{"id":"https://openalex.org/W4294891625","doi":"https://doi.org/10.1109/tcsvt.2022.3203247","title":"Deep Supervised Dual Cycle Adversarial Network for Cross-Modal Retrieval","display_name":"Deep Supervised Dual Cycle Adversarial Network for Cross-Modal Retrieval","publication_year":2022,"publication_date":"2022-09-07","ids":{"openalex":"https://openalex.org/W4294891625","doi":"https://doi.org/10.1109/tcsvt.2022.3203247"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3203247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3203247","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/A5052227145","display_name":"Lei Liao","orcid":"https://orcid.org/0000-0002-4751-504X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Liao","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4751-504X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037873810","display_name":"Meng Yang","orcid":"https://orcid.org/0000-0002-0795-3221"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","Key Laboratory of Machine Intelligence and Advanced Computing (SYSU), Ministry of Education, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0795-3221","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Key Laboratory of Machine Intelligence and Advanced Computing (SYSU), Ministry of Education, Guangzhou, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048088901","display_name":"Bob Zhang","orcid":"https://orcid.org/0000-0003-2497-9519"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Bob Zhang","raw_affiliation_strings":["Department of Computer and Information Science, PAMI Research Group, University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0003-2497-9519","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, PAMI Research Group, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052227145"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":1.8274,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.8658105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"33","issue":"2","first_page":"920","last_page":"934"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9751999974250793,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7652444839477539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6610150337219238},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6307726502418518},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5843300223350525},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.573774516582489},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.537318766117096},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4706786274909973},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4706677198410034},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4616715908050537},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45581287145614624},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44175484776496887},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4208492338657379},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.41803276538848877},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4122583866119385},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3691074252128601},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3494967520236969},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10388252139091492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652444839477539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6610150337219238},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6307726502418518},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5843300223350525},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.573774516582489},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.537318766117096},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4706786274909973},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4706677198410034},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4616715908050537},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45581287145614624},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44175484776496887},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4208492338657379},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.41803276538848877},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4122583866119385},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3691074252128601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3494967520236969},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10388252139091492},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3203247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3203247","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":[{"display_name":"Reduced inequalities","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3031428753","display_name":null,"funder_award_id":"61772568","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4868506558","display_name":null,"funder_award_id":"2019A1515012029","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6484137807","display_name":null,"funder_award_id":"62176271","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/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1964073652","https://openalex.org/W2007972815","https://openalex.org/W2013535308","https://openalex.org/W2052727801","https://openalex.org/W2106277773","https://openalex.org/W2138118304","https://openalex.org/W2155803963","https://openalex.org/W2295088417","https://openalex.org/W2326180695","https://openalex.org/W2430055109","https://openalex.org/W2590822257","https://openalex.org/W2591669147","https://openalex.org/W2606965845","https://openalex.org/W2765440071","https://openalex.org/W2799150641","https://openalex.org/W2896442399","https://openalex.org/W2897135094","https://openalex.org/W2900802124","https://openalex.org/W2915533878","https://openalex.org/W2944906272","https://openalex.org/W2954672622","https://openalex.org/W2956335072","https://openalex.org/W2962793481","https://openalex.org/W2963187862","https://openalex.org/W2963521811","https://openalex.org/W2967957126","https://openalex.org/W2998356391","https://openalex.org/W3005881764","https://openalex.org/W3011997138","https://openalex.org/W3015686016","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3048707520","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094286186","https://openalex.org/W3103717910","https://openalex.org/W3117993946","https://openalex.org/W3119746927","https://openalex.org/W3159952799","https://openalex.org/W3166304536","https://openalex.org/W3169472988","https://openalex.org/W3173220247","https://openalex.org/W3176451698","https://openalex.org/W3181159501","https://openalex.org/W3209108016","https://openalex.org/W3216333240","https://openalex.org/W4205474609","https://openalex.org/W4210593721","https://openalex.org/W4224301727","https://openalex.org/W4249992252","https://openalex.org/W4313181088","https://openalex.org/W6631216910","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6639103823","https://openalex.org/W6677994088","https://openalex.org/W6684191040","https://openalex.org/W6721087566","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6809741598"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W627697492","https://openalex.org/W3208297503","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W4283320496"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,11,44,74,110],"tasks,":[2,12],"which":[3,54],"are":[4],"more":[5],"natural":[6],"and":[7,83,90,97,146,160,179,191,203,260],"challenging":[8],"than":[9,275],"traditional":[10],"have":[13,29,67,246],"attracted":[14],"increasing":[15],"interest":[16],"from":[17,173],"researchers":[18],"in":[19,53,86,107,240],"recent":[20],"years.":[21],"Although":[22],"different":[23],"modalities":[24,225],"with":[25],"the":[26,33,40,69,80,87,95,101,144,149,157,166,174,180,184,199,208,212,220,237,241,250,267,276],"same":[27],"semantics":[28],"some":[30],"potential":[31],"relevance,":[32],"feature":[34,178,182],"space":[35,63,89,132,214],"heterogeneity":[36],"still":[37],"seriously":[38],"weakens":[39],"performance":[41,274],"of":[42,100,137,168,183,211,236],"cross-modal":[43,73,139,238],"models.":[45],"To":[46,112],"solve":[47,113],"this":[48,116],"problem,":[49],"common":[50,62,88,131,213,242],"space-based":[51],"methods":[52,78],"multimodal":[55],"data":[56,167,221],"is":[57,135,194,230],"projected":[58],"into":[59],"a":[60,119,188,227,233,272],"learned":[61],"for":[64,72,143,148],"similarity":[65,229],"measurement":[66,235],"become":[68],"mainstream":[70],"approach":[71],"tasks.":[75],"However,":[76],"current":[77],"entangle":[79],"modality":[81,161,170],"style":[82,162,177],"semantic":[84,96,102,158,190,209],"content":[85,159,181],"neglect":[91],"to":[92,206,218],"fully":[93,197],"explore":[94],"discriminative":[98,189],"representation/reconstruction":[99],"content.":[103],"This":[104],"often":[105],"results":[106,264],"an":[108],"unsatisfactory":[109],"performance.":[111],"these":[114],"issues,":[115],"paper":[117],"proposes":[118],"new":[120],"Deep":[121],"Supervised":[122],"Dual":[123],"Cycle":[124],"Adversarial":[125],"Network":[126],"(DSDCAN)":[127],"model":[128,155],"based":[129],"on":[130,249],"learning.":[133],"It":[134],"composed":[136],"two":[138,224],"cycle":[140,153],"GANs,":[141],"one":[142,147,169],"image":[145],"text.":[150],"The":[151,263],"proposed":[152,195,268],"GAN":[154],"disentangles":[156],"features":[163],"by":[164,196],"making":[165],"well":[171],"reconstructed":[172],"extracted":[175],"modal":[176],"other":[185],"modality.":[186],"Then,":[187],"label":[192,204],"loss":[193],"considering":[198],"category,":[200],"sample":[201],"contrast,":[202],"supervision":[205],"enhance":[207],"discrimination":[210],"representation.":[215],"Besides":[216],"this,":[217],"make":[219],"distribution":[222],"between":[223],"similar,":[226],"second-order":[228],"presented":[231],"as":[232],"distance":[234],"representation":[239],"space.":[243],"Extensive":[244],"experiments":[245],"been":[247],"conducted":[248],"Wikipedia,":[251],"Pascal":[252],"Sentence,":[253],"NUS-WIDE-10k,":[254],"PKU":[255],"XMedia,":[256],"MSCOCO,":[257],"NUS-WIDE,":[258],"Flickr30k":[259],"MIRFlickr":[261],"datasets.":[262],"demonstrate":[265],"that":[266],"method":[269],"can":[270],"achieve":[271],"higher":[273],"state-of-the-art":[277],"methods.":[278]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}