{"id":"https://openalex.org/W4387448536","doi":"https://doi.org/10.1109/tmm.2023.3321504","title":"Multi-Granularity Matching Transformer for Text-Based Person Search","display_name":"Multi-Granularity Matching Transformer for Text-Based Person Search","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4387448536","doi":"https://doi.org/10.1109/tmm.2023.3321504"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3321504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3321504","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5017398538","display_name":"Liping Bao","orcid":"https://orcid.org/0000-0003-2812-688X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liping Bao","raw_affiliation_strings":["Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050660610","display_name":"Longhui Wei","orcid":"https://orcid.org/0000-0001-6916-3009"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longhui Wei","raw_affiliation_strings":["Department of Electrical Engineering and Information Science, University of Science and Technology of China and Huawei Cloud, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Science, University of Science and Technology of China and Huawei Cloud, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707809","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0001-8406-085X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075290241","display_name":"Lingxi Xie","orcid":"https://orcid.org/0000-0003-4831-9451"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxi Xie","raw_affiliation_strings":["Huawei Cloud, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111172356","display_name":"Qi Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Huawei Cloud, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5017398538"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.6851,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86626478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"4281","last_page":"4293"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.995199978351593,"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":0.9937999844551086,"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":0.8466669321060181},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6445192694664001},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6225175857543945},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6013361215591431},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5700396299362183},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5667811036109924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5041424036026001},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.492397665977478},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4620148241519928},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4541066586971283},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41166603565216064},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4103849530220032},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4084196090698242},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3497081995010376},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3364149332046509},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.324341356754303},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.09220921993255615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8466669321060181},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6445192694664001},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6225175857543945},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6013361215591431},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5700396299362183},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5667811036109924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5041424036026001},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.492397665977478},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4620148241519928},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4541066586971283},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41166603565216064},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4103849530220032},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4084196090698242},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3497081995010376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3364149332046509},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.324341356754303},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.09220921993255615},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3321504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3321504","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G5038960961","display_name":null,"funder_award_id":"U20A20183","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6308808780","display_name":null,"funder_award_id":"62021001","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"},{"id":"https://openalex.org/F4320325599","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2138621090","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2883311563","https://openalex.org/W2885709146","https://openalex.org/W2891175865","https://openalex.org/W2894786240","https://openalex.org/W2895675617","https://openalex.org/W2896457183","https://openalex.org/W2955147859","https://openalex.org/W2963047834","https://openalex.org/W2963389687","https://openalex.org/W2963438548","https://openalex.org/W2963449390","https://openalex.org/W2963842104","https://openalex.org/W2963901085","https://openalex.org/W2981384185","https://openalex.org/W2985951359","https://openalex.org/W2996695408","https://openalex.org/W2997421053","https://openalex.org/W3005530336","https://openalex.org/W3015686580","https://openalex.org/W3024059432","https://openalex.org/W3035524453","https://openalex.org/W3090449556","https://openalex.org/W3093025987","https://openalex.org/W3093206719","https://openalex.org/W3094502228","https://openalex.org/W3095440956","https://openalex.org/W3098711604","https://openalex.org/W3105077954","https://openalex.org/W3110337799","https://openalex.org/W3120182027","https://openalex.org/W3120797281","https://openalex.org/W3154169267","https://openalex.org/W3175919531","https://openalex.org/W3184033217","https://openalex.org/W3187261085","https://openalex.org/W3189221782","https://openalex.org/W3204887981","https://openalex.org/W3206868111","https://openalex.org/W4214736485","https://openalex.org/W4283818632","https://openalex.org/W4294068600","https://openalex.org/W4297833440","https://openalex.org/W4313136445","https://openalex.org/W4321231469","https://openalex.org/W6620707391","https://openalex.org/W6757817989","https://openalex.org/W6762573206","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6776700526","https://openalex.org/W6788774013","https://openalex.org/W6789753369","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6798810632","https://openalex.org/W6802411921"],"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-based":[0],"person":[1],"search":[2],"aims":[3],"to":[4,27,40,62,99,116,127,153,163,185],"retrieve":[5],"the":[6,29,42,50,64,69,86,93,100,129,155,164],"most":[7],"relevant":[8],"pedestrian":[9],"images":[10],"from":[11],"an":[12],"image":[13,30,45,109],"gallery":[14],"based":[15],"on":[16,23,171],"textual":[17],"descriptions.":[18],"Most":[19],"existing":[20],"methods":[21,58],"rely":[22],"two":[24,114],"separate":[25],"encoders":[26],"extract":[28],"and":[31,34,46,104,136,161,173],"text":[32,47],"features,":[33],"then":[35],"elaborately":[36],"design":[37],"various":[38],"schemes":[39],"bridge":[41],"gap":[43],"between":[44,53,82],"modalities.":[48],"However,":[49],"shallow":[51],"interaction":[52,81],"both":[54,83],"modalities":[55,84],"in":[56,89,108],"these":[57,118],"is":[59,125,151],"still":[60],"insufficient":[61],"eliminate":[63],"modality":[65,94],"gap.":[66,95],"To":[67],"address":[68,128],"above":[70],"problem,":[71],"we":[72,111],"propose":[73],"TransTPS,":[74],"a":[75],"transformer-based":[76],"framework":[77,180],"that":[78,177],"enables":[79],"deeper":[80],"through":[85],"self-attention":[87],"mechanism":[88],"transformer,":[90],"effectively":[91],"alleviating":[92],"In":[96],"addition,":[97],"due":[98],"small":[101,133],"inter-class":[102,134],"variance":[103,107,135,160],"large":[105,158],"intra-class":[106,159],"modality,":[110],"further":[112],"develop":[113],"techniques":[115],"overcome":[117],"limitations.":[119],"Specifically,":[120],"Cross-modal":[121],"Multi-Granularity":[122],"Matching":[123],"(CMGM)":[124],"proposed":[126,179],"problem":[130],"caused":[131],"by":[132],"facilitate":[137],"distinguishing":[138],"pedestrians":[139],"with":[140,146],"similar":[141],"appearance.":[142],"Besides,":[143],"Contrastive":[144],"Loss":[145],"Weakly":[147],"Positive":[148],"pairs":[149],"(CLWP)":[150],"introduced":[152],"mitigate":[154],"impact":[156],"of":[157,166],"contribute":[162],"retrieval":[165],"more":[167],"target":[168],"images.":[169],"Experiments":[170],"CUHK-PEDES":[172],"RSTPReID":[174],"datasets":[175],"demonstrate":[176],"our":[178],"achieves":[181],"state-of-the-art":[182],"performance":[183],"compared":[184],"previous":[186],"methods.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
