{"id":"https://openalex.org/W3097343785","doi":"https://doi.org/10.1109/icassp39728.2021.9413456","title":"Robust Latent Representations Via Cross-Modal Translation and Alignment","display_name":"Robust Latent Representations Via Cross-Modal Translation and Alignment","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3097343785","doi":"https://doi.org/10.1109/icassp39728.2021.9413456","mag":"3097343785"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.01631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071287333","display_name":"Vandana Rajan","orcid":"https://orcid.org/0000-0002-2250-1688"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Vandana Rajan","raw_affiliation_strings":["Queen Mary University of London,Centre for Intelligent Sensing,UK","Queen Mary University of London, Centre for Intelligent Sensing, UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Intelligent Sensing,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London, Centre for Intelligent Sensing, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066363315","display_name":"Alessio Brutti","orcid":"https://orcid.org/0000-0003-4146-3071"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Brutti","raw_affiliation_strings":["Fondazione Bruno Kessler,Trento,Italy","Fondazione Bruno Kessler Trento Italy"],"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Trento,Italy","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Fondazione Bruno Kessler Trento Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004087827","display_name":"Andrea Cavallaro","orcid":"https://orcid.org/0000-0001-5086-7858"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrea Cavallaro","raw_affiliation_strings":["Queen Mary University of London,Centre for Intelligent Sensing,UK","Queen Mary University of London, Centre for Intelligent Sensing, UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Intelligent Sensing,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London, Centre for Intelligent Sensing, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071287333"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.0968,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34003212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"4315","last_page":"4319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9977999925613403,"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":0.9977999925613403,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9882000088691711,"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/modalities","display_name":"Modalities","score":0.8860580921173096},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.8142139911651611},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7054908275604248},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6596679091453552},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6220757961273193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5042582750320435},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45231905579566956},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.438640296459198},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4357047975063324},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43119657039642334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33724555373191833}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8860580921173096},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.8142139911651611},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7054908275604248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6596679091453552},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6220757961273193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5042582750320435},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45231905579566956},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.438640296459198},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4357047975063324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43119657039642334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33724555373191833},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.01631","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01631","pdf_url":"https://arxiv.org/pdf/2011.01631","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3097343785","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2011.01631.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.01631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.01631","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.17023/5t1x-g658","is_oa":true,"landing_page_url":"https://doi.org/10.17023/5t1x-g658","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.01631","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01631","pdf_url":"https://arxiv.org/pdf/2011.01631","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3097343785.pdf","grobid_xml":"https://content.openalex.org/works/W3097343785.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1523385540","https://openalex.org/W1606749791","https://openalex.org/W2346454595","https://openalex.org/W2610961739","https://openalex.org/W2619383789","https://openalex.org/W2624578427","https://openalex.org/W2767087747","https://openalex.org/W2892550322","https://openalex.org/W2895368507","https://openalex.org/W2897611955","https://openalex.org/W2904106524","https://openalex.org/W2962931121","https://openalex.org/W2962931510","https://openalex.org/W2964276171","https://openalex.org/W2972921424","https://openalex.org/W2997258743","https://openalex.org/W3036595416","https://openalex.org/W3102160429","https://openalex.org/W3103512193","https://openalex.org/W6631216910","https://openalex.org/W6756485162","https://openalex.org/W6840018054"],"related_works":["https://openalex.org/W3190138501","https://openalex.org/W3176157254","https://openalex.org/W2809347440","https://openalex.org/W3035333188","https://openalex.org/W3145183144","https://openalex.org/W3093199520","https://openalex.org/W3110801570","https://openalex.org/W3209494353","https://openalex.org/W3194603040","https://openalex.org/W2884695718","https://openalex.org/W3002271958","https://openalex.org/W3205259372","https://openalex.org/W2795389793","https://openalex.org/W2060300564","https://openalex.org/W2964216321","https://openalex.org/W2904518532","https://openalex.org/W3016663370","https://openalex.org/W2954672622","https://openalex.org/W2765440071","https://openalex.org/W3009205145"],"abstract_inverted_index":{"Multi-modal":[0],"learning":[1,19],"relates":[2],"information":[3],"across":[4],"observation":[5],"modalities":[6,25,42,64],"of":[7,59,85,112,149],"the":[8,24,56,83,95,98,121,132,136,147,150],"same":[9],"physical":[10],"phenomenon":[11],"to":[12,54,81,97],"leverage":[13],"complementary":[14],"information.":[15],"Most":[16],"multi-modal":[17,70,106],"machine":[18],"methods":[20],"require":[21],"that":[22,109,152],"all":[23],"used":[26],"for":[27,32,141,158],"training":[28,66,71],"are":[29,43],"also":[30],"available":[31],"testing.":[33],"This":[34,115],"is":[35,110,117],"a":[36,86,105,126],"limitation":[37],"when":[38],"signals":[39],"from":[40,94],"some":[41],"unavailable":[44],"or":[45],"severely":[46],"degraded.":[47],"To":[48],"address":[49],"this":[50],"limitation,":[51],"we":[52],"aim":[53],"improve":[55,82],"testing":[57],"performance":[58,157],"uni-modal":[60],"systems":[61],"using":[62],"multiple":[63],"during":[65],"only.":[67],"The":[68,92],"proposed":[69,133],"framework":[72,134,151],"uses":[73],"cross-modal":[74],"translation":[75,93],"and":[76,145],"correlation-based":[77],"latent":[78,128],"space":[79],"alignment":[80],"representations":[84],"worse":[87],"performing":[88,100],"(or":[89,101],"weaker)":[90],"modality.":[91],"weaker":[96,159],"better":[99],"stronger)":[102],"modality":[103,123],"generates":[104],"intermediate":[107],"encoding":[108,116],"representative":[111],"both":[113],"modalities.":[114,160],"then":[118],"correlated":[119],"with":[120],"stronger":[122],"representation":[124],"in":[125],"shared":[127],"space.":[129],"We":[130],"validate":[131],"on":[135],"AVEC":[137],"2016":[138],"dataset":[139],"(RECOLA)":[140],"continuous":[142],"emotion":[143],"recognition":[144],"show":[146],"effectiveness":[148],"achieves":[153],"state-of-":[154],"the-art":[155],"(uni-modal)":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}