{"id":"https://openalex.org/W4319663732","doi":"https://doi.org/10.1109/tmm.2023.3243665","title":"Inter-Intra Modal Representation Augmentation With DCT-Transformer Adversarial Network for Image-Text Matching","display_name":"Inter-Intra Modal Representation Augmentation With DCT-Transformer Adversarial Network for Image-Text Matching","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4319663732","doi":"https://doi.org/10.1109/tmm.2023.3243665"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3243665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3243665","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5100418527","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-0579-2353"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, Xidian University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, Xidian University, Xian, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411782","display_name":"Dan Wang","orcid":"https://orcid.org/0000-0001-9302-3233"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Wang","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, Xidian University, Xian, China"],"raw_orcid":"https://orcid.org/0000-0001-9302-3233","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, Xidian University, Xian, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035560190","display_name":"Bin Song","orcid":"https://orcid.org/0000-0002-8096-3370"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Song","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, Xidian University, Xian, China"],"raw_orcid":"https://orcid.org/0000-0002-8096-3370","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, Xidian University, Xian, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100751512","display_name":"Hao Tan","orcid":"https://orcid.org/0000-0003-1774-4375"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Tan","raw_affiliation_strings":["Software Engineering Division, Guangdong OPPO Mobile Telecommunications Corp, Dongguan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Engineering Division, Guangdong OPPO Mobile Telecommunications Corp, Dongguan, China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9145,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87930872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"8933","last_page":"8945"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9973000288009644,"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":0.7907584309577942},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.6936772465705872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6540488600730896},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5615208148956299},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5275363922119141},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5261275768280029},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46845579147338867},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4310929775238037},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3419848084449768},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2916191518306732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907584309577942},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.6936772465705872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6540488600730896},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5615208148956299},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5275363922119141},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5261275768280029},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46845579147338867},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4310929775238037},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3419848084449768},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2916191518306732},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3243665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3243665","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4406704326","display_name":null,"funder_award_id":"62201419","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4721957486","display_name":null,"funder_award_id":"62071354","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7517857404","display_name":null,"funder_award_id":"2022ZDLGY05-08","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330485","display_name":"State Key Laboratory of Integrated Services Networks","ror":null},{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2031614119","https://openalex.org/W2185175083","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2546696630","https://openalex.org/W2745461083","https://openalex.org/W2883311563","https://openalex.org/W2953106684","https://openalex.org/W2962964995","https://openalex.org/W2963055199","https://openalex.org/W2963882743","https://openalex.org/W2963942586","https://openalex.org/W2964042428","https://openalex.org/W2981586349","https://openalex.org/W2988823324","https://openalex.org/W2990503944","https://openalex.org/W2997525715","https://openalex.org/W2998215884","https://openalex.org/W2998508940","https://openalex.org/W3026441479","https://openalex.org/W3028452400","https://openalex.org/W3034305926","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3045147787","https://openalex.org/W3088460296","https://openalex.org/W3091588028","https://openalex.org/W3092820619","https://openalex.org/W3094071022","https://openalex.org/W3094172275","https://openalex.org/W3106250896","https://openalex.org/W3118694826","https://openalex.org/W3135254306","https://openalex.org/W3155230099","https://openalex.org/W3190055600","https://openalex.org/W3202436960","https://openalex.org/W3207478986","https://openalex.org/W4206314411","https://openalex.org/W4312761738","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6678470764","https://openalex.org/W6726873649","https://openalex.org/W6739901393","https://openalex.org/W6745136726","https://openalex.org/W6747225742","https://openalex.org/W6755207826","https://openalex.org/W6766904570"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W4310988119"],"abstract_inverted_index":{"Image-text":[0],"matching":[1,87],"has":[2],"become":[3],"a":[4,79,112],"challenging":[5],"task":[6],"in":[7,25,38,55,59,88],"the":[8,31,39,50,152,160,165,181,195,202,205,209],"multimedia":[9],"analysis":[10],"field.":[11],"Many":[12],"advanced":[13],"methods":[14,29],"have":[15],"been":[16],"used":[17],"to":[18,115],"explore":[19],"local":[20],"and":[21,45,57,65,120,139,159,199],"global":[22],"cross-modal":[23,46],"correspondence":[24],"matching.":[26],"However,":[27],"most":[28],"ignore":[30],"importance":[32],"of":[33,42,136,155,204],"eliminating":[34],"potential":[35],"irrelevant":[36,122],"features":[37,41,51,123,154],"original":[40,153],"each":[43,169],"modality":[44,170],"common":[47,118,162,182],"feature.":[48],"Moreover,":[49],"extracted":[52],"from":[53,74,124],"regions":[54],"images":[56],"words":[58],"sentences":[60],"contain":[61],"cluttered":[62],"background":[63,166],"noise":[64,167],"different":[66,125,137],"occlusion":[67],"noise,":[68],"which":[69],"negatively":[70],"affects":[71],"alignment.":[72,189],"Different":[73],"these":[75],"methods,":[76],"we":[77],"propose":[78],"novel":[80],"DCT-Transformer":[81,103],"Adversarial":[82],"Network":[83],"(DTAN)":[84],"for":[85,188],"image-text":[86],"this":[89],"paper.":[90],"This":[91],"work":[92],"can":[93,178],"obtain":[94,180],"an":[95,147],"effective":[96],"metric":[97],"based":[98,110],"on":[99,111,194],"two":[100],"aspects:":[101],"i)":[102],"uses":[104],"DCT":[105,130],"(Discrete":[106],"Cosine":[107],"Transform)":[108],"method":[109,177],"transformer":[113],"mechanism":[114],"extract":[116],"multi-domain":[117,161],"representations":[119],"eliminate":[121],"modalities":[126,158],"(inter-modal).":[127],"Among":[128],"them,":[129],"divides":[131],"multi-modal":[132],"content":[133],"into":[134],"chunks":[135],"frequencies":[138],"quantifies":[140],"them.":[141],"ii)":[142],"The":[143,172],"adversarial":[144,174],"network":[145],"introduces":[146],"adversary":[148],"idea":[149],"by":[150],"combining":[151],"various":[156],"single":[157],"representation,":[163],"alleviating":[164],"within":[168],"(intra-modal).":[171],"proposed":[173],"feature":[175],"augmentation":[176],"easily":[179],"representation":[183],"that":[184],"is":[185],"only":[186],"useful":[187],"Extensive":[190],"experiments":[191],"are":[192],"completed":[193],"benchmark":[196],"datasets":[197],"Flickr30K":[198],"MS-COCO,":[200],"demonstrating":[201],"superiority":[203],"DTAN":[206],"model":[207],"over":[208],"state-of-the-art":[210],"methods.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}