{"id":"https://openalex.org/W4415708529","doi":"https://doi.org/10.1109/icme59968.2025.11209524","title":"CLIP-based Robust Pedestrian Attribute Recognition via Attribute Localization and Data Augmentation","display_name":"CLIP-based Robust Pedestrian Attribute Recognition via Attribute Localization and Data Augmentation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708529","doi":"https://doi.org/10.1109/icme59968.2025.11209524"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209524","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/A5010833287","display_name":"Yunpeng Zhou","orcid":"https://orcid.org/0000-0002-2432-7898"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpeng Zhou","raw_affiliation_strings":["School of Information Science and Technology, Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101201286","display_name":"Qiwen Liang","orcid":"https://orcid.org/0009-0003-4844-9691"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiwen Liang","raw_affiliation_strings":["School of Information Science and Technology, Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353780","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-0041-3134"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["School of Information Science and Technology, Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102635158","display_name":"Jianping Ren","orcid":"https://orcid.org/0009-0005-8160-3675"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Ren","raw_affiliation_strings":["School of Information Science and Technology, Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liujinxiang Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujinxiang Zhu","raw_affiliation_strings":["School of Information Science and Technology, Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017815095","display_name":"Shuhua Liu","orcid":"https://orcid.org/0000-0002-8333-1045"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhua Liu","raw_affiliation_strings":["School of Information Science and Technology, Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184983240"],"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":0.4205000102519989,"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":0.4205000102519989,"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":0.4025000035762787,"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":0.10999999940395355,"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/pedestrian","display_name":"Pedestrian","score":0.7358999848365784},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5098000168800354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46810001134872437},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4230000078678131},{"id":"https://openalex.org/keywords/pedestrian-detection","display_name":"Pedestrian detection","score":0.4049000144004822},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.3885999917984009}],"concepts":[{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.7358999848365784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7325000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5806000232696533},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5098000168800354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4927000105381012},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4230000078678131},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.4049000144004822},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3808000087738037},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3634999990463257},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209524","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2111025459","https://openalex.org/W2808154247","https://openalex.org/W2898491875","https://openalex.org/W2963365374","https://openalex.org/W2963377110","https://openalex.org/W2998496429","https://openalex.org/W3112567928","https://openalex.org/W3169129566","https://openalex.org/W3187415662","https://openalex.org/W3200445214","https://openalex.org/W4281965046","https://openalex.org/W4283816693","https://openalex.org/W4285207098","https://openalex.org/W4307823382","https://openalex.org/W4312680644","https://openalex.org/W4312784228","https://openalex.org/W4360595253","https://openalex.org/W4380303606","https://openalex.org/W4385767807","https://openalex.org/W4389640337","https://openalex.org/W4393156340","https://openalex.org/W4402216993","https://openalex.org/W4402702915","https://openalex.org/W4402728455"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,19,26,42,86,101],"emergence":[2],"of":[3,37,88],"contrastive":[4],"vision-language":[5],"pre-training":[6],"(CLIP)":[7],"models,":[8],"research":[9],"on":[10,94],"pedestrian":[11,54,89],"attribute":[12,55,72,82,90],"recognition":[13,28,56],"has":[14],"achieved":[15],"great":[16],"success.":[17],"However,":[18],"high":[20],"variability":[21],"in":[22],"real-world":[23,48],"scenarios":[24],"and":[25,47,74],"low":[27],"rates":[29],"for":[30,71,81],"sparse":[31],"attributes":[32],"are":[33],"still":[34],"challenging":[35],"issues":[36],"this":[38,62],"field.":[39],"To":[40],"bridge":[41],"gap":[43],"between":[44],"powerful":[45],"models":[46],"applications,":[49],"we":[50],"propose":[51],"a":[52,65],"robust":[53],"framework,":[57],"RobustPAR.":[58],"Built":[59],"upon":[60],"CLIP,":[61],"framework":[63],"introduces":[64],"Multi-modal":[66],"Joint":[67],"Transformer":[68],"(MJT)":[69],"module":[70,80],"localization":[73],"an":[75],"Attribute":[76],"Replacement":[77],"Enhancement":[78],"(ARE)":[79],"disentanglement,":[83],"thereby":[84],"improving":[85],"performance":[87],"recognition.":[91],"Extensive":[92],"experiments":[93],"multiple":[95],"PAR":[96],"benchmark":[97],"datasets":[98],"demonstrate":[99],"that":[100],"proposed":[102],"method":[103],"outperforms":[104],"existing":[105],"approaches,":[106],"validating":[107],"its":[108],"effectiveness.":[109],"Code":[110],"is":[111],"available":[112],"at":[113],"https://github.com/ZYP771/ICME25_RobustPAR.":[114]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}