{"id":"https://openalex.org/W4403863334","doi":"https://doi.org/10.1109/tcsvt.2024.3487908","title":"Cross-Modal Uncertainty Modeling With Diffusion-Based Refinement for Text-Based Person Retrieval","display_name":"Cross-Modal Uncertainty Modeling With Diffusion-Based Refinement for Text-Based Person Retrieval","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4403863334","doi":"https://doi.org/10.1109/tcsvt.2024.3487908"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3487908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3487908","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5043867916","display_name":"Shenshen Li","orcid":"https://orcid.org/0000-0002-6340-012X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenshen Li","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-6340-012X","affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5685-3123","affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043065700","display_name":"Chen He","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen He","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074492050","display_name":"Fumin Shen","orcid":"https://orcid.org/0000-0001-7303-3231"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fumin Shen","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-7303-3231","affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5070-4511","affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.635,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8520625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"35","issue":"3","first_page":"2881","last_page":"2893"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9736999869346619,"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":0.9736999869346619,"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/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.9236000180244446,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6906458735466003},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5049365162849426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4144342839717865},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4112267792224884},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3809244632720947},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33255845308303833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6906458735466003},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5049365162849426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4144342839717865},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4112267792224884},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3809244632720947},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33255845308303833},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3487908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3487908","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4510122299","display_name":"\u9762\u5411\u81ea\u7136\u8bed\u53e5\u67e5\u8be2\u7684\u591a\u6a21\u6001\u6570\u636e\u68c0\u7d22\u7814\u7a76","funder_award_id":"62072080","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5347999826","display_name":null,"funder_award_id":"62222203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5987255547","display_name":null,"funder_award_id":"2023-XT00-00001-GX","funder_id":"https://openalex.org/F4320336756","funder_display_name":"Tianjin Science and Technology Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336756","display_name":"Tianjin Science and Technology Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W2134670261","https://openalex.org/W2135442311","https://openalex.org/W2591669147","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2963127401","https://openalex.org/W2963449390","https://openalex.org/W2985951359","https://openalex.org/W3035376925","https://openalex.org/W3035402405","https://openalex.org/W3092346218","https://openalex.org/W3095440956","https://openalex.org/W3097580349","https://openalex.org/W3111984153","https://openalex.org/W3138516171","https://openalex.org/W3168433561","https://openalex.org/W3205032456","https://openalex.org/W3206868111","https://openalex.org/W4283818632","https://openalex.org/W4297821751","https://openalex.org/W4297833440","https://openalex.org/W4304087170","https://openalex.org/W4312388283","https://openalex.org/W4312998013","https://openalex.org/W4322730934","https://openalex.org/W4361801760","https://openalex.org/W4385245566","https://openalex.org/W4385764787","https://openalex.org/W4386038408","https://openalex.org/W4386065462","https://openalex.org/W4386758381","https://openalex.org/W4387968073","https://openalex.org/W4387968135","https://openalex.org/W4387968696","https://openalex.org/W4387969466","https://openalex.org/W4390190636","https://openalex.org/W4390874394","https://openalex.org/W4393148792","https://openalex.org/W4393241214","https://openalex.org/W4395027807","https://openalex.org/W4405521305","https://openalex.org/W6631190155","https://openalex.org/W6678984984","https://openalex.org/W6679045638","https://openalex.org/W6743555512","https://openalex.org/W6779823529","https://openalex.org/W6795288823","https://openalex.org/W6798447524","https://openalex.org/W6798810632","https://openalex.org/W6801392204","https://openalex.org/W6838815585","https://openalex.org/W6844872470","https://openalex.org/W6846209384","https://openalex.org/W6850427756","https://openalex.org/W6851950068","https://openalex.org/W6856066198","https://openalex.org/W6856202087","https://openalex.org/W6858925035"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2053286651","https://openalex.org/W2181743346","https://openalex.org/W2187401768","https://openalex.org/W2181413294","https://openalex.org/W2989452537","https://openalex.org/W2052122378","https://openalex.org/W2544423928","https://openalex.org/W2062023542"],"abstract_inverted_index":{"Text-based":[0],"person":[1],"retrieval":[2],"(TBPR)":[3],"is":[4,230],"a":[5,16,37,50,59,115,192],"challenging":[6],"task":[7],"that":[8,27,72],"aims":[9],"at":[10,68,232],"retrieving":[11],"candidate":[12,34,66,107],"pedestrian":[13],"images":[14,67],"from":[15,86,178],"gallery,":[17],"using":[18],"textual":[19,29,60,104],"descriptions":[20],"as":[21],"queries.":[22],"Existing":[23],"methods":[24,92],"generally":[25],"assume":[26],"the":[28,32,73,77,82,87,99,103,127,134,154,164,168,179,186,212,223],"query":[30,61,105],"and":[31,44,106,141,172,215],"unique":[33],"image":[35],"have":[36],"certain":[38],"cross-modal":[39,79,135,199],"relationship":[40],"under":[41],"one-to-one":[42],"constraint,":[43],"optimize":[45],"their":[46],"conditional":[47,84],"probability":[48],"via":[49],"discriminative":[51,88],"paradigm.":[52],"However,":[53],"in":[54,76,97],"real":[55],"scenarios":[56],"of":[57,90,102,156,170,217],"TBPR,":[58],"may":[62,93],"associate":[63],"with":[64,122,159],"multiple":[65],"one":[69],"time,":[70],"indicating":[71],"uncertainty":[74,136,165],"resides":[75],"one-to-many":[78],"relationship.":[80],"Moreover,":[81],"learnt":[83],"probabilities":[85,101],"paradigm":[89],"existing":[91],"be":[94],"less":[95],"effective":[96],"reflecting":[98],"joint":[100,203],"images.":[108],"To":[109],"tackle":[110],"these":[111],"problems,":[112],"we":[113,131,162,190],"propose":[114,191],"novel":[116,193],"method":[117],"termed":[118],"Cross-modal":[119],"Uncertainty":[120],"Modeling":[121],"Diffusion-based":[123],"Refinement":[124],"(CUMDR)":[125],"for":[126],"TBPR":[128,209],"task.":[129],"First,":[130],"implicitly":[132],"model":[133,183],"to":[137,151,166,196,222],"capture":[138],"richer":[139],"semantics":[140],"complex":[142],"correlations,":[143],"thus":[144],"generating":[145],"diverse":[146],"yet":[147],"plausible":[148],"retrievals.":[149],"Additionally,":[150],"reasonably":[152],"mitigate":[153],"impact":[155],"noisy":[157],"data":[158],"high":[160],"uncertainty,":[161],"quantify":[163],"allocate":[167],"importance":[169],"raw":[171],"complement":[173],"annotations,":[174],"which":[175],"are":[176],"generated":[177],"multi-modal":[180],"large":[181],"language":[182],"based":[184],"on":[185,207],"retrieval-augmented":[187],"template.":[188],"Finally,":[189],"diffusion-based":[194],"denoiser":[195],"progressively":[197],"refine":[198],"alignments":[200],"by":[201],"learning":[202],"probabilities.":[204],"Extensive":[205],"experiments":[206],"three":[208],"datasets":[210],"demonstrate":[211],"superior":[213],"performance":[214],"generalizability":[216],"our":[218],"CUMDR":[219],"approach":[220],"compared":[221],"latest":[224],"methods.":[225],"Our":[226],"anonymous":[227],"implementation":[228],"repository":[229],"available":[231],"<uri":[233],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[234],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Shenshen7/CUMDR</uri>.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}