{"id":"https://openalex.org/W2624340939","doi":"https://doi.org/10.1109/taffc.2017.2713783","title":"Audio-Visual Emotion Recognition in Video Clips","display_name":"Audio-Visual Emotion Recognition in Video Clips","publication_year":2017,"publication_date":"2017-06-09","ids":{"openalex":"https://openalex.org/W2624340939","doi":"https://doi.org/10.1109/taffc.2017.2713783","mag":"2624340939"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2017.2713783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2017.2713783","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.lboro.ac.uk/2134/37902","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053780228","display_name":"Fatemeh Noroozi","orcid":"https://orcid.org/0000-0002-4618-1375"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Fatemeh Noroozi","raw_affiliation_strings":["Institute of Technology, University of Tartu, Tartu, Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Technology, University of Tartu, Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020121219","display_name":"Marina Marjanovi\u0107","orcid":"https://orcid.org/0000-0002-1213-882X"},"institutions":[{"id":"https://openalex.org/I170253739","display_name":"Singidunum University","ror":"https://ror.org/017v7rz39","country_code":"RS","type":"education","lineage":["https://openalex.org/I170253739"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Marina Marjanovic","raw_affiliation_strings":["Faculty of Technical Sciences, Singidunum University, Belgrade, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Technical Sciences, Singidunum University, Belgrade, Serbia","institution_ids":["https://openalex.org/I170253739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026443661","display_name":"Angelina Njegu\u0161","orcid":"https://orcid.org/0000-0001-8682-7014"},"institutions":[{"id":"https://openalex.org/I170253739","display_name":"Singidunum University","ror":"https://ror.org/017v7rz39","country_code":"RS","type":"education","lineage":["https://openalex.org/I170253739"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Angelina Njegus","raw_affiliation_strings":["Faculty of Technical Sciences, Singidunum University, Belgrade, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Technical Sciences, Singidunum University, Belgrade, Serbia","institution_ids":["https://openalex.org/I170253739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038228433","display_name":"S\u00e9rgio Escalera","orcid":"https://orcid.org/0000-0003-0617-8873"},"institutions":[{"id":"https://openalex.org/I71999127","display_name":"Universitat de Barcelona","ror":"https://ror.org/021018s57","country_code":"ES","type":"education","lineage":["https://openalex.org/I71999127"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sergio Escalera","raw_affiliation_strings":["Department of Mathematics and Informatics, University of Barcelona, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0003-0617-8873","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Informatics, University of Barcelona, Barcelona, Spain","institution_ids":["https://openalex.org/I71999127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005605270","display_name":"Gholamreza Anbarjafari","orcid":"https://orcid.org/0000-0001-8460-5717"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Gholamreza Anbarjafari","raw_affiliation_strings":["iCV Research Group, Institute of Technology, University of Tartu, Tartu, Estonia"],"raw_orcid":"https://orcid.org/0000-0001-8460-5717","affiliations":[{"raw_affiliation_string":"iCV Research Group, Institute of Technology, University of Tartu, Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.4602,"has_fulltext":false,"cited_by_count":267,"citation_normalized_percentile":{"value":0.99363625,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"10","issue":"1","first_page":"60","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9991000294685364,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7411789298057556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6345176696777344},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5712352991104126},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5576813220977783},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5069308876991272},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4920205771923065},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.4827239215373993},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4754718840122223},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4520632028579712},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.449402779340744},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4448014497756958},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.44456571340560913},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.42921534180641174},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38100069761276245},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36083102226257324},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3542238473892212},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.13085374236106873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411789298057556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6345176696777344},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5712352991104126},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5576813220977783},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5069308876991272},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4920205771923065},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.4827239215373993},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4754718840122223},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4520632028579712},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.449402779340744},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4448014497756958},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44456571340560913},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.42921534180641174},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38100069761276245},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36083102226257324},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3542238473892212},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.13085374236106873},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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:10.1109/taffc.2017.2713783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2017.2713783","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-article"},{"id":"pmh:oai:dspace.lboro.ac.uk:2134/37902","is_oa":true,"landing_page_url":"https://dspace.lboro.ac.uk/2134/37902","pdf_url":null,"source":{"id":"https://openalex.org/S4306401023","display_name":"Loughborough University Institutional Repository (Loughborough University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I143804889","host_organization_name":"Loughborough University","host_organization_lineage":["https://openalex.org/I143804889"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:openaccess.hku.edu.tr:20.500.11782/574","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11782/574","pdf_url":null,"source":{"id":"https://openalex.org/S4306401159","display_name":"Hasan Kalyoncu University Institutional Repository (Hasan Kalyoncu University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210154391","host_organization_name":"Hasan Kalyoncu University","host_organization_lineage":["https://openalex.org/I4210154391"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:dspace.lboro.ac.uk:2134/37902","is_oa":true,"landing_page_url":"https://dspace.lboro.ac.uk/2134/37902","pdf_url":null,"source":{"id":"https://openalex.org/S4306401023","display_name":"Loughborough University Institutional Repository (Loughborough University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I143804889","host_organization_name":"Loughborough University","host_organization_lineage":["https://openalex.org/I143804889"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6700000166893005}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W84641558","https://openalex.org/W114517082","https://openalex.org/W132837572","https://openalex.org/W849766940","https://openalex.org/W1119298599","https://openalex.org/W1480583224","https://openalex.org/W1521476198","https://openalex.org/W1528280116","https://openalex.org/W1529943034","https://openalex.org/W1559788381","https://openalex.org/W1587355710","https://openalex.org/W1701721925","https://openalex.org/W1869734671","https://openalex.org/W1901075642","https://openalex.org/W1967844720","https://openalex.org/W1983018143","https://openalex.org/W1984389434","https://openalex.org/W1990833761","https://openalex.org/W1996218183","https://openalex.org/W2019096742","https://openalex.org/W2026093575","https://openalex.org/W2027562013","https://openalex.org/W2036727939","https://openalex.org/W2042700175","https://openalex.org/W2060079959","https://openalex.org/W2071249869","https://openalex.org/W2087914506","https://openalex.org/W2090240826","https://openalex.org/W2097117768","https://openalex.org/W2101193678","https://openalex.org/W2106433180","https://openalex.org/W2118512999","https://openalex.org/W2119821739","https://openalex.org/W2126552487","https://openalex.org/W2129291408","https://openalex.org/W2130125713","https://openalex.org/W2134008851","https://openalex.org/W2143215363","https://openalex.org/W2148154194","https://openalex.org/W2162418306","https://openalex.org/W2166835339","https://openalex.org/W2168692779","https://openalex.org/W2234589100","https://openalex.org/W2332270997","https://openalex.org/W2339042347","https://openalex.org/W2404873702","https://openalex.org/W2406846344","https://openalex.org/W2413641397","https://openalex.org/W2474425654","https://openalex.org/W2510725918","https://openalex.org/W2587299955","https://openalex.org/W2589993082","https://openalex.org/W2597780659","https://openalex.org/W2608956662","https://openalex.org/W2727455004","https://openalex.org/W2911964244","https://openalex.org/W2949868867","https://openalex.org/W3210693441","https://openalex.org/W4206906090","https://openalex.org/W4239510810","https://openalex.org/W4249328408","https://openalex.org/W4298354116","https://openalex.org/W6628771001","https://openalex.org/W6631696408","https://openalex.org/W6631707306","https://openalex.org/W6634989455","https://openalex.org/W6659283891","https://openalex.org/W6660909453","https://openalex.org/W6678892181","https://openalex.org/W6689519716","https://openalex.org/W6713322803","https://openalex.org/W6725236325"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W4398164220","https://openalex.org/W2745497104","https://openalex.org/W2773864994","https://openalex.org/W2775620487","https://openalex.org/W1997400788","https://openalex.org/W2112393832","https://openalex.org/W2722112567","https://openalex.org/W4298012442","https://openalex.org/W2777738607"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,60,79,104,117],"multimodal":[4],"emotion":[5,113],"recognition":[6],"system,":[7],"which":[8,65],"is":[9,83],"based":[10],"on":[11,124],"the":[12,20,35,72,94,98,125,145],"analysis":[13],"of":[14,63,92],"audio":[15,21],"and":[16,29,49,128],"visual":[17,36],"cues.":[18],"From":[19],"channel,":[22],"Mel-Frequency":[23],"Cepstral":[24],"Coefficients,":[25],"Filter":[26],"Bank":[27],"Energies":[28],"prosodic":[30],"features":[31],"are":[32,40,51,66,100],"extracted.":[33],"For":[34],"part,":[37],"two":[38],"strategies":[39],"considered.":[41],"First,":[42],"facial":[43],"landmarks'":[44],"geometric":[45],"relations,":[46],"i.e.,":[47],"distances":[48],"angles,":[50],"computed.":[52],"Second,":[53],"we":[54],"summarize":[55],"each":[56],"emotional":[57],"video":[58],"into":[59],"reduced":[61],"set":[62],"key-frames,":[64],"taught":[67],"to":[68,76,85,102,108,141],"visually":[69],"discriminate":[70],"between":[71],"emotions.":[73],"In":[74],"order":[75],"do":[77],"so,":[78],"convolutional":[80],"neural":[81],"network":[82],"applied":[84],"key-frames":[86],"summarizing":[87],"videos.":[88],"Finally,":[89],"confidence":[90],"outputs":[91],"all":[93,97,149],"classifiers":[95],"from":[96],"modalities":[99],"used":[101],"define":[103],"new":[105],"feature":[106],"space":[107],"be":[109],"learned":[110],"for":[111],"final":[112],"label":[114],"prediction,":[115],"in":[116,139,148],"late":[118],"fusion/stacking":[119],"fashion.":[120],"The":[121],"experiments":[122],"conducted":[123],"SAVEE,":[126],"eNTERFACE'05,":[127],"RML":[129],"databases":[130],"show":[131],"significant":[132],"performance":[133],"improvements":[134],"by":[135],"our":[136],"proposed":[137],"system":[138],"comparison":[140],"current":[142,146],"alternatives,":[143],"defining":[144],"state-of-the-art":[147],"three":[150],"databases.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":46},{"year":2021,"cited_by_count":43},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":4}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2017-06-15T00:00:00"}