{"id":"https://openalex.org/W4304087170","doi":"https://doi.org/10.1145/3503161.3548028","title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification","display_name":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304087170","doi":"https://doi.org/10.1145/3503161.3548028"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548028","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548028","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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/A5040122296","display_name":"Zhiyin Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyin Shao","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390693","display_name":"Xinyu Zhang","orcid":"https://orcid.org/0000-0002-2999-3291"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":["Baidu VIS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu VIS, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400486","display_name":"Meng Fang","orcid":"https://orcid.org/0000-0001-6745-286X"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Meng Fang","raw_affiliation_strings":["University of Liverpool, Liverpool, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Liverpool, Liverpool, United Kingdom","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664594","display_name":"Zhifeng Lin","orcid":"https://orcid.org/0000-0002-4597-4322"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Lin","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696824","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-4316-932X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["Baidu VIS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu VIS, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038748720","display_name":"Changxing Ding","orcid":"https://orcid.org/0000-0001-7232-3181"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changxing Ding","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040122296"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":9.1988,"has_fulltext":false,"cited_by_count":166,"citation_normalized_percentile":{"value":0.98353442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5566","last_page":"5574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9950000047683716,"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":0.9890999794006348,"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/granularity","display_name":"Granularity","score":0.885454535484314},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7473804950714111},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7418607473373413},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6607222557067871},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.6443358659744263},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5794371366500854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5474104285240173},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5447931289672852},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49971675872802734},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37696442008018494},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36375701427459717},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35792404413223267},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34143537282943726},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10609626770019531}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.885454535484314},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473804950714111},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7418607473373413},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6607222557067871},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.6443358659744263},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5794371366500854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5474104285240173},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5447931289672852},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49971675872802734},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37696442008018494},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36375701427459717},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35792404413223267},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34143537282943726},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10609626770019531},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548028","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548028","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2563212024","https://openalex.org/W2724213014","https://openalex.org/W2795758732","https://openalex.org/W2798775284","https://openalex.org/W2801814609","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2962964995","https://openalex.org/W2963047834","https://openalex.org/W2963449390","https://openalex.org/W2963842104","https://openalex.org/W2963882743","https://openalex.org/W2981851019","https://openalex.org/W2985951359","https://openalex.org/W2988964414","https://openalex.org/W2997421053","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3015686580","https://openalex.org/W3024059432","https://openalex.org/W3087359593","https://openalex.org/W3087658752","https://openalex.org/W3090449556","https://openalex.org/W3093025987","https://openalex.org/W3093206719","https://openalex.org/W3095440956","https://openalex.org/W3096609285","https://openalex.org/W3100506510","https://openalex.org/W3100927979","https://openalex.org/W3133793254","https://openalex.org/W3184784418","https://openalex.org/W3189221782","https://openalex.org/W3194199634","https://openalex.org/W3204887981","https://openalex.org/W4225706465"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Text-to-image":[0],"person":[1],"re-identification":[2],"(ReID)":[3],"aims":[4],"to":[5,21,75,107,121,142,162],"search":[6],"for":[7,59,79,169],"pedestrian":[8],"images":[9],"of":[10,111,146,154],"an":[11,69],"interested":[12],"identity":[13],"via":[14],"textual":[15,51,126],"descriptions.":[16],"It":[17],"is":[18,56],"challenging":[19],"due":[20],"both":[22,80,123,170,196],"rich":[23],"intra-modal":[24],"variations":[25],"and":[26,96,125,138,156,165,198],"significant":[27],"inter-modal":[28,62],"gaps.":[29,63],"Existing":[30],"works":[31],"usually":[32,48],"ignore":[33],"the":[34,40,44,60,109,135,139,144,160,173,180],"difference":[35],"in":[36,105,172],"feature":[37,175],"granularity":[38],"between":[39],"two":[41,88,112,131],"modalities,":[42,81,113],"i.e.,":[43,134],"visual":[45,124],"features":[46,52,168],"are":[47,53],"fine-grained":[49],"while":[50],"coarse,":[54],"which":[55,177],"mainly":[57],"responsible":[58],"large":[61,193],"In":[64,103,148],"this":[65],"paper,":[66],"we":[67,114,150],"propose":[68],"end-to-end":[70],"framework":[71,86],"based":[72],"on":[73,195],"transformers":[74],"learn":[76],"granularity-unified":[77,174],"representations":[78],"denoted":[82],"as":[83,159],"LGUR.":[84],"LGUR":[85,188],"contains":[87],"modules:":[89],"a":[90,97,116,152],"Dictionary-based":[91],"Granularity":[92,99],"Alignment":[93],"(DGA)":[94],"module":[95],"Prototype-based":[98],"Unification":[100],"(PGU)":[101],"module.":[102],"DGA,":[104],"order":[106],"align":[108],"granularities":[110],"introduce":[115],"Multi-modality":[117],"Shared":[118],"Dictionary":[119],"(MSD)":[120],"reconstruct":[122],"features.":[127],"Besides,":[128],"DGA":[129],"has":[130],"important":[132],"factors,":[133],"cross-modality":[136],"guidance":[137],"foreground-centric":[140],"reconstruction,":[141],"facilitate":[143],"optimization":[145],"MSD.":[147],"PGU,":[149],"adopt":[151],"set":[153],"shared":[155],"learnable":[157],"prototypes":[158],"queries":[161],"extract":[163],"diverse":[164],"semantically":[166],"aligned":[167],"modalities":[171],"space,":[176],"further":[178],"promotes":[179],"ReID":[181],"performance.":[182],"Comprehensive":[183],"experiments":[184],"show":[185],"that":[186],"our":[187],"consistently":[189],"outperforms":[190],"state-of-the-arts":[191],"by":[192],"margins":[194],"CUHK-PEDES":[197],"ICFG-PEDES":[199],"datasets.":[200],"Code":[201],"will":[202],"be":[203],"released":[204],"at":[205],"https://github.com/ZhiyinShao-H/LGUR.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":70},{"year":2024,"cited_by_count":56},{"year":2023,"cited_by_count":28}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}