005","https://openalex.org/W3184927044","https://openalex.org/W3198377975","https://openalex.org/W3200445214","https://openalex.org/W4220906215","https://openalex.org/W4226074212","https://openalex.org/W4283075695","https://openalex.org/W4283816693","https://openalex.org/W4285207098","https://openalex.org/W4303647578","https://openalex.org/W4312532537","https://openalex.org/W4312680644","https://openalex.org/W4377235190","https://openalex.org/W4386158713","https://openalex.org/W4387969649","https://openalex.org/W4393156340","https://openalex.org/W4402216993"],"related_works":[],"abstract_inverted_index":{"Pedestrian":[0],"attribute":[1,29,115,175],"recognition":[2],"(PAR)":[3],"is":[4,35],"a":[5,32,40,182,199],"fundamental":[6],"perception":[7],"task":[8],"in":[9,46,55,69,87],"intelligent":[10],"transportation":[11],"and":[12,53,221,227],"security.":[13],"To":[14,185],"tackle":[15],"this":[16,92],"fine-grained":[17,63,110],"task,":[18],"most":[19],"existing":[20],"methods":[21],"focus":[22,190],"on":[23,191,218],"extracting":[24],"regional":[25,33],"features":[26,60,80,112,139,176],"to":[27,38,66,83,136,170,211],"enrich":[28],"information.":[30,153],"However,":[31],"feature":[34],"typically":[36],"used":[37],"predict":[39,84],"fixed":[41],"set":[42],"of":[43,71,118,143,150,231],"pre-defined":[44],"attributes":[45,68,86,121,167,189,206],"these":[47],"methods,":[48],"which":[49,107,164],"limits":[50],"the":[51,88,96,120,131,148,151,157,178,192,208,225],"performance":[52],"practicality":[54],"two":[56],"aspects:":[57],"1)":[58],"Regional":[59,79],"may":[61],"compromise":[62],"patterns":[64],"unique":[65],"certain":[67],"favor":[70],"capturing":[72],"common":[73],"characteristics":[74],"shared":[75],"across":[76],"attributes.":[77],"2)":[78],"cannot":[81],"generalize":[82],"unseen":[85],"test":[89],"time.":[90],"In":[91],"paper,":[93],"we":[94,129,155,196],"propose":[95,130],"Fine-grained":[97],"Optimization":[98],"with":[99],"semantiC":[100],"gUided":[101],"underStanding":[102],"(FOCUS)":[103],"approach":[104],"for":[105,113],"PAR,":[106],"adaptively":[108],"extracts":[109],"attribute-level":[111],"each":[114],"individually,":[116],"regardless":[117],"whether":[119],"are":[122],"seen":[123],"or":[124],"not":[125],"during":[126],"training.":[127],"Specifically,":[128],"Multi-Granularity":[132],"Mix":[133,179,194],"Tokens":[134,180],"(MGMT)":[135],"capture":[137],"latent":[138],"at":[140],"varying":[141],"levels":[142],"visual":[144,174],"granularity,":[145],"thereby":[146],"enriching":[147],"diversity":[149],"extracted":[152],"Next,":[154],"introduce":[156],"Attribute-guided":[158],"Visual":[159],"Feature":[160],"Extraction":[161],"(AVFE)":[162],"module,":[163],"leverages":[165],"textual":[166,188],"as":[168],"queries":[169],"retrieve":[171],"their":[172],"corresponding":[173],"from":[177],"using":[181],"cross-attention":[183],"mechanism.":[184],"ensure":[186],"that":[187],"appropriate":[193],"Tokens,":[195],"further":[197],"incorporate":[198],"Region-Aware":[200],"Contrastive":[201],"Learning":[202],"(RACL)":[203],"method,":[204],"encouraging":[205],"within":[207],"same":[209],"region":[210],"share":[212],"consistent":[213],"attention":[214],"maps.":[215],"Extensive":[216],"experiments":[217],"PA100K,":[219],"PETA,":[220],"RAPv1":[222],"datasets":[223],"demonstrate":[224],"effectiveness":[226],"strong":[228],"generalization":[229],"ability":[230],"our":[232],"method.":[233]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}