{"id":"https://openalex.org/W4387969466","doi":"https://doi.org/10.1145/3581783.3611709","title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","display_name":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969466","doi":"https://doi.org/10.1145/3581783.3611709"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611709","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/A5001721932","display_name":"Shuyu Yang","orcid":"https://orcid.org/0000-0003-0409-1467"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuyu Yang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028344824","display_name":"Yinan Zhou","orcid":"https://orcid.org/0009-0003-2211-6688"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinan Zhou","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034162160","display_name":"Zhedong Zheng","orcid":"https://orcid.org/0000-0002-2434-9050"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhedong Zheng","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651167","display_name":"Yaxiong Wang","orcid":"https://orcid.org/0000-0001-6596-8117"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxiong Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635252","display_name":"Li Zhu","orcid":"https://orcid.org/0000-0003-2136-3196"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhu","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032565150","display_name":"Yujiao Wu","orcid":"https://orcid.org/0000-0001-6366-9834"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujiao Wu","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001721932"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":14.9247,"has_fulltext":false,"cited_by_count":125,"citation_normalized_percentile":{"value":0.99416632,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4492","last_page":"4501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9986000061035156,"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":0.9986000061035156,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9934999942779541,"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":0.9724000096321106,"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/computer-science","display_name":"Computer science","score":0.8539919853210449},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6783806085586548},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5876235365867615},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5492253303527832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.520119309425354},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5192766189575195},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5016202926635742},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4829687178134918},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4386962056159973},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4299094080924988},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41114574670791626},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32234784960746765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8539919853210449},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6783806085586548},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5876235365867615},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5492253303527832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.520119309425354},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5192766189575195},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5016202926635742},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4829687178134918},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4386962056159973},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4299094080924988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41114574670791626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32234784960746765},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611709","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":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1949591461","https://openalex.org/W1991452654","https://openalex.org/W2108598243","https://openalex.org/W2204750386","https://openalex.org/W2398118205","https://openalex.org/W2511791013","https://openalex.org/W2559085405","https://openalex.org/W2766111649","https://openalex.org/W2801814609","https://openalex.org/W2883311563","https://openalex.org/W2885709146","https://openalex.org/W2894786240","https://openalex.org/W2896457183","https://openalex.org/W2896632102","https://openalex.org/W2913623386","https://openalex.org/W2942426756","https://openalex.org/W2963488642","https://openalex.org/W2963557071","https://openalex.org/W2964194231","https://openalex.org/W2968039979","https://openalex.org/W2970416732","https://openalex.org/W2981827289","https://openalex.org/W2986999591","https://openalex.org/W2997421053","https://openalex.org/W2998508940","https://openalex.org/W3015686580","https://openalex.org/W3035682985","https://openalex.org/W3082913072","https://openalex.org/W3093025987","https://openalex.org/W3093078906","https://openalex.org/W3110264553","https://openalex.org/W3138516171","https://openalex.org/W3165835426","https://openalex.org/W3174189418","https://openalex.org/W3189221782","https://openalex.org/W3194950734","https://openalex.org/W3205256737","https://openalex.org/W4283818632","https://openalex.org/W4297833440","https://openalex.org/W4304087170","https://openalex.org/W4312933868","https://openalex.org/W4312998013","https://openalex.org/W4321231469","https://openalex.org/W4362641980","https://openalex.org/W4386076215","https://openalex.org/W4386076618","https://openalex.org/W6600553734"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W2241813887","https://openalex.org/W2405355225","https://openalex.org/W3127015870"],"abstract_inverted_index":{"In":[0,36,185],"this":[1],"paper,":[2],"we":[3,67,87],"introduce":[4],"a":[5,89,121,189,207],"large":[6],"Multi-Attribute":[7],"and":[8,18,29,52,64,95,107,120,156,196,203,214],"Language":[9],"Search":[10],"dataset":[11],"for":[12,135],"text-based":[13],"person":[14],"retrieval,":[15],"called":[16],"MALS,":[17,173],"explore":[19],"the":[20,61,69,75,79,84,102,110,132,140,150,160,167,170],"feasibility":[21,80],"of":[22,81,169,192],"performing":[23],"pre-training":[24,171],"on":[25,153,172,180,200],"both":[26],"attribute":[27,106,116,128,133,161],"recognition":[28],"image-text":[30,41],"matching":[31,123,142,147],"tasks":[32],"in":[33,157],"one":[34],"stone.":[35],"particular,":[37,186],"MALS":[38],"contains":[39,114],"1,510,330":[40],"pairs,":[42],"which":[43,138],"is":[44],"about":[45],"37.5":[46],"\u00d7":[47],"larger":[48],"than":[49],"prevailing":[50],"CUHK-PEDES,":[51,201],"all":[53],"images":[54],"are":[55,216],"annotated":[56],"with":[57],"27":[58],"attributes.":[59],"Considering":[60],"privacy":[62],"concerns":[63],"annotation":[65],"costs,":[66],"leverage":[68],"off-the-shelf":[70],"diffusion":[71],"models":[72],"to":[73],"generate":[74],"dataset.":[76],"To":[77],"verify":[78],"learning":[82,118,124,130,148,152],"from":[83],"generated":[85],"data,":[86],"develop":[88],"new":[90],"joint":[91],"Attribute":[92],"Prompt":[93],"Learning":[94,98],"Text":[96],"Matching":[97],"(APTM)":[99],"framework,":[100],"considering":[101],"shared":[103],"knowledge":[104],"between":[105],"text.":[108],"As":[109],"name":[111],"implies,":[112],"APTM":[113,179,187],"an":[115],"prompt":[117,129,162],"stream":[119],"text":[122,141,146],"stream.":[125],"(1)":[126],"The":[127,145,211],"leverages":[131],"prompts":[134],"image-attribute":[136],"alignment,":[137],"enhances":[139],"learning.":[143,163],"(2)":[144],"facilitates":[149],"representation":[151],"fine-grained":[154],"details,":[155],"turn,":[158],"boosts":[159],"Extensive":[164],"experiments":[165],"validate":[166],"effectiveness":[168],"achieving":[174],"state-of-the-art":[175],"retrieval":[176],"performance":[177],"via":[178],"three":[181],"challenging":[182],"real-world":[183],"benchmarks.":[184],"achieves":[188],"consistent":[190],"improvement":[191],"+6.96":[193],"%,":[194],"+7.68%,":[195],"+16.95%":[197],"Recall@1":[198],"accuracy":[199],"ICFG-PEDES,":[202],"RSTPReid":[204],"datasets":[205],"by":[206],"clear":[208],"margin,":[209],"respectively.":[210],"dataset,":[212],"model,":[213],"code":[215],"available":[217],"at":[218],"https://github.com/Shuyu-XJTU/APTM.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":68},{"year":2024,"cited_by_count":43},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}