{"id":"https://openalex.org/W3161359760","doi":"https://doi.org/10.1109/icpr48806.2021.9411959","title":"Multi-label Contrastive Focal Loss for Pedestrian Attribute Recognition","display_name":"Multi-label Contrastive Focal Loss for Pedestrian Attribute Recognition","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3161359760","doi":"https://doi.org/10.1109/icpr48806.2021.9411959","mag":"3161359760"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9411959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9411959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5102988664","display_name":"Xiaoqiang Zheng","orcid":"https://orcid.org/0000-0001-5151-8561"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqiang Zheng","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100571304","display_name":"Zhenxia Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I24201400","display_name":"Chengdu University of Information Technology","ror":"https://ror.org/01yxwrh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I24201400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenxia Yu","raw_affiliation_strings":["School of computer science, Chengdu University Of Information Technology, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of computer science, Chengdu University Of Information Technology, Chengdu, China","institution_ids":["https://openalex.org/I24201400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745599","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0002-2290-1630"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["Chongqing Key Laboratory of Big Data and Intelligent Computing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing Key Laboratory of Big Data and Intelligent Computing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069879969","display_name":"Fan Zhu","orcid":"https://orcid.org/0000-0002-0279-9587"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhu","raw_affiliation_strings":["Chongqing Key Laboratory of Big Data and Intelligent Computing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing Key Laboratory of Big Data and Intelligent Computing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633957","display_name":"Shilong Wang","orcid":"https://orcid.org/0000-0002-3321-027X"},"institutions":[{"id":"https://openalex.org/I24201400","display_name":"Chengdu University of Information Technology","ror":"https://ror.org/01yxwrh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I24201400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilong Wang","raw_affiliation_strings":["School of computer science, Chengdu University Of Information Technology, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of computer science, Chengdu University Of Information Technology, Chengdu, China","institution_ids":["https://openalex.org/I24201400"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3819,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65608432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7349","last_page":"7356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991999864578247,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991999864578247,"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":0.9915000200271606,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9840999841690063,"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/discriminative-model","display_name":"Discriminative model","score":0.8577269315719604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8121728897094727},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6760781407356262},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.6503803133964539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6290004849433899},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.621307373046875},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.602892279624939},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.49650317430496216},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4876827001571655},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.43779486417770386},{"id":"https://openalex.org/keywords/pedestrian-detection","display_name":"Pedestrian detection","score":0.43701502680778503},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3391856551170349},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.067728191614151}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8577269315719604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8121728897094727},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6760781407356262},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.6503803133964539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6290004849433899},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.621307373046875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.602892279624939},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.49650317430496216},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4876827001571655},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.43779486417770386},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.43701502680778503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3391856551170349},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.067728191614151},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9411959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9411959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G4701661562","display_name":null,"funder_award_id":"61902370,61802360","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2102734144","https://openalex.org/W2111025459","https://openalex.org/W2146621071","https://openalex.org/W2150692496","https://openalex.org/W2286727787","https://openalex.org/W2308869522","https://openalex.org/W2331234693","https://openalex.org/W2410968923","https://openalex.org/W2467139031","https://openalex.org/W2555897561","https://openalex.org/W2613151562","https://openalex.org/W2624871570","https://openalex.org/W2737725206","https://openalex.org/W2739088263","https://openalex.org/W2808154247","https://openalex.org/W2867270703","https://openalex.org/W2896249043","https://openalex.org/W2898491875","https://openalex.org/W2904764169","https://openalex.org/W2905439313","https://openalex.org/W2954148997","https://openalex.org/W2962898354","https://openalex.org/W2962926870","https://openalex.org/W2963351448","https://openalex.org/W2963365374","https://openalex.org/W2963620099","https://openalex.org/W2963775347","https://openalex.org/W2963790258","https://openalex.org/W2964350391","https://openalex.org/W2965153332","https://openalex.org/W2966350035","https://openalex.org/W2986999591","https://openalex.org/W2998496429","https://openalex.org/W3026128218","https://openalex.org/W3034927684","https://openalex.org/W3035590987","https://openalex.org/W6638791942","https://openalex.org/W6694260854","https://openalex.org/W6698448323","https://openalex.org/W6719816043","https://openalex.org/W6730323794","https://openalex.org/W6739365718","https://openalex.org/W6741936186","https://openalex.org/W6752623288","https://openalex.org/W6754364688","https://openalex.org/W6776360428","https://openalex.org/W6777516870","https://openalex.org/W6777666385"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W2052835778","https://openalex.org/W2392100589","https://openalex.org/W259157601","https://openalex.org/W2972620127","https://openalex.org/W2981141433","https://openalex.org/W2751005898"],"abstract_inverted_index":{"Pedestrian":[0],"Attribute":[1],"Recognition":[2],"(PAR)":[3],"has":[4,26],"received":[5],"extensive":[6],"attention":[7],"during":[8],"the":[9,14,22,52,58,76,80,104,123,126,134,137,153,172,176],"past":[10],"few":[11],"years.":[12],"With":[13],"advances":[15],"of":[16,24,54,60,79,125,139,188],"deep":[17],"convolutional":[18],"neural":[19],"networks":[20],"(CNNs),":[21],"performance":[23],"PAR":[25],"been":[27],"significantly":[28],"improved.":[29],"Existing":[30],"methods":[31],"tend":[32],"to":[33,83,121,132,142,145,181],"acquire":[34],"attribute-specific":[35],"features":[36],"by":[37,109],"designing":[38],"various":[39],"complex":[40],"network":[41,55],"structures":[42],"with":[43,175],"additional":[44,47],"modules.":[45],"Such":[46],"modules,":[48],"however,":[49],"dramatically":[50],"increase":[51],"number":[53],"parameters.":[56],"Meanwhile,":[57],"problems":[59,87],"class":[61],"imbalance":[62],"and":[63,88,106,118,165],"hard":[64,105],"attribute":[65],"retrieving":[66],"remain":[67],"underestimated":[68],"in":[69,186],"PAR.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"explore":[75],"optimization":[77],"mechanism":[78,114],"training":[81],"processing":[82],"account":[84],"for":[85,115],"these":[86],"propose":[89],"a":[90,111],"new":[91],"loss":[92],"function":[93],"called":[94],"Multi-label":[95],"Contrastive":[96],"Focal":[97],"Loss":[98],"(MCFL).":[99],"This":[100],"proposed":[101,154,173],"MCFL":[102,128,155,174],"emphasizes":[103],"minority":[107],"attributes":[108],"using":[110],"separated":[112],"re-weighting":[113],"different":[116],"positive":[117],"negative":[119],"classes":[120],"alleviate":[122],"impact":[124],"imbalance.":[127],"is":[129,179],"also":[130],"able":[131,180],"enlarge":[133],"gaps":[135],"between":[136],"intra-class":[138],"multi-label":[140],"attributes,":[141],"force":[143],"CNNs":[144],"extract":[146],"more":[147],"subtle":[148],"discriminative":[149],"features.":[150],"We":[151],"evaluate":[152],"on":[156],"three":[157],"large":[158],"public":[159],"pedestrian":[160],"datasets,":[161],"including":[162],"RAP,":[163],"PA-100K,":[164],"PETA.":[166],"The":[167],"experimental":[168],"results":[169],"indicate":[170],"that":[171],"ResNet-50":[177],"backbone":[178],"outperform":[182],"other":[183],"state-of-the-art":[184],"approaches":[185],"term":[187],"mean":[189],"accuracy.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}