{"id":"https://openalex.org/W4403428260","doi":"https://doi.org/10.1145/3686160","title":"Text-and-Image Learning Transformer for Cross-Modal Person Re-Identification","display_name":"Text-and-Image Learning Transformer for Cross-Modal Person Re-Identification","publication_year":2024,"publication_date":"2024-10-15","ids":{"openalex":"https://openalex.org/W4403428260","doi":"https://doi.org/10.1145/3686160"},"language":"en","primary_location":{"id":"doi:10.1145/3686160","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686160","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3686160","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3686160","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101531827","display_name":"Tinghui Wu","orcid":"https://orcid.org/0009-0007-0144-6169"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tinghui Wu","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China","School of Electronics and Information Technology, China"],"raw_orcid":"https://orcid.org/0009-0007-0144-6169","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115600535","display_name":"Shuhe Zhang","orcid":"https://orcid.org/0000-0002-4502-0000"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhe Zhang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China","School of Electronics and Information Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-4502-0000","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071453879","display_name":"Dihu Chen","orcid":"https://orcid.org/0000-0001-5432-8149"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dihu Chen","raw_affiliation_strings":["School of Integrated Circuits, Sun Yat-Sen University, Shenzhen, China","School of Integrated Circuits, China"],"raw_orcid":"https://orcid.org/0000-0001-5432-8149","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Sun Yat-Sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Integrated Circuits, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056953478","display_name":"Haifeng Hu","orcid":"https://orcid.org/0000-0002-4884-323X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Hu","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China","School of Electronics and Information Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-4884-323X","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101531827"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.4507,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63767833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"21","issue":"1","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"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":0.9998999834060669,"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/T11448","display_name":"Face recognition and analysis","score":0.9973000288009644,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8601086735725403},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6381872296333313},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6283053755760193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4967523217201233},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42204561829566956},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.41869205236434937},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4084415137767792},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3717349171638489},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3649548292160034},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.15074422955513},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11239966750144958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8601086735725403},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6381872296333313},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6283053755760193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4967523217201233},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42204561829566956},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41869205236434937},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4084415137767792},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3717349171638489},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3649548292160034},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15074422955513},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11239966750144958},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3686160","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686160","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3686160","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3686160","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686160","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3686160","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403428260.pdf"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2511791013","https://openalex.org/W2883311563","https://openalex.org/W2889564963","https://openalex.org/W2896575354","https://openalex.org/W2912338293","https://openalex.org/W2914911817","https://openalex.org/W2962784628","https://openalex.org/W2969301371","https://openalex.org/W2997421053","https://openalex.org/W2998792609","https://openalex.org/W3015686580","https://openalex.org/W3082913072","https://openalex.org/W3089552914","https://openalex.org/W3091766168","https://openalex.org/W3092072146","https://openalex.org/W3094502228","https://openalex.org/W3098711604","https://openalex.org/W3119679835","https://openalex.org/W3125736290","https://openalex.org/W3128690020","https://openalex.org/W3157986864","https://openalex.org/W3165835426","https://openalex.org/W3166274350","https://openalex.org/W3173902027","https://openalex.org/W3184033217","https://openalex.org/W3201519611","https://openalex.org/W3205168784","https://openalex.org/W3206868111","https://openalex.org/W3209337301","https://openalex.org/W3210554596","https://openalex.org/W3213189520","https://openalex.org/W4200633094","https://openalex.org/W4205659497","https://openalex.org/W4206903995","https://openalex.org/W4214540501","https://openalex.org/W4226002554","https://openalex.org/W4226445047","https://openalex.org/W4249142012","https://openalex.org/W4251372957","https://openalex.org/W4253243846","https://openalex.org/W4283818632","https://openalex.org/W4289766616","https://openalex.org/W4295677973","https://openalex.org/W4295754656","https://openalex.org/W4297821751","https://openalex.org/W4297833440","https://openalex.org/W4298046825","https://openalex.org/W4304087170","https://openalex.org/W4312356172","https://openalex.org/W4312359729","https://openalex.org/W4312475827","https://openalex.org/W4323824385","https://openalex.org/W4367314371","https://openalex.org/W4376653864","https://openalex.org/W4382460786","https://openalex.org/W4385764787","https://openalex.org/W4386758381","https://openalex.org/W4388145471","https://openalex.org/W4388430673","https://openalex.org/W4388660550","https://openalex.org/W4389331836","https://openalex.org/W4389934400"],"related_works":["https://openalex.org/W2898732673","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W2410053581","https://openalex.org/W613940353","https://openalex.org/W2383658677","https://openalex.org/W3123203398","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099"],"abstract_inverted_index":{"Text-based":[0],"person":[1,8],"re-identification":[2],"aims":[3],"to":[4,50,64,82,108,134,162,184],"find":[5],"the":[6,15,38,48,60,65,88,96,103,110,130,155,164,169,186],"target":[7],"from":[9,91],"a":[10,32,76,150],"large":[11],"pedestrian":[12],"gallery":[13],"with":[14,114,121],"given":[16],"natural":[17],"language":[18],"description.":[19],"Previous":[20],"works":[21],"mainly":[22],"focus":[23],"on":[24,95,176,200],"embedding":[25,106],"salient":[26],"textual":[27,84],"and":[28,86,117,144,167,182],"visual":[29],"representations":[30],"in":[31,124,149],"common":[33,151],"latent":[34],"space":[35],"by":[36,140],"utilizing":[37],"dual-path":[39],"structure":[40],"or":[41],"parameter-shared":[42],"network.":[43],"However,":[44],"they":[45],"still":[46],"lack":[47],"ability":[49],"effectively":[51],"extract":[52],"fine-grained":[53,119],"unimodal":[54,111],"features":[55,120],"as":[56,58],"well":[57],"fuse":[59,145],"cross-modal":[61,89,131,138,156],"data,":[62],"leading":[63],"increase":[66],"of":[67,188],"misaligned":[68],"cases.":[69],"To":[70],"settle":[71],"these":[72],"issues,":[73],"we":[74,101,128],"propose":[75],"text-and-image":[77],"implicit":[78,137],"learning":[79],"Transformer":[80],"(TILT)":[81],"eliminate":[83],"anisotropy":[85,112],"enhance":[87],"alignment":[90],"both":[92],"domains":[93],"based":[94],"bi-direction":[97],"multi-modal":[98,105,147],"encoders.":[99],"Specifically,":[100],"apply":[102],"pre-trained":[104],"module":[107,159],"overcome":[109],"problem":[113],"contrastive":[115],"learning,":[116],"map":[118],"dual":[122],"encoder":[123,133],"bi-directional":[125],"masking.":[126],"Then,":[127],"design":[129],"interaction":[132],"comprehensively":[135],"mine":[136],"relations":[139],"reconstructing":[141],"masked":[142],"tokens,":[143],"rich":[146],"knowledge":[148],"space.":[152],"In":[153],"addition,":[154],"similarity":[157],"matching":[158],"is":[160],"proposed":[161,190],"optimize":[163],"intra-domain":[165],"classification":[166],"decrease":[168],"inter-domain":[170],"divergence.":[171],"Extensive":[172],"experiments":[173],"are":[174],"conducted":[175],"three":[177],"public":[178],"benchmarks":[179],"CUHK-PEDES,":[180],"ICFG-PEDES,":[181],"RSTPReid":[183],"verify":[185],"effectiveness":[187],"our":[189,195],"framework.":[191],"Results":[192],"prove":[193],"that":[194],"model":[196],"outperforms":[197],"state-of-the-art":[198],"methods":[199],"all":[201],"metrics.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}