{"id":"https://openalex.org/W4402753821","doi":"https://doi.org/10.1109/cvpr52733.2024.01621","title":"Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID","display_name":"Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402753821","doi":"https://doi.org/10.1109/cvpr52733.2024.01621"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060463460","display_name":"Wentao Tan","orcid":"https://orcid.org/0000-0001-5907-1581"},"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":"Wentao Tan","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002479852","display_name":"Jiayu Jiang","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":false,"raw_author_name":"Jiayu Jiang","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695181","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0001-5768-7323"},"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":"Fei Wang","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074672983","display_name":"Yibing Zhan","orcid":"https://orcid.org/0000-0003-3180-0484"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibing Zhan","raw_affiliation_strings":["JD Explore Academy,Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy,Beijing","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067600725","display_name":"Dapeng Tao","orcid":"https://orcid.org/0000-0003-0783-5273"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Tao","raw_affiliation_strings":["Yunnan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan University","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.9086,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.99522886,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"17127","last_page":"17137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9879000186920166,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9782000184059143,"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/image","display_name":"Image (mathematics)","score":0.6438236832618713},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.6145641207695007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.561173677444458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3689308762550354},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3562517762184143},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09368154406547546}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6438236832618713},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.6145641207695007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.561173677444458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3689308762550354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3562517762184143},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09368154406547546},{"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/cvpr52733.2024.01621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":95,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2480418144","https://openalex.org/W2801814609","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2896457183","https://openalex.org/W2962964995","https://openalex.org/W2963389687","https://openalex.org/W2963449390","https://openalex.org/W2985951359","https://openalex.org/W2997421053","https://openalex.org/W3015686580","https://openalex.org/W3024059432","https://openalex.org/W3087658752","https://openalex.org/W3095440956","https://openalex.org/W3111484680","https://openalex.org/W3117117673","https://openalex.org/W3120182027","https://openalex.org/W3163938969","https://openalex.org/W3165835426","https://openalex.org/W3166396011","https://openalex.org/W3175445198","https://openalex.org/W3184033217","https://openalex.org/W3184735396","https://openalex.org/W3194199634","https://openalex.org/W3204887981","https://openalex.org/W3205168784","https://openalex.org/W3206868111","https://openalex.org/W4200633094","https://openalex.org/W4224308101","https://openalex.org/W4225323055","https://openalex.org/W4226182655","https://openalex.org/W4280538209","https://openalex.org/W4283818632","https://openalex.org/W4292779060","https://openalex.org/W4297821751","https://openalex.org/W4297833440","https://openalex.org/W4304087170","https://openalex.org/W4306705078","https://openalex.org/W4312933868","https://openalex.org/W4318718936","https://openalex.org/W4320005661","https://openalex.org/W4320458302","https://openalex.org/W4321231469","https://openalex.org/W4322627096","https://openalex.org/W4322718191","https://openalex.org/W4322730934","https://openalex.org/W4362515116","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4379742452","https://openalex.org/W4380353763","https://openalex.org/W4382132560","https://openalex.org/W4382491206","https://openalex.org/W4384918448","https://openalex.org/W4385764787","https://openalex.org/W4386065462","https://openalex.org/W4386066088","https://openalex.org/W4386076131","https://openalex.org/W4386555501","https://openalex.org/W4386758381","https://openalex.org/W4386942538","https://openalex.org/W4387968073","https://openalex.org/W4387969466","https://openalex.org/W4390874394","https://openalex.org/W4396681775","https://openalex.org/W6755207826","https://openalex.org/W6761764063","https://openalex.org/W6764281047","https://openalex.org/W6771067870","https://openalex.org/W6777275738","https://openalex.org/W6778883912","https://openalex.org/W6788774013","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6798810632","https://openalex.org/W6801549958","https://openalex.org/W6802411921","https://openalex.org/W6810081322","https://openalex.org/W6810334672","https://openalex.org/W6811013733","https://openalex.org/W6845839425","https://openalex.org/W6849177959","https://openalex.org/W6850096897","https://openalex.org/W6850204008","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6852874933","https://openalex.org/W6852989508","https://openalex.org/W6854262950","https://openalex.org/W6854866820","https://openalex.org/W6855594702","https://openalex.org/W6856398428","https://openalex.org/W6881141306"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Text-to-image":[0],"person":[1],"re-identification":[2],"(ReID)":[3],"retrieves":[4],"pedestrian":[5],"images":[6,114],"according":[7,115],"to":[8,55,89,98,112,116],"textual":[9,13,83,142,208],"descriptions.":[10,84,143,150,209],"Manually":[11],"annotating":[12],"descriptions":[14,91],"is":[15,173],"time-consuming,":[16],"restricting":[17],"the":[18,25,36,81,96,169,176,187,199,204,219,227,237],"scale":[19],"of":[20,28,206],"existing":[21],"datasets":[22,57],"and":[23,51,74,181],"therefore":[24],"generalization":[26],"ability":[27],"ReID":[29,39,223],"models.":[30],"As":[31],"a":[32,44,106,124,128,137,154,162,195],"result,":[33],"we":[34,42,72,104,134,152,190,231],"study":[35],"transferable":[37],"text-to-image":[38,222],"problem,":[40],"where":[41],"train":[43],"model":[45,97,229],"on":[46,175],"our":[47,215],"proposed":[48],"large-scale":[49,138],"database":[50],"directly":[52],"deploy":[53],"it":[54],"various":[56,117],"for":[58],"evaluation.":[59],"We":[60],"obtain":[61],"substantial":[62],"training":[63,201],"data":[64],"via":[65],"Multi-modal":[66],"Large":[67,129],"Language":[68,130],"Models":[69],"(MLLMs).":[70],"Moreover,":[71],"identify":[73],"address":[75],"two":[76],"key":[77],"challenges":[78],"in":[79,161,186,198,236],"utilizing":[80],"obtained":[82,122],"First,":[85],"an":[86,145],"MLLM":[87,146],"tends":[88],"generate":[90],"with":[92,127,140,168,194],"similar":[93],"structures,":[94],"causing":[95],"overfit":[99],"specific":[100],"sentence":[101],"patterns.":[102],"Thus,":[103],"propose":[105],"novel":[107,155],"method":[108,156,172],"that":[109,157,164,214],"uses":[110],"MLLMs":[111],"caption":[113],"templates.":[118],"These":[119],"templates":[120],"are":[121],"using":[123],"multi-turn":[125],"dialogue":[126],"Model":[131],"(LLM).":[132],"Therefore,":[133],"can":[135],"build":[136],"dataset":[139],"diverse":[141],"Second,":[144],"may":[147],"produce":[148],"incorrect":[149],"Hence,":[151],"introduce":[153],"automatically":[158],"identifies":[159],"words":[160,193],"description":[163],"do":[165],"not":[166],"correspond":[167],"image.":[170,188],"This":[171],"based":[174],"similarity":[177],"between":[178],"one":[179],"text":[180],"all":[182],"patch":[183],"token":[184],"embeddings":[185],"Then,":[189],"mask":[191],"these":[192],"larger":[196],"probability":[197],"subsequent":[200],"epoch,":[202],"alleviating":[203],"impact":[205],"noisy":[207],"The":[210],"experimental":[211],"results":[212],"demonstrate":[213],"methods":[216],"significantly":[217],"boost":[218],"direct":[220],"transfer":[221],"performance.":[224],"Benefiting":[225],"from":[226],"pre-trained":[228],"weights,":[230],"also":[232],"achieve":[233],"state-of-the-art":[234],"performance":[235],"traditional":[238],"evaluation":[239],"settings.https://github.com/WentaoTan/MLLM4Text-ReID":[240]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":5}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}