{"id":"https://openalex.org/W2612041314","doi":"https://doi.org/10.1109/wacv.2017.140","title":"Deep Spatio-Temporal Features for Multimodal Emotion Recognition","display_name":"Deep Spatio-Temporal Features for Multimodal Emotion Recognition","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2612041314","doi":"https://doi.org/10.1109/wacv.2017.140","mag":"2612041314"},"language":"en","primary_location":{"id":"doi:10.1109/wacv.2017.140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv.2017.140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Winter Conference on Applications of Computer Vision (WACV)","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/A5103039763","display_name":"Dung Nguyen","orcid":"https://orcid.org/0000-0001-7042-7788"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dung Nguyen","raw_affiliation_strings":["Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038839161","display_name":"Kien Nguyen","orcid":"https://orcid.org/0000-0002-3466-9218"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kien Nguyen","raw_affiliation_strings":["Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065910961","display_name":"Afsane Ghasemi","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Afsane Ghasemi","raw_affiliation_strings":["Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000014182","display_name":"David Dean","orcid":"https://orcid.org/0000-0003-1274-9775"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Dean","raw_affiliation_strings":["Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034095159","display_name":"Clinton Fookes","orcid":"https://orcid.org/0000-0002-8515-6324"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Clinton Fookes","raw_affiliation_strings":["Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":9.1244,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.98397316,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1215","last_page":"1223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9968000054359436,"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":0.7964480519294739},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6606048345565796},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6084286570549011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5957332849502563},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5871864557266235},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5686101913452148},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5622903108596802},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5157573223114014},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.49241864681243896},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4519665837287903},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4184038043022156},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38166487216949463},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37525853514671326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964480519294739},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6606048345565796},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6084286570549011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5957332849502563},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5871864557266235},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5686101913452148},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5622903108596802},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5157573223114014},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.49241864681243896},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4519665837287903},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4184038043022156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38166487216949463},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37525853514671326},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wacv.2017.140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv.2017.140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:105854","is_oa":false,"landing_page_url":"http://purl.org/au-research/grants/arc/DP140100793","pdf_url":null,"source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W28988658","https://openalex.org/W164066603","https://openalex.org/W1522021943","https://openalex.org/W1522734439","https://openalex.org/W1539625571","https://openalex.org/W1586730761","https://openalex.org/W1587120099","https://openalex.org/W1587870007","https://openalex.org/W1592254367","https://openalex.org/W1601218598","https://openalex.org/W1869734671","https://openalex.org/W1983364832","https://openalex.org/W2009059481","https://openalex.org/W2042684846","https://openalex.org/W2059348974","https://openalex.org/W2071249869","https://openalex.org/W2097618823","https://openalex.org/W2099846230","https://openalex.org/W2100474751","https://openalex.org/W2110798204","https://openalex.org/W2111623727","https://openalex.org/W2115135068","https://openalex.org/W2122458510","https://openalex.org/W2132860741","https://openalex.org/W2136922672","https://openalex.org/W2140000523","https://openalex.org/W2142653084","https://openalex.org/W2143350951","https://openalex.org/W2146835635","https://openalex.org/W2155893237","https://openalex.org/W2158419735","https://openalex.org/W2163685610","https://openalex.org/W2164471543","https://openalex.org/W2168692779","https://openalex.org/W2170950676","https://openalex.org/W2171880639","https://openalex.org/W2181741066","https://openalex.org/W2275733078","https://openalex.org/W2284127411","https://openalex.org/W2406223855","https://openalex.org/W2525648609","https://openalex.org/W2546253415","https://openalex.org/W2919115771","https://openalex.org/W3097096317","https://openalex.org/W6635259260","https://openalex.org/W6639121642","https://openalex.org/W6674437205","https://openalex.org/W6729220966","https://openalex.org/W7075385858"],"related_works":["https://openalex.org/W4389505417","https://openalex.org/W2962931510","https://openalex.org/W4380551887","https://openalex.org/W2945121592","https://openalex.org/W2904518532","https://openalex.org/W4285159263","https://openalex.org/W4280529741","https://openalex.org/W4293919860","https://openalex.org/W2963650472","https://openalex.org/W2014713986"],"abstract_inverted_index":{"Automatic":[0],"emotion":[1,86,96],"recognition":[2,97],"has":[3,29],"attracted":[4],"great":[5],"interest":[6],"and":[7,77,99],"numerous":[8],"solutions":[9],"have":[10],"been":[11],"proposed,":[12],"most":[13],"of":[14],"which":[15],"focus":[16],"either":[17],"individually":[18],"on":[19,82],"facial":[20],"expression":[21],"or":[22],"acoustic":[23],"information.":[24],"While":[25],"more":[26],"recent":[27,102],"research":[28],"considered":[30],"multimodal":[31,68,85,95],"approaches,":[32],"individual":[33],"modalities":[34],"are":[35],"often":[36],"combined":[37],"only":[38],"by":[39],"simple":[40],"fusion":[41],"at":[42],"the":[43,63,75,83],"feature":[44],"and/or":[45],"decision-level.":[46],"In":[47],"this":[48,90],"paper,":[49],"we":[50],"introduce":[51],"a":[52],"novel":[53],"approach":[54,91],"using":[55],"3-dimensional":[56],"convolutional":[57],"neural":[58],"networks":[59,70],"(C3Ds)":[60],"to":[61,93],"model":[62],"spatio-temporal":[64],"information,":[65],"cascaded":[66],"with":[67],"deep-belief":[69],"(DBNs)":[71],"that":[72,89],"can":[73],"represent":[74],"audio":[76],"video":[78],"streams.":[79],"Experiments":[80],"conducted":[81],"eNTERFACE":[84],"database":[87],"demonstrate":[88],"leads":[92],"improved":[94],"performance":[98],"significantly":[100],"outperforms":[101],"state-of-the-art":[103],"proposals.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}