{"id":"https://openalex.org/W2952307697","doi":"https://doi.org/10.18653/v1/p19-1095","title":"Multimodal and Multi-view Models for Emotion Recognition","display_name":"Multimodal and Multi-view Models for Emotion Recognition","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2952307697","doi":"https://doi.org/10.18653/v1/p19-1095","mag":"2952307697"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1095","doi":"https://doi.org/10.18653/v1/p19-1095","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1095","pdf_url":"https://www.aclweb.org/anthology/P19-1095.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.aclweb.org/anthology/P19-1095.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101479796","display_name":"Gustavo Aguilar","orcid":"https://orcid.org/0000-0002-3028-7626","observed_orcids":["https://orcid.org/0000-0002-3028-7626"]},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gustavo Aguilar","raw_affiliation_strings":["University of Houston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091009689","display_name":"Viktor Rozgi\u0107","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor Rozgic","raw_affiliation_strings":["University of Houston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X","observed_orcids":["https://orcid.org/0009-0000-0843-707X"]},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiran Wang","raw_affiliation_strings":["University of Houston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115076700","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-4887-923X","observed_orcids":["https://orcid.org/0000-0003-4887-923X","https://orcid.org/0009-0004-9858-2500","https://orcid.org/0000-0002-1858-1005"]},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["University of Houston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":8.5196,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.9785372,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"991","last_page":"1002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9970999956130981,"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":0.9970999956130981,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.001500000013038516,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0008999999845400453,"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/emotion-recognition","display_name":"emotion recognition","score":0.9860000014305115},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.8080000281333923},{"id":"https://openalex.org/keywords/lexical-information","display_name":"lexical data","score":0.6620000004768372},{"id":"https://openalex.org/keywords/acoustic-characteristics","display_name":"acoustic features","score":0.8399999737739563},{"id":"https://openalex.org/keywords/multi-view-learning","display_name":"multi-view learning","score":0.8650000095367432},{"id":"https://openalex.org/keywords/contrastive-loss","display_name":"contrastive loss","score":0.8159999847412109},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.8429999947547913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8224803805351257},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7041177749633789},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6267633438110352},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5545774102210999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5013303756713867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4954115152359009},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4919290542602539},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4608319401741028},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42467665672302246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4046799838542938},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/p19-1095","doi":"https://doi.org/10.18653/v1/p19-1095","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1095","pdf_url":"https://www.aclweb.org/anthology/P19-1095.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.10198","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.10198","pdf_url":"https://arxiv.org/pdf/1906.10198","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1906.10198","doi":"https://doi.org/10.48550/arxiv.1906.10198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.10198","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1095","doi":"https://doi.org/10.18653/v1/p19-1095","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1095","pdf_url":"https://www.aclweb.org/anthology/P19-1095.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952307697.pdf","grobid_xml":"https://content.openalex.org/works/W2952307697.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1523385540","https://openalex.org/W1534131679","https://openalex.org/W1670132599","https://openalex.org/W1836465849","https://openalex.org/W1883346539","https://openalex.org/W2048679005","https://openalex.org/W2090777335","https://openalex.org/W2095705004","https://openalex.org/W2098689807","https://openalex.org/W2133564696","https://openalex.org/W2144005487","https://openalex.org/W2146334809","https://openalex.org/W2170876097","https://openalex.org/W2171198878","https://openalex.org/W2402040300","https://openalex.org/W2402302915","https://openalex.org/W2533262878","https://openalex.org/W2557283755","https://openalex.org/W2566587499","https://openalex.org/W2587372848","https://openalex.org/W2738581557","https://openalex.org/W2740659164","https://openalex.org/W2767461737","https://openalex.org/W2787560479","https://openalex.org/W2790793790","https://openalex.org/W2795867901","https://openalex.org/W2805662932","https://openalex.org/W2896584247","https://openalex.org/W2949117887","https://openalex.org/W2963702064","https://openalex.org/W2964121744","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W4220856327","https://openalex.org/W4372341189","https://openalex.org/W4405709339","https://openalex.org/W2973062889","https://openalex.org/W3096723250","https://openalex.org/W7148616616","https://openalex.org/W4387664134","https://openalex.org/W4309799497","https://openalex.org/W3136644942","https://openalex.org/W2997949149"],"abstract_inverted_index":{"Studies":[0],"on":[1,24,146,151],"emotion":[2],"recognition":[3],"(ER)":[4],"show":[5],"that":[6,84,106,163],"combining":[7,70],"lexical":[8,73,88,107,152],"and":[9,16,33,72,95,153],"acoustic":[10,71,82,154,158,169],"information":[11,108,123],"results":[12],"in":[13,31,35,50],"more":[14],"robust":[15],"accurate":[17],"models.The":[18],"majority":[19],"of":[20,68,103,143],"the":[21,41,66,101,104,113,140,144,147],"studies":[22],"focus":[23],"settings":[25],"where":[26],"both":[27],"modalities":[28,74],"are":[29],"available":[30],"training":[32,76],"evaluation.However,":[34],"practice,":[36],"this":[37,62],"is":[38],"not":[39,86],"always":[40],"case;":[42],"getting":[43],"ASR":[44],"output":[45],"may":[46],"represent":[47],"a":[48,51,80,116,125,133],"bottleneck":[49],"deployment":[52],"pipeline":[53],"due":[54],"to":[55,99,120],"computational":[56],"complexity":[57],"or":[58],"privacyrelated":[59],"constraints.To":[60],"address":[61],"challenge,":[63],"we":[64,111],"study":[65],"problem":[67,119],"efficiently":[69],"during":[75],"while":[77],"still":[78],"providing":[79],"deployable":[81],"model":[83,127,138],"does":[85],"require":[87],"inputs.We":[89],"first":[90],"experiment":[91],"with":[92,168],"multimodal":[93,126,137],"models":[94,162],"two":[96],"attention":[97],"mechanisms":[98],"assess":[100],"extent":[102],"benefits":[105],"can":[109],"provide.Then,":[110],"frame":[112],"task":[114],"as":[115],"multi-view":[117],"learning":[118],"induce":[121],"semantic":[122],"from":[124],"into":[128],"our":[129,156],"acoustic-only":[130],"network":[131,159],"using":[132],"contrastive":[134],"loss":[135],"function.Our":[136],"outperforms":[139],"previous":[141],"state":[142],"art":[145],"USC-IEMOCAP":[148],"dataset":[149],"reported":[150],"information.Additionally,":[155],"multi-view-trained":[157],"significantly":[160],"surpasses":[161],"have":[164],"been":[165],"exclusively":[166],"trained":[167],"features.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2019-06-27T00:00:00"}