{"id":"https://openalex.org/W2937551712","doi":"https://doi.org/10.1109/icassp.2019.8682454","title":"Learning to Fuse Latent Representations for Multimodal Data","display_name":"Learning to Fuse Latent Representations for Multimodal Data","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937551712","doi":"https://doi.org/10.1109/icassp.2019.8682454","mag":"2937551712"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbilu.uni.lu/handle/10993/40568","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025028067","display_name":"Oyebade K. Oyedotun","orcid":"https://orcid.org/0000-0002-4652-1691"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4405259781","display_name":"Interdisciplinary Centre for Security, Reliability and Trust","ror":"https://ror.org/02qav7c04","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Oyebade K. Oyedotun","raw_affiliation_strings":["Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083368272","display_name":"Djamila Aouada","orcid":"https://orcid.org/0000-0002-7576-2064"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4405259781","display_name":"Interdisciplinary Centre for Security, Reliability and Trust","ror":"https://ror.org/02qav7c04","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Djamila Aouada","raw_affiliation_strings":["Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080037825","display_name":"Bj\u00f6rn Ottersten","orcid":"https://orcid.org/0000-0003-2298-6774"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4405259781","display_name":"Interdisciplinary Centre for Security, Reliability and Trust","ror":"https://ror.org/02qav7c04","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Bjorn Ottersten","raw_affiliation_strings":["Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0915,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.30330399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"1","issue":null,"first_page":"3122","last_page":"3126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9991999864578247,"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/T11448","display_name":"Face recognition and analysis","score":0.9991999864578247,"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":0.9983000159263611,"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/T10057","display_name":"Face and Expression Recognition","score":0.9979000091552734,"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":0.7837594747543335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.712827205657959},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6181363463401794},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6124910116195679},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6079230308532715},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.5511738657951355},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5152490735054016},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5023162364959717},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4991164207458496},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.49793219566345215},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49157270789146423},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.46088194847106934},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4452381432056427},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4436585605144501},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44147711992263794},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4412226974964142},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.43254178762435913},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42715099453926086},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.25514084100723267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837594747543335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.712827205657959},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6181363463401794},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6124910116195679},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6079230308532715},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.5511738657951355},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5152490735054016},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5023162364959717},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4991164207458496},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.49793219566345215},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49157270789146423},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.46088194847106934},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4452381432056427},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4436585605144501},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44147711992263794},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4412226974964142},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.43254178762435913},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42715099453926086},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.25514084100723267},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8682454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:orbilu.uni.lu:10993/40568","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/40568","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom [GB], 12-05-2019 to 17-05-2019","raw_type":"info:eu-repo/semantics/conferencePoster"}],"best_oa_location":{"id":"pmh:oai:orbilu.uni.lu:10993/40568","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/40568","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom [GB], 12-05-2019 to 17-05-2019","raw_type":"info:eu-repo/semantics/conferencePoster"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W171902450","https://openalex.org/W1026270304","https://openalex.org/W1040410175","https://openalex.org/W1480583224","https://openalex.org/W1603155784","https://openalex.org/W2018776244","https://openalex.org/W2137306662","https://openalex.org/W2148463593","https://openalex.org/W2163605009","https://openalex.org/W2164587673","https://openalex.org/W2167510172","https://openalex.org/W2260041796","https://openalex.org/W2318145034","https://openalex.org/W2534547303","https://openalex.org/W2752758619","https://openalex.org/W2800780290","https://openalex.org/W2950621961","https://openalex.org/W2963956866","https://openalex.org/W2964052309","https://openalex.org/W6606244218","https://openalex.org/W6626481562","https://openalex.org/W6636286539","https://openalex.org/W6680591342","https://openalex.org/W6681753794","https://openalex.org/W6684191040","https://openalex.org/W6684372118","https://openalex.org/W6692320821","https://openalex.org/W6753968785"],"related_works":["https://openalex.org/W2895918973","https://openalex.org/W2396919411","https://openalex.org/W4285815173","https://openalex.org/W2946165673","https://openalex.org/W4312851439","https://openalex.org/W4376653966","https://openalex.org/W2291115585","https://openalex.org/W4307474775","https://openalex.org/W4321022102","https://openalex.org/W4385573445"],"abstract_inverted_index":{"Multimodal":[0],"learning":[1,147],"leverages":[2],"data":[3,21,46,107,156],"from":[4,19],"different":[5,45,155],"modalities":[6,47,157],"to":[7,97,159],"improve":[8],"the":[9,41,44,61,69,80,100,116,130,138,148,151,164],"performance":[10],"of":[11,31,43,102,119,150],"a":[12,32,37,52,110],"trained":[13],"model.":[14],"Typically,":[15],"latent":[16,62,103,121,152],"representations":[17,63,85,104,122,153],"extracted":[18,120],"multimodal":[20,106,142],"are":[22,87],"provided":[23],"via":[24],"direct":[25],"feature":[26],"fusion":[27,101,149,167],"for":[28,65,90,105,133,154],"end-to-end":[29],"training":[30],"deep":[33],"neural":[34],"network":[35],"towards":[36],"specific":[38],"task.":[39],"However,":[40],"informativeness":[42],"can":[48],"easily":[49],"vary":[50],"across":[51],"collected":[53],"dataset.":[54],"As":[55],"such,":[56],"naively":[57],"or":[58],"directly":[59],"fusing":[60],"obtained":[64],"one":[66],"modality":[67,111],"and":[68,137],"other,":[70],"as":[71],"is":[72],"commonly":[73],"done":[74],"in":[75,82],"state-of-the-art":[76],"works,":[77],"may":[78],"burden":[79],"model":[81,161],"finding":[83],"concise":[84],"that":[86,114,146],"indeed":[88],"useful":[89],"learning.":[91],"In":[92],"this":[93],"paper,":[94],"we":[95],"propose":[96],"instead":[98],"learn":[99],"by":[108],"using":[109,129],"gating":[112],"mechanism":[113],"allows":[115],"dynamic":[117],"weighting":[118],"based":[123],"on":[124],"their":[125],"informativness.":[126],"Extensive":[127],"experiments":[128],"BU-3DFE":[131],"dataset":[132,144],"facial":[134],"expression":[135],"recognition":[136],"Washington":[139],"object":[140],"classification":[141],"RGB-D":[143],"show":[145],"leads":[158],"improved":[160],"generalization":[162],"than":[163],"conventional":[165],"naive":[166],"method.":[168]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}