{"id":"https://openalex.org/W4390603585","doi":"https://doi.org/10.1109/tip.2023.3348297","title":"USER: Unified Semantic Enhancement With Momentum Contrast for Image-Text Retrieval","display_name":"USER: Unified Semantic Enhancement With Momentum Contrast for Image-Text Retrieval","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390603585","doi":"https://doi.org/10.1109/tip.2023.3348297","pmid":"https://pubmed.ncbi.nlm.nih.gov/38190676"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3348297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3348297","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":"https://openalex.org/A5100456404","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0003-2819-388X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-2819-388X","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005367680","display_name":"Zhong Ji","orcid":"https://orcid.org/0000-0002-2197-3739"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Ji","raw_affiliation_strings":["Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2197-3739","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401468","display_name":"Di Wang","orcid":"https://orcid.org/0000-0003-1586-0196"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-1586-0196","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086887025","display_name":"Yanwei Pang","orcid":"https://orcid.org/0000-0001-6670-3727"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Pang","raw_affiliation_strings":["Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6670-3727","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106943753","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2924-946X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Key Laboratory of Intelligent Interaction and Applications, Ministry of Industry and Information Technology, and the School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-2924-946X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Interaction and Applications, Ministry of Industry and Information Technology, and the School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004","https://openalex.org/I890469752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8691,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.99089332,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"33","issue":null,"first_page":"595","last_page":"609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987000226974487,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9926000237464905,"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":0.8210783004760742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5537859797477722},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.49765804409980774},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48241719603538513},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4595550298690796},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4348376393318176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38219255208969116},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3247224688529968},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2430773377418518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8210783004760742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5537859797477722},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.49765804409980774},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48241719603538513},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4595550298690796},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4348376393318176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38219255208969116},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3247224688529968},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2430773377418518},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3348297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3348297","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:38190676","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38190676","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3103725251","display_name":null,"funder_award_id":"2022ZD0160403","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3930161243","display_name":null,"funder_award_id":"62176178","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1527575280","https://openalex.org/W1861492603","https://openalex.org/W2106277773","https://openalex.org/W2108598243","https://openalex.org/W2138118304","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2211092169","https://openalex.org/W2277195237","https://openalex.org/W2476624367","https://openalex.org/W2591669147","https://openalex.org/W2745461083","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2963536419","https://openalex.org/W2964727037","https://openalex.org/W2966715458","https://openalex.org/W2988823324","https://openalex.org/W2990571534","https://openalex.org/W2994818707","https://openalex.org/W2997326970","https://openalex.org/W3009561768","https://openalex.org/W3035454331","https://openalex.org/W3035524453","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094172275","https://openalex.org/W3107593279","https://openalex.org/W3108373531","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3145807616","https://openalex.org/W3155230099","https://openalex.org/W3174377922","https://openalex.org/W3175888430","https://openalex.org/W3190055600","https://openalex.org/W3192443982","https://openalex.org/W3208314443","https://openalex.org/W3209163491","https://openalex.org/W4206314411","https://openalex.org/W4210894218","https://openalex.org/W4226391640","https://openalex.org/W4283516491","https://openalex.org/W4285145317","https://openalex.org/W4285197287","https://openalex.org/W4297808394","https://openalex.org/W4308774120","https://openalex.org/W4312193929","https://openalex.org/W4312761738","https://openalex.org/W4312934263","https://openalex.org/W4319299832","https://openalex.org/W4385245566","https://openalex.org/W4385565405","https://openalex.org/W6631516269","https://openalex.org/W6679434410","https://openalex.org/W6726873649","https://openalex.org/W6739901393","https://openalex.org/W6747225742","https://openalex.org/W6757817989","https://openalex.org/W6766904570","https://openalex.org/W6774314701","https://openalex.org/W6774670964","https://openalex.org/W6779326418","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6802411921","https://openalex.org/W6803316292","https://openalex.org/W6811013733"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"As":[0],"a":[1,107,159,206],"fundamental":[2],"and":[3,9,34,164,197,218,229,239,267,272],"challenging":[4],"task":[5],"in":[6,188],"bridging":[7],"language":[8],"vision":[10],"domains,":[11],"Image-Text":[12],"Retrieval":[13],"(ITR)":[14],"aims":[15],"at":[16,296],"searching":[17],"for":[18,116],"the":[19,27,31,41,64,67,72,87,95,135,139,153,166,181,199,226,233,246,251,258],"target":[20],"instances":[21],"that":[22],"are":[23,193],"semantically":[24],"relevant":[25],"to":[26,39,162,195,213],"given":[28],"query":[29],"from":[30,57,152,168,215],"other":[32,149],"modality,":[33],"its":[35],"key":[36],"challenge":[37],"is":[38,81,211,263],"measure":[40],"semantic":[42],"similarity":[43],"across":[44],"different":[45],"modalities.":[46],"Although":[47],"significant":[48],"progress":[49],"has":[50],"been":[51],"achieved,":[52],"existing":[53,247],"approaches":[54],"typically":[55],"suffer":[56],"two":[58,122,190],"major":[59],"limitations:":[60],"(1)":[61],"It":[62,85],"hurts":[63],"accuracy":[65,238],"of":[66,89,184,201,235,254],"representation":[68,127,137],"by":[69,93,265],"directly":[70],"exploiting":[71],"bottom-up":[73],"attention":[74],"based":[75,97,128,217,221],"region-level":[76],"features":[77],"where":[78],"each":[79],"region":[80],"equally":[82],"treated.":[83],"(2)":[84],"limits":[86],"scale":[88,200],"negative":[90,202],"sample":[91,203],"pairs":[92],"employing":[94],"mini-batch":[96,216],"end-to-end":[98],"training":[99,182],"mechanism.":[100],"To":[101],"address":[102],"these":[103],"limitations,":[104],"we":[105,119,179],"propose":[106],"Unified":[108,207],"Semantic":[109,129],"Enhancement":[110,130,145,175],"Momentum":[111],"Contrastive":[112],"Learning":[113],"(USER)":[114],"method":[115,249],"ITR.":[117],"Specifically,":[118],"delicately":[120],"design":[121],"simple":[123],"but":[124],"effective":[125],"Global":[126],"(GSE)":[131],"modules.":[132],"One":[133],"learns":[134],"global":[136],"via":[138],"self-attention":[140],"algorithm,":[141],"noted":[142,172],"as":[143,173],"Self-Guided":[144],"(SGE)":[146],"module.":[147,177],"The":[148],"module":[150],"benefits":[151],"pre-trained":[154,280],"CLIP":[155],"module,":[156],"which":[157,189],"provides":[158],"novel":[160],"scheme":[161],"exploit":[163],"transfer":[165],"knowledge":[167,278],"an":[169],"off-the-shelf":[170],"model,":[171],"CLIP-Guided":[174],"(CGE)":[176],"Moreover,":[178],"incorporate":[180],"mechanism":[183],"MoCo":[185],"into":[186],"ITR,":[187],"dynamic":[191,219],"queues":[192],"employed":[194],"enrich":[196],"enlarge":[198],"pairs.":[204],"Meanwhile,":[205],"Training":[208],"Objective":[209],"(UTO)":[210],"developed":[212],"learn":[214],"queue":[220],"samples.":[222],"Extensive":[223],"experiments":[224],"on":[225,257,269],"benchmark":[227],"MSCOCO":[228,259],"Flickr30K":[230],"datasets":[231],"demonstrate":[232],"superiority":[234],"both":[236],"retrieval":[237,271,274],"inference":[240,288],"efficiency.":[241],"For":[242],"instance,":[243],"compared":[244],"with":[245],"best":[248],"NAAF,":[250],"metric":[252],"R@1":[253],"our":[255],"USER":[256],"5K":[260],"Testing":[261],"set":[262],"improved":[264],"5%":[266],"2.4%":[268],"caption":[270],"image":[273],"without":[275],"any":[276],"external":[277],"or":[279],"model":[281],"while":[282],"enjoying":[283],"over":[284],"60":[285],"times":[286],"faster":[287],"speed.":[289],"Our":[290],"source":[291],"code":[292],"will":[293],"be":[294],"released":[295],"https://github.com/zhangy0822/USER.":[297]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":31},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}