{"id":"https://openalex.org/W1869734671","doi":"https://doi.org/10.5220/0001082801450151","title":"LOW-LEVEL FUSION OF AUDIO AND VIDEO FEATURE FOR MULTI-MODAL EMOTION RECOGNITION","display_name":"LOW-LEVEL FUSION OF AUDIO AND VIDEO FEATURE FOR MULTI-MODAL EMOTION RECOGNITION","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W1869734671","doi":"https://doi.org/10.5220/0001082801450151","mag":"1869734671"},"language":"en","primary_location":{"id":"doi:10.5220/0001082801450151","doi":"https://doi.org/10.5220/0001082801450151","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0001082801450151","pdf_url":null,"source":{"id":"https://openalex.org/S4306419275","display_name":"International Conference on Computer Vision Theory and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third International Conference on Computer Vision Theory and Applications","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.5220/0001082801450151","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Matthias Wimmer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Wimmer","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn Wolfgang Schuller","orcid":"https://orcid.org/0000-0002-6478-8699","observed_orcids":["https://orcid.org/0000-0002-6478-8699"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Schuller","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088855123","display_name":"Dejan Arsi\u0107","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dejan Arsic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596","observed_orcids":["https://orcid.org/0000-0003-1096-1596"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Rigoll","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005874088","display_name":"Bernd Radig","orcid":"https://orcid.org/0000-0003-2951-2192","observed_orcids":["https://orcid.org/0000-0003-2951-2192"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bernd Radig","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.879,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.97057305,"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":"145","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0003000000142492354,"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":9.999999747378752e-05,"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/multimodal-emotion-recognition","display_name":"multimodal emotion recognition","score":0.9449999928474426},{"id":"https://openalex.org/keywords/audiovisual-integration","display_name":"audiovisual integration","score":0.7260000109672546},{"id":"https://openalex.org/keywords/low-level-features","display_name":"low-level features","score":0.7570000290870667},{"id":"https://openalex.org/keywords/early-fusion","display_name":"feature-level fusion","score":0.859000027179718},{"id":"https://openalex.org/keywords/decision-level-fusion","display_name":"decision fusion","score":0.6660000085830688},{"id":"https://openalex.org/keywords/audio-visual-synchronization","display_name":"audio-video synchronization","score":0.460999995470047},{"id":"https://openalex.org/keywords/support-vector-machine-classification","display_name":"support vector machine classification","score":0.7670000195503235},{"id":"https://openalex.org/keywords/feature-space-optimization","display_name":"feature space optimization","score":0.8619999885559082},{"id":"https://openalex.org/keywords/emotional-events","display_name":"emotional events","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7936028242111206},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6083379983901978},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5643306374549866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5524055361747742},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4940977394580841},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44654208421707153},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.42918336391448975},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42578035593032837},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42374560236930847},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4176226258277893},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3718993067741394},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5220/0001082801450151","doi":"https://doi.org/10.5220/0001082801450151","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0001082801450151","pdf_url":null,"source":{"id":"https://openalex.org/S4306419275","display_name":"International Conference on Computer Vision Theory and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third International Conference on Computer Vision Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.117.3359","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.117.3359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www9.in.tum.de/papers/pdf/wimmer08lowlevel.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.331.1090","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.331.1090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mmk.ei.tum.de/publ/pdf/08/08wim1.pdf","raw_type":"text"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:76699","doi":null,"is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-766995","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"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":"bookpart"}],"best_oa_location":{"id":"doi:10.5220/0001082801450151","doi":"https://doi.org/10.5220/0001082801450151","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0001082801450151","pdf_url":null,"source":{"id":"https://openalex.org/S4306419275","display_name":"International Conference on Computer Vision Theory and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third International Conference on Computer Vision Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W170282027","https://openalex.org/W1484676170","https://openalex.org/W1591991095","https://openalex.org/W1628541567","https://openalex.org/W2073039128","https://openalex.org/W2093797275","https://openalex.org/W2097041931","https://openalex.org/W2123864036","https://openalex.org/W2131420259","https://openalex.org/W2131445446","https://openalex.org/W2158663709","https://openalex.org/W2171939880","https://openalex.org/W2405494274","https://openalex.org/W3097096317","https://openalex.org/W4230190357"],"related_works":["https://openalex.org/W2036727939","https://openalex.org/W4360868558","https://openalex.org/W2599967332","https://openalex.org/W2962749013","https://openalex.org/W7172355387","https://openalex.org/W4220829848","https://openalex.org/W2787104312","https://openalex.org/W2977809668","https://openalex.org/W7162004855","https://openalex.org/W2981072818"],"abstract_inverted_index":{"Abstract:":[0],"Bimodal":[1],"emotion":[2],"recognition":[3,76],"through":[4],"audiovisual":[5],"feature":[6],"fusion":[7,44,65],"has":[8],"been":[9],"shown":[10,118],"superior":[11],"over":[12],"each":[13],"individual":[14],"modality":[15],"in":[16,72,128],"the":[17,22,57],"past.":[18],"Still,":[19],"synchronization":[20],"of":[21,60,87,114,122],"two":[23],"streams":[24],"is":[25,66,117],"a":[26,34,81,102,120],"challenge,":[27],"as":[28,47],"many":[29,73],"vision":[30],"approaches":[31],"work":[32],"on":[33,119],"frame":[35],"basis":[36],"opposing":[37],"audio":[38,88],"turn-":[39],"or":[40,50],"chunk-basis.":[41],"Therefore,":[42],"late":[43],"schemes":[45],"such":[46],"simple":[48],"logic":[49],"voting":[51],"strategies":[52],"are":[53],"commonly":[54],"used":[55],"for":[56,92,101],"overall":[58],"estimation":[59],"underlying":[61],"affect.":[62],"However,":[63],"early":[64],"known":[67],"to":[68],"be":[69,108],"more":[70],"effective":[71],"other":[74],"multimodal":[75],"tasks.":[77],"We":[78],"therefore":[79],"suggest":[80],"combined":[82,103],"analysis":[83],"by":[84],"descriptive":[85],"statistics":[86],"and":[89],"video":[90],"Low-Level-Descriptors":[91],"subsequent":[93],"static":[94],"SVM":[95],"Classification.":[96],"This":[97],"strategy":[98],"also":[99],"allows":[100],"feature-space":[104],"optimization":[105],"which":[106],"will":[107],"discussed":[109],"herein.":[110],"The":[111],"high":[112],"effectiveness":[113],"this":[115],"approach":[116],"database":[121],"11.5h":[123],"containing":[124],"six":[125],"emotional":[126],"situations":[127],"an":[129],"airplane":[130],"scenario.":[131],"1":[132]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2016-06-24T00:00:00"}