{"id":"https://openalex.org/W4387969649","doi":"https://doi.org/10.1145/3581783.3611719","title":"POAR: Towards Open Vocabulary Pedestrian Attribute Recognition","display_name":"POAR: Towards Open Vocabulary Pedestrian Attribute Recognition","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969649","doi":"https://doi.org/10.1145/3581783.3611719"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611719","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5100333769","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0003-0179-1396"},"institutions":[{"id":"https://openalex.org/I75955062","display_name":"Henan Normal University","ror":"https://ror.org/00s13br28","country_code":"CN","type":"education","lineage":["https://openalex.org/I75955062"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Henan Normal University, Xinxiang, China"],"affiliations":[{"raw_affiliation_string":"Henan Normal University, Xinxiang, China","institution_ids":["https://openalex.org/I75955062"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020106541","display_name":"Suchen Wang","orcid":"https://orcid.org/0000-0002-4086-0713"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Suchen Wang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025341442","display_name":"Shichao Kan","orcid":"https://orcid.org/0000-0003-0097-6196"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shichao Kan","raw_affiliation_strings":["Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067922510","display_name":"Zhenyu Weng","orcid":"https://orcid.org/0000-0001-7857-8687"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhenyu Weng","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082462498","display_name":"Yigang Cen","orcid":"https://orcid.org/0000-0001-6255-9422"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yigang Cen","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yap-peng Tan","orcid":"https://orcid.org/0000-0002-0645-9109"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yap-peng Tan","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100333769"],"corresponding_institution_ids":["https://openalex.org/I75955062"],"apc_list":null,"apc_paid":null,"fwci":1.9202,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88891347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"655","last_page":"665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9839000105857849,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9839000105857849,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9781000018119812,"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":0.9696000218391418,"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/computer-science","display_name":"Computer science","score":0.8361615538597107},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.7299946546554565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5772958993911743},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5169869661331177},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5159974098205566},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4975784122943878},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41522416472435},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39439570903778076},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36089104413986206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8361615538597107},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.7299946546554565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5772958993911743},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5169869661331177},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5159974098205566},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4975784122943878},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41522416472435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39439570903778076},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36089104413986206},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611719","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5405212225","display_name":null,"funder_award_id":"62202499,62062021","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2111025459","https://openalex.org/W2119880843","https://openalex.org/W2410968923","https://openalex.org/W2471768434","https://openalex.org/W2560662850","https://openalex.org/W2766111649","https://openalex.org/W2798685991","https://openalex.org/W2808154247","https://openalex.org/W2904764169","https://openalex.org/W2905535961","https://openalex.org/W2963365374","https://openalex.org/W2963592586","https://openalex.org/W2973218493","https://openalex.org/W2986999591","https://openalex.org/W2997998901","https://openalex.org/W2998496429","https://openalex.org/W3033971630","https://openalex.org/W3035590987","https://openalex.org/W3106827427","https://openalex.org/W3112567928","https://openalex.org/W3184927044","https://openalex.org/W3187415662","https://openalex.org/W3200445214","https://openalex.org/W4200498145","https://openalex.org/W4214736485","https://openalex.org/W4220961760","https://openalex.org/W4229014680","https://openalex.org/W4240900090","https://openalex.org/W4283816693","https://openalex.org/W4285207098","https://openalex.org/W4300981332","https://openalex.org/W4312574495","https://openalex.org/W4312747482","https://openalex.org/W4321020060","https://openalex.org/W4360595253","https://openalex.org/W4387872955"],"related_works":["https://openalex.org/W2392100589","https://openalex.org/W2512789322","https://openalex.org/W2101960027","https://openalex.org/W2197846993","https://openalex.org/W49697837","https://openalex.org/W2586575957","https://openalex.org/W3122828758","https://openalex.org/W2170799233","https://openalex.org/W2768112316","https://openalex.org/W4205958986"],"abstract_inverted_index":{"Pedestrian":[0,50],"attribute":[1,27,98,109,139,182],"recognition":[2],"(PAR)":[3],"aims":[4],"to":[5,76,100,135,173],"predict":[6],"the":[7,17,39,57,79,102,121,127,130,137,142,175,201,211],"attributes":[8,37,80,104,148],"of":[9,62,81,97,149,203],"a":[10,22,48,60,68,72,95,114,150,155,167,207],"target":[11],"pedestrian.":[12],"Recent":[13],"methods":[14],"often":[15],"address":[16],"PAR":[18,192],"problem":[19,58],"by":[20,55,120],"training":[21],"multi-label":[23],"classifier":[24],"with":[25,71,160,194],"predefined":[26],"classes,":[28],"but":[29],"they":[30],"can":[31],"hardly":[32],"exhaust":[33],"all":[34],"possible":[35],"pedestrian":[36,83],"in":[38],"real":[40],"world.":[41],"To":[42,145],"tackle":[43],"this":[44],"problem,":[45],"we":[46,125,153,165],"propose":[47,154,166],"novel":[49],"Open-Attribute":[51],"Recognition":[52],"(POAR)":[53],"approach":[54,66],"formulating":[56],"as":[59,113,206],"task":[61],"image-text":[63],"search.":[64],"Our":[65,214],"employs":[67],"Transformer-based":[69],"Encoder":[70],"Masking":[73],"Strategy":[74],"(TEMS)":[75],"focus":[77],"on":[78,190],"specific":[82],"parts":[84],"(e.g.,":[85],"head,":[86],"upper":[87],"body,":[88,90],"lower":[89],"feet,":[91],"etc.),":[92],"and":[93,118,132,180],"introduces":[94],"set":[96],"tokens":[99],"encode":[101],"corresponding":[103],"into":[105],"visual":[106,131,178],"embeddings.":[107,184],"Each":[108],"category":[110],"is":[111,216],"described":[112],"natural":[115],"language":[116],"sentence":[117],"encoded":[119],"text":[122,133,183],"encoder.":[123],"Then,":[124],"compute":[126],"similarity":[128],"between":[129,177],"embeddings":[134,179],"find":[136],"best":[138],"descriptions":[140],"for":[141,210],"input":[143],"images.":[144],"handle":[146],"multiple":[147],"single":[151],"pedestrian,":[152],"Many-To-Many":[156],"Contrastive":[157],"(MTMC)":[158],"loss":[159],"masked":[161],"tokens.":[162],"In":[163],"addition,":[164],"Grouped":[168],"Knowledge":[169],"Distillation":[170],"(GKD)":[171],"method":[172,189,205],"minimize":[174],"disparity":[176],"unseen":[181],"We":[185],"evaluate":[186],"our":[187,204],"proposed":[188],"three":[191],"datasets":[193],"an":[195],"open-attribute":[196],"setting.":[197],"The":[198],"results":[199],"demonstrate":[200],"effectiveness":[202],"strong":[208],"baseline":[209],"POAR":[212],"task.":[213],"code":[215],"available":[217],"at":[218],"https://github.com/IvyYZ/POAR.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}