{"id":"https://openalex.org/W4375869346","doi":"https://doi.org/10.1109/icassp49357.2023.10096138","title":"Learning Cross-Modal Audiovisual Representations with Ladder Networks for Emotion Recognition","display_name":"Learning Cross-Modal Audiovisual Representations with Ladder Networks for Emotion Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869346","doi":"https://doi.org/10.1109/icassp49357.2023.10096138"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5017966455","display_name":"Lucas Goncalves","orcid":"https://orcid.org/0000-0001-9613-1002"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lucas Goncalves","raw_affiliation_strings":["The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017966455"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":2.6118,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8957722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/modal","display_name":"Modal","score":0.7704949378967285},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7398785948753357},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6090042591094971},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5880969762802124},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5784581899642944},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5667401552200317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5364957451820374},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5195789337158203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5064641237258911},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5061644911766052},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.46566250920295715},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4136633574962616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38786694407463074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33895397186279297}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7704949378967285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398785948753357},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6090042591094971},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5880969762802124},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5784581899642944},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5667401552200317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5364957451820374},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5195789337158203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5064641237258911},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5061644911766052},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46566250920295715},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4136633574962616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38786694407463074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33895397186279297},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1976725440","https://openalex.org/W2030931454","https://openalex.org/W2144005487","https://openalex.org/W2174554700","https://openalex.org/W2238244608","https://openalex.org/W2325939864","https://openalex.org/W2341528187","https://openalex.org/W2619383789","https://openalex.org/W2745497104","https://openalex.org/W2807126412","https://openalex.org/W2883409523","https://openalex.org/W2892921685","https://openalex.org/W2942837495","https://openalex.org/W2962839749","https://openalex.org/W2963702064","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964346351","https://openalex.org/W2972602947","https://openalex.org/W3034266838","https://openalex.org/W3086923691","https://openalex.org/W3093051361","https://openalex.org/W3101998545","https://openalex.org/W3114214226","https://openalex.org/W3122081138","https://openalex.org/W3128412859","https://openalex.org/W3196749180","https://openalex.org/W4224932526","https://openalex.org/W4312976151","https://openalex.org/W4385245566","https://openalex.org/W6685251022","https://openalex.org/W6689779973","https://openalex.org/W6739901393","https://openalex.org/W6753277404","https://openalex.org/W7073743773"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","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":{"Representation":[0],"learning":[1],"is":[2,14,33],"a":[3,68,123],"challenging,":[4],"but":[5],"essential":[6],"task":[7],"in":[8,26,40],"audiovisual":[9,41],"learning.":[10],"A":[11],"key":[12],"challenge":[13],"to":[15,35,54,71,76],"generate":[16],"strong":[17,60],"cross-modal":[18,51,61,92],"representations":[19,66,80,101],"while":[20,58],"still":[21],"capturing":[22,30],"discriminative":[23],"information":[24,32,57],"contained":[25],"unimodal":[27],"features.":[28],"Properly":[29],"this":[31,47],"important":[34],"increase":[36],"accuracy":[37],"and":[38,84,94,99,117],"robustness":[39],"tasks.":[42],"Focusing":[43],"on":[44,107,122],"emotion":[45,103],"recognition,":[46],"study":[48],"proposes":[49],"novel":[50],"ladder":[52],"networks":[53],"capture":[55],"modality-specific":[56,98],"building":[59],"representations.":[62],"Our":[63,105],"method":[64],"utilizes":[65],"from":[67],"backbone":[69],"network":[70],"implement":[72],"unsupervised":[73],"auxiliary":[74],"tasks":[75],"reconstruct":[77],"intermediate":[78],"layer":[79],"across":[81],"the":[82,91,108],"acoustic":[83],"visual":[85],"networks.":[86],"The":[87],"skip":[88],"connections":[89],"between":[90],"encoder":[93],"decoder":[95],"provide":[96],"powerful":[97],"multimodal":[100],"for":[102],"recognition.":[104],"model":[106],"CREMA-D":[109],"corpus":[110],"achieves":[111],"high":[112],"performance":[113],"with":[114],"precision,":[115],"recall,":[116],"F1":[118],"scores":[119],"over":[120],"80%":[121],"six-class":[124],"problem.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}