{"id":"https://openalex.org/W2977259558","doi":"https://doi.org/10.1109/acii.2019.8925444","title":"Multimodal and Temporal Perception of Audio-visual Cues for Emotion Recognition","display_name":"Multimodal and Temporal Perception of Audio-visual Cues for Emotion Recognition","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2977259558","doi":"https://doi.org/10.1109/acii.2019.8925444","mag":"2977259558"},"language":"en","primary_location":{"id":"doi:10.1109/acii.2019.8925444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acii.2019.8925444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII)","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/A5046627420","display_name":"Esam Ghaleb","orcid":"https://orcid.org/0000-0002-0603-9817"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Esam Ghaleb","raw_affiliation_strings":["Department of Data Science and Knowledge Engineering Maastricht, University Maastricht, Maastricht, Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Data Science and Knowledge Engineering Maastricht, University Maastricht, Maastricht, Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015435362","display_name":"Mirela Popa","orcid":"https://orcid.org/0000-0002-6449-1158"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mirela Popa","raw_affiliation_strings":["Department of Data Science and Knowledge Engineering Maastricht, University Maastricht, Maastricht, Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Data Science and Knowledge Engineering Maastricht, University Maastricht, Maastricht, Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040216921","display_name":"Stylianos Asteriadis","orcid":"https://orcid.org/0000-0002-4298-6870"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Stylianos Asteriadis","raw_affiliation_strings":["Department of Data Science and Knowledge Engineering Maastricht, University Maastricht, Maastricht, Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Data Science and Knowledge Engineering Maastricht, University Maastricht, Maastricht, Netherlands","institution_ids":["https://openalex.org/I34352273"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046627420"],"corresponding_institution_ids":["https://openalex.org/I34352273"],"apc_list":null,"apc_paid":null,"fwci":10.8042,"has_fulltext":false,"cited_by_count":91,"citation_normalized_percentile":{"value":0.98699093,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"552","last_page":"558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.6680375933647156},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6541392803192139},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6171904802322388},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5951380729675293},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4932331442832947},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4879414737224579},{"id":"https://openalex.org/keywords/emotion-perception","display_name":"Emotion perception","score":0.46595439314842224},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4355151057243347},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36860033869743347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35965731739997864},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.35920894145965576},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.21740645170211792},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.21236169338226318},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1523779034614563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6680375933647156},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6541392803192139},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6171904802322388},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5951380729675293},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4932331442832947},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4879414737224579},{"id":"https://openalex.org/C2776141551","wikidata":"https://www.wikidata.org/wiki/Q16000087","display_name":"Emotion perception","level":3,"score":0.46595439314842224},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4355151057243347},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36860033869743347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35965731739997864},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.35920894145965576},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.21740645170211792},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.21236169338226318},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1523779034614563},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/acii.2019.8925444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acii.2019.8925444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII)","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.maastrichtuniversity.nl:openaire_cris_publications/bc4e1d6e-e488-43d0-a18c-beaf8707bfcc","is_oa":false,"landing_page_url":"https://cris.maastrichtuniversity.nl/en/publications/bc4e1d6e-e488-43d0-a18c-beaf8707bfcc","pdf_url":null,"source":{"id":"https://openalex.org/S4306402616","display_name":"Research Publications (Maastricht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I34352273","host_organization_name":"Maastricht University","host_organization_lineage":["https://openalex.org/I34352273"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ghaleb, E, Popa, M & Asteriadis, S 2019, Multimodal and Temporal Perception of Audio-visual Cues for Emotion Recognition. in 8th International Conference on Affective Computing & Intelligent Interaction (ACII 2019), Cambridge, United Kingdom. pp. 552-558. https://doi.org/10.1109/ACII.2019.8925444","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1854772995","https://openalex.org/W1885777359","https://openalex.org/W1968106821","https://openalex.org/W2015394094","https://openalex.org/W2030931454","https://openalex.org/W2096733369","https://openalex.org/W2106053110","https://openalex.org/W2138396459","https://openalex.org/W2156503193","https://openalex.org/W2184188583","https://openalex.org/W2298261874","https://openalex.org/W2497173630","https://openalex.org/W2546702061","https://openalex.org/W2546875627","https://openalex.org/W2555897561","https://openalex.org/W2593216954","https://openalex.org/W2619383789","https://openalex.org/W2767325013","https://openalex.org/W2797653144","https://openalex.org/W2803193013","https://openalex.org/W2808859004","https://openalex.org/W2886300652","https://openalex.org/W2899366898","https://openalex.org/W2907891676","https://openalex.org/W2909902844","https://openalex.org/W2919115771","https://openalex.org/W2962756039","https://openalex.org/W2962905870","https://openalex.org/W2963516811","https://openalex.org/W2963524571","https://openalex.org/W3099206234","https://openalex.org/W3103205982","https://openalex.org/W3122451732","https://openalex.org/W4239973432","https://openalex.org/W4293665662","https://openalex.org/W4396952261","https://openalex.org/W6675751002","https://openalex.org/W6686207219","https://openalex.org/W6690073643","https://openalex.org/W6729831399","https://openalex.org/W6730323794","https://openalex.org/W6756086341","https://openalex.org/W6789185007"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"In":[0,38,73],"Audio-Video":[1],"Emotion":[2],"Recognition":[3],"(AVER),":[4],"the":[5,70,129,153],"idea":[6],"is":[7,19,100,108,139],"to":[8,22,31,120],"have":[9],"a":[10,20,28,52,78,94,161],"human-level":[11],"understanding":[12],"of":[13,47,54,134,164],"emotions":[14,49,65],"from":[15],"video":[16,87],"clips.":[17],"There":[18],"need":[21],"bring":[23],"these":[24],"two":[25,112,142],"modalities":[26],"into":[27],"unified":[29],"framework,":[30],"effectively":[32],"learn":[33],"multimodal":[34,80,165],"fusion":[35],"for":[36],"AVER.":[37],"addition,":[39],"literature":[40],"studies":[41,59],"lack":[42],"in-depth":[43],"analysis":[44],"and":[45,57,63,102,105,123,132,145,159,166],"utilization":[46],"how":[48,116,125],"vary":[50],"as":[51],"function":[53],"time.":[55],"Psychological":[56],"neurological":[58],"show":[60],"that":[61,85],"negative":[62],"positive":[64],"are":[66,150],"not":[67],"recognized":[68],"at":[69],"same":[71],"speed.":[72],"this":[74],"paper,":[75],"we":[76],"propose":[77],"novel":[79],"temporal":[81,126,167],"deep":[82],"network":[83],"framework":[84],"embeds":[86],"clips":[88],"using":[89],"their":[90,98,103],"audio-visual":[91,117],"content,":[92],"onto":[93],"metric":[95],"space,":[96],"where":[97],"gap":[99],"reduced":[101],"complementary":[104],"supplementary":[106],"information":[107,127],"explored.":[109],"We":[110],"address":[111],"research":[113],"questions,":[114],"(1)":[115],"cues":[118],"contribute":[119],"emotion":[121,168],"recognition":[122,130],"(2)":[124],"impacts":[128],"rate":[131],"speed":[133],"emotions.":[135],"The":[136,147],"proposed":[137],"method":[138],"evaluated":[140],"on":[141,156],"datasets,":[143,158],"CREMA-D":[144],"RAVDESS.":[146],"study":[148],"findings":[149],"promising,":[151],"achieving":[152],"state-of-the-art":[154],"performance":[155],"both":[157],"showing":[160],"significant":[162],"impact":[163],"perception.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":12}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}
