{"id":"https://openalex.org/W7138165535","doi":"https://doi.org/10.1609/aaai.v40i10.37775","title":"Image-Text Knowledge Modeling for Unsupervised Multi-Scenario Person Re-Identification","display_name":"Image-Text Knowledge Modeling for Unsupervised Multi-Scenario Person Re-Identification","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138165535","doi":"https://doi.org/10.1609/aaai.v40i10.37775"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i10.37775","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37775","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37775/41737","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37775/41737","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011350783","display_name":"Zhiqi Pang","orcid":"https://orcid.org/0000-0003-0940-3351"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqi Pang","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129704217","display_name":"Lingling Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingling Zhao","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129734632","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-5553-3646"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129740465","display_name":"Chunyu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Wang","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129692451","display_name":"Gaurav Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Sharma","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Rochester, Rochester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41096866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"8269","last_page":"8277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.7304999828338623,"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":0.7304999828338623,"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":0.06759999692440033,"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":0.03739999979734421,"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/leverage","display_name":"Leverage (statistics)","score":0.6171000003814697},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5418999791145325},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5367000102996826},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5307999849319458},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5065000057220459},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4966000020503998},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4767000079154968},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.4765999913215637},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.43549999594688416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764999866485596},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763000249862671},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5307999849319458},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.43549999594688416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4113999903202057},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.382099986076355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3352000117301941},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3312999904155731},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.2842999994754791},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.25519999861717224},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i10.37775","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37775","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37775/41737","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37775","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37775","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37775","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37775/41737","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G164923050","display_name":null,"funder_award_id":"2023YFC3305003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5798893398","display_name":null,"funder_award_id":"62231013","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138165535.pdf","grobid_xml":"https://content.openalex.org/works/W7138165535.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,49],"propose":[1,154],"unsupervised":[2],"multi-scenario":[3,108],"(UMS)":[4],"person":[5],"re-identification":[6],"(ReID)":[7],"as":[8],"a":[9,23,37,52,61,69,92,107,138,155],"new":[10],"task":[11],"that":[12,40],"expands":[13],"ReID":[14],"across":[15,172],"diverse":[16],"scenarios":[17,174],"(cross-resolution,":[18],"clothing":[19],"change,":[20],"etc.)":[21],"within":[22,149],"single":[24],"coherent":[25],"framework.":[26],"To":[27],"tackle":[28],"UMS-ReID,":[29],"we":[30,67,90,122,153],"introduce":[31,68,106,124],"image-text":[32],"knowledge":[33,83,196],"modeling":[34],"(ITKM)":[35],"--":[36],"three-stage":[38],"framework":[39],"effectively":[41],"exploits":[42],"the":[43,73,78,113,146,176],"representational":[44],"power":[45],"of":[46,94,145,180],"vision-language":[47],"models.":[48],"start":[50],"with":[51,56,100],"pre-trained":[53],"CLIP":[54],"model":[55],"an":[57,142],"image":[58,74,140,144,167],"encoder":[59,75,79],"and":[60,76,105,126,141,166,178],"text":[62,96,117,157,165],"encoder.":[63],"In":[64,87,119],"Stage":[65,88,103,120],"I,":[66],"scenario":[70],"embedding":[71],"in":[72],"fine-tune":[77],"to":[80,98,111,131,161],"adaptively":[81],"leverage":[82],"from":[84,102,197],"multiple":[85,173,198],"scenarios.":[86,199],"II,":[89],"optimize":[91],"set":[93],"learned":[95],"embeddings":[97],"associate":[99],"pseudo-labels":[101],"I":[104],"separation":[109],"loss":[110],"increase":[112],"divergence":[114],"between":[115,164],"inter-scenario":[116],"representations.":[118],"III,":[121],"first":[123],"cluster-level":[125],"instance-level":[127],"heterogeneous":[128,134],"matching":[129],"modules":[130],"obtain":[132],"reliable":[133],"positive":[135],"pairs":[136],"(e.g.,":[137],"visible":[139],"infrared":[143],"same":[147],"person)":[148],"each":[150],"scenario.":[151],"Next,":[152],"dynamic":[156],"representation":[158],"update":[159],"strategy":[160],"maintain":[162],"consistency":[163],"supervision":[168],"signals.":[169],"Experimental":[170],"results":[171],"demonstrate":[175],"superiority":[177],"generalizability":[179],"ITKM;":[181],"it":[182],"not":[183],"only":[184],"outperforms":[185],"existing":[186],"scenario-specific":[187],"methods":[188],"but":[189],"also":[190],"enhances":[191],"overall":[192],"performance":[193],"by":[194],"integrating":[195]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}