{"id":"https://openalex.org/W3172942971","doi":"https://doi.org/10.1109/icme51207.2021.9428280","title":"Learning Controlled Semantic Embedding for Cross-Modal Retrieval","display_name":"Learning Controlled Semantic Embedding for Cross-Modal Retrieval","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3172942971","doi":"https://doi.org/10.1109/icme51207.2021.9428280","mag":"3172942971"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055831079","display_name":"Rong Yang","orcid":"https://orcid.org/0000-0002-6983-4682"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Yang","raw_affiliation_strings":["Guangdong University of Technology,Department of Computer Science,China","Department of Computer Science, Guangdong University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Department of Computer Science,China","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"Department of Computer Science, Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048763159","display_name":"Min Meng","orcid":"https://orcid.org/0000-0002-5107-5585"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Meng","raw_affiliation_strings":["Guangdong University of Technology,Department of Computer Science,China","Department of Computer Science, Guangdong University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Department of Computer Science,China","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"Department of Computer Science, Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019516431","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-7758-9349"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Hangzhou Dianzi University,School of Computer Science,Hangzhou,China,310018"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University,School of Computer Science,Hangzhou,China,310018","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060755096","display_name":"Jigang Wu","orcid":"https://orcid.org/0000-0002-6470-9794"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jigang Wu","raw_affiliation_strings":["Guangdong University of Technology,Department of Computer Science,China","Department of Computer Science, Guangdong University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Department of Computer Science,China","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"Department of Computer Science, Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9789000153541565,"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":0.8007874488830566},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6950526833534241},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.67929607629776},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6445776224136353},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.620847225189209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5894106030464172},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.560965359210968},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.553015947341919},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.46874740719795227},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44635188579559326},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44524919986724854},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44436416029930115},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.43171054124832153},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.43030351400375366},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39696046710014343},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.1322660744190216},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06634160876274109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007874488830566},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6950526833534241},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.67929607629776},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6445776224136353},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.620847225189209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5894106030464172},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.560965359210968},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.553015947341919},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.46874740719795227},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44635188579559326},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44524919986724854},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44436416029930115},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43171054124832153},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.43030351400375366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39696046710014343},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.1322660744190216},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06634160876274109},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"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/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/icme51207.2021.9428280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W138284169","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1870428314","https://openalex.org/W1922199343","https://openalex.org/W1959608418","https://openalex.org/W1976258951","https://openalex.org/W2007972815","https://openalex.org/W2049993534","https://openalex.org/W2106277773","https://openalex.org/W2170942078","https://openalex.org/W2203543769","https://openalex.org/W2266728343","https://openalex.org/W2388114291","https://openalex.org/W2418353079","https://openalex.org/W2604394529","https://openalex.org/W2604880013","https://openalex.org/W2759194679","https://openalex.org/W2905040928","https://openalex.org/W2962955826","https://openalex.org/W2963187862","https://openalex.org/W2964222296","https://openalex.org/W2966146145","https://openalex.org/W2981938443","https://openalex.org/W2999606372","https://openalex.org/W3098232083","https://openalex.org/W6605707561","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6639283537","https://openalex.org/W6640963894","https://openalex.org/W6644302431","https://openalex.org/W6688143368","https://openalex.org/W6735953149","https://openalex.org/W6736114314","https://openalex.org/W6741121127","https://openalex.org/W6784889160"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1],"has":[2],"caught":[3],"appealing":[4],"attentions":[5],"as":[6],"it":[7],"supports":[8],"querying":[9],"across":[10],"different":[11],"modalities.":[12],"However,":[13],"most":[14],"existing":[15],"methods":[16,133],"have":[17],"emphasized":[18],"on":[19,78],"directly":[20],"mapping":[21],"heterogeneous":[22],"features":[23],"into":[24,99],"the":[25,40,57,100,105,118,126],"common":[26],"subspace,":[27],"which":[28,55,81,109],"inevitably":[29],"results":[30],"in":[31,134],"highly":[32],"entangled":[33],"representations,":[34],"thereby":[35],"preventing":[36],"them":[37],"from":[38],"bridging":[39],"modality":[41],"gap.":[42],"This":[43],"paper":[44],"presents":[45],"a":[46,92,114],"novel":[47],"deep":[48],"framework":[49],"called":[50],"Controlled":[51],"Semantic":[52],"Embedding":[53],"(CSE),":[54],"is":[56,96,110],"first":[58],"attempt":[59],"to":[60,103],"learn":[61],"disentangled":[62],"representations":[63],"with":[64,113],"controlled":[65],"semantic":[66,83,94,106,121],"structure":[67],"for":[68,85,116],"cross-modal":[69,135],"retrieval.":[70,136],"Specifically,":[71],"we":[72],"design":[73],"two":[74],"generative":[75,101],"networks":[76,102],"based":[77],"variational":[79],"autoencoder,":[80],"incorporate":[82],"discriminators":[84],"effective":[86],"prediction":[87],"of":[88,120,128],"structured":[89],"semantics.":[90],"Meanwhile,":[91],"self-supervised":[93],"network":[95],"seamlessly":[97],"integrated":[98],"supervise":[104],"embedding":[107],"process,":[108],"further":[111],"coupled":[112],"quantizer":[115],"controlling":[117],"quantizability":[119],"representations.":[122],"Extensive":[123],"experiments":[124],"show":[125],"superiority":[127],"CSE":[129],"over":[130],"other":[131],"state-of-the-art":[132]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}