{"id":"https://openalex.org/W4413050925","doi":"https://doi.org/10.1109/tip.2025.3594880","title":"Enhancing Text-Based Person Retrieval by Combining Fused Representation and Reciprocal Learning With Adaptive Loss Refinement","display_name":"Enhancing Text-Based Person Retrieval by Combining Fused Representation and Reciprocal Learning With Adaptive Loss Refinement","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413050925","doi":"https://doi.org/10.1109/tip.2025.3594880","pmid":"https://pubmed.ncbi.nlm.nih.gov/40773399"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3594880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3594880","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Anh D. Nguyen","orcid":"https://orcid.org/0000-0002-5097-2401"},"institutions":[{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Anh D. Nguyen","raw_affiliation_strings":["Department of Information Systems, VNU University of Engineering and Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-5097-2401","affiliations":[{"raw_affiliation_string":"Department of Information Systems, VNU University of Engineering and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I67868205"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101905435","display_name":"Hoa N. Nguyen","orcid":"https://orcid.org/0000-0002-2565-281X"},"institutions":[{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hoa N. Nguyen","raw_affiliation_strings":["Department of Information Systems, VNU University of Engineering and Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-2565-281X","affiliations":[{"raw_affiliation_string":"Department of Information Systems, VNU University of Engineering and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I67868205"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I67868205"],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83969844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"34","issue":null,"first_page":"5147","last_page":"5157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9898999929428101,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9886000156402588,"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":0.8134053945541382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6580933332443237},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6185612678527832},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6011125445365906},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5020453929901123},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4942796230316162},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48873114585876465},{"id":"https://openalex.org/keywords/reciprocal","display_name":"Reciprocal","score":0.47759127616882324},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4772907793521881},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4667632281780243},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4466787874698639},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4405660927295685},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43080225586891174},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4107202887535095},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3830749988555908},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.382641464471817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134053945541382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6580933332443237},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6185612678527832},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6011125445365906},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5020453929901123},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4942796230316162},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48873114585876465},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.47759127616882324},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4772907793521881},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4667632281780243},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4466787874698639},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4405660927295685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43080225586891174},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4107202887535095},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3830749988555908},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.382641464471817},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3594880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3594880","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:40773399","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40773399","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W119849253","https://openalex.org/W1951304353","https://openalex.org/W2345837149","https://openalex.org/W2894786240","https://openalex.org/W2896457183","https://openalex.org/W2962858109","https://openalex.org/W2963449390","https://openalex.org/W2998508940","https://openalex.org/W3003755145","https://openalex.org/W3029767270","https://openalex.org/W3142849873","https://openalex.org/W3165835426","https://openalex.org/W3196835757","https://openalex.org/W3206868111","https://openalex.org/W4283818632","https://openalex.org/W4287947470","https://openalex.org/W4295754656","https://openalex.org/W4304014355","https://openalex.org/W4362554499","https://openalex.org/W4385764787","https://openalex.org/W4386065462","https://openalex.org/W4386076631","https://openalex.org/W4386083137","https://openalex.org/W4386645546","https://openalex.org/W4386918752","https://openalex.org/W4387968696","https://openalex.org/W4387969466","https://openalex.org/W4388145471","https://openalex.org/W4389331836","https://openalex.org/W4391730826","https://openalex.org/W4391944287","https://openalex.org/W4393154149","https://openalex.org/W4393158793","https://openalex.org/W4393160134","https://openalex.org/W4393170802","https://openalex.org/W4395659479","https://openalex.org/W4396216126","https://openalex.org/W4402753821","https://openalex.org/W4402753981","https://openalex.org/W4407900581","https://openalex.org/W4408220440","https://openalex.org/W4409426360","https://openalex.org/W4409657206"],"related_works":["https://openalex.org/W2391753177","https://openalex.org/W2965546495","https://openalex.org/W2996284460","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3119773509","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611"],"abstract_inverted_index":{"Text-based":[0],"person":[1,114],"retrieval":[2,115,205],"is":[3],"defined":[4],"as":[5],"the":[6,31,56,61,71,90],"challenging":[7],"task":[8],"of":[9,48,67,196],"searching":[10],"for":[11,43,169],"people's":[12],"images":[13,68,170],"based":[14],"on":[15,226],"given":[16],"textual":[17,36],"queries":[18,94],"in":[19,52,92,95],"natural":[20],"language.":[21],"Conventional":[22],"methods":[23,221],"primarily":[24],"use":[25],"deep":[26],"neural":[27],"networks":[28],"to":[29,70,76,103,147,164,178,202,209],"understand":[30],"relationship":[32],"between":[33,55],"visual":[34],"and":[35,64,83,123,171,181,188,232],"data,":[37],"creating":[38],"a":[39,111,119,130,160,175,194],"shared":[40],"feature":[41,53],"space":[42],"cross-modal":[44],"matching.":[45],"The":[46],"absence":[47],"awareness":[49],"regarding":[50],"variations":[51],"granularity":[54],"two":[57,138],"modalities,":[58,85],"coupled":[59],"with":[60],"diverse":[62],"poses":[63],"viewing":[65],"angles":[66],"corresponding":[69],"same":[72],"individual,":[73],"may":[74],"lead":[75],"overlooking":[77],"significant":[78,156],"differences":[79],"within":[80],"each":[81,145],"modality":[82],"across":[84],"despite":[86],"notable":[87],"enhancements.":[88],"Furthermore,":[89],"inconsistency":[91],"caption":[93],"large":[96],"public":[97],"datasets":[98],"presents":[99],"an":[100,124],"additional":[101],"obstacle":[102],"cross-modality":[104],"mapping":[105],"learning.":[106],"Therefore,":[107],"we":[108,135,214],"introduce":[109],"3RTPR,":[110],"novel":[112,176],"text-based":[113],"method":[116,163],"that":[117,184],"integrates":[118],"representation":[120,162],"fusing":[121],"mechanism":[122],"adaptive":[125],"loss":[126,180],"refinement":[127],"algorithm":[128,177],"into":[129],"dual-encoder":[131],"branch":[132],"architecture.":[133],"Moreover,":[134],"propose":[136],"training":[137],"independent":[139,197],"models":[140],"simultaneously,":[141],"which":[142,199],"reciprocally":[143],"support":[144],"other":[146],"enhance":[148,203],"learning":[149,192],"effectiveness.":[150],"Consequently,":[151],"our":[152,211],"approach":[153],"encompasses":[154],"three":[155,227],"contributions:":[157],"(i)":[158],"proposing":[159,190],"fused":[161],"generate":[165],"more":[166],"discriminative":[167],"representations":[168],"captions;":[172],"(ii)":[173],"introducing":[174],"adjust":[179],"prioritize":[182],"samples":[183],"contain":[185],"valuable":[186],"information;":[187],"(iii)":[189],"reciprocal":[191],"involving":[193],"pair":[195],"models,":[198],"allows":[200],"us":[201],"general":[204],"performance.":[206],"In":[207],"order":[208],"validate":[210],"method's":[212],"effectiveness,":[213],"also":[215],"demonstrate":[216],"superior":[217],"performance":[218],"over":[219],"state-of-the-art":[220],"by":[222],"performing":[223],"rigorous":[224],"experiments":[225],"well-known":[228],"benchmarks:":[229],"CUHK-PEDES,":[230],"ICFG-PEDES,":[231],"RSTPReid.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}