{"id":"https://openalex.org/W2018549299","doi":"https://doi.org/10.1109/icassp.2007.366340","title":"Audiovisual Behavior Modeling by Combined Feature Spaces","display_name":"Audiovisual Behavior Modeling by Combined Feature Spaces","publication_year":2007,"publication_date":"2007-04-01","ids":{"openalex":"https://openalex.org/W2018549299","doi":"https://doi.org/10.1109/icassp.2007.366340","mag":"2018549299"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2007.366340","doi":"https://doi.org/10.1109/icassp.2007.366340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2007.366340","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07","raw_type":"proceedings-article"},"volume":null,"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/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":"Bjorn Schuller","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","Inst. for Human-Machine Commun., Tech. Univ. Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Tech. Univ. Munchen, 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":[{"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":"Dejan Arsic","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","Inst. for Human-Machine Commun., Tech. Univ. Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Tech. Univ. Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"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":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","Inst. for Human-Machine Commun., Tech. Univ. Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Tech. Univ. Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","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":["Department of Informatics, Technische Universit\u00e4t M\u00fcnchen, Garching, Germany","Technische Universit\u00e4t M\u00fcnchen, Department of Informatics, Boltzmannstr. 3, 85748 Garching, Germany. wimmerm@cs.tum.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technische Universit\u00e4t M\u00fcnchen, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen, Department of Informatics, Boltzmannstr. 3, 85748 Garching, Germany. wimmerm@cs.tum.edu","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":[{"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":"Bernd Radig","raw_affiliation_strings":["Department of Informatics, Technische Universit\u00e4t M\u00fcnchen, Garching, Germany","Technische Universit\u00e4t M\u00fcnchen, Department of Informatics, Boltzmannstr. 3, 85748 Garching, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technische Universit\u00e4t M\u00fcnchen, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen, Department of Informatics, Boltzmannstr. 3, 85748 Garching, Germany#TAB#","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":8.0693,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.97554492,"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":"II","last_page":"733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9092000126838684,"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":0.9092000126838684,"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":0.0272000003606081,"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":0.013100000098347664,"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/multimodal-fusion","display_name":"multimodal fusion","score":0.8820000290870667},{"id":"https://openalex.org/keywords/audio-visual-synchronization","display_name":"audio-video synchronization","score":0.6690000295639038},{"id":"https://openalex.org/keywords/low-level-descriptors","display_name":"low-level descriptors","score":0.7120000123977661},{"id":"https://openalex.org/keywords/multivariate-time-series-analysis","display_name":"multivariate time series analysis","score":0.9739999771118164},{"id":"https://openalex.org/keywords/public-surveillance","display_name":"public surveillance","score":0.8080000281333923},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"emotion recognition","score":0.5260000228881836},{"id":"https://openalex.org/keywords/behavior-classification","display_name":"behavior classification","score":0.36000001430511475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7729097008705139},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7683699727058411},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6810414791107178},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6381099224090576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.522952139377594},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.457295298576355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4052259922027588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3701484799385071},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32458049058914185},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2007.366340","doi":"https://doi.org/10.1109/icassp.2007.366340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2007.366340","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6299999952316284}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W170282027","https://openalex.org/W1628541567","https://openalex.org/W1983634995","https://openalex.org/W2032254851","https://openalex.org/W2039792682","https://openalex.org/W2073039128","https://openalex.org/W2110052520","https://openalex.org/W2118877769","https://openalex.org/W2123864036","https://openalex.org/W2131445446","https://openalex.org/W2154716422","https://openalex.org/W2159017231","https://openalex.org/W2164598857","https://openalex.org/W2171939880","https://openalex.org/W3140954725","https://openalex.org/W4239447739"],"related_works":["https://openalex.org/W7098151136","https://openalex.org/W2345127196","https://openalex.org/W1869734671","https://openalex.org/W2140647972","https://openalex.org/W2066084510","https://openalex.org/W2106336084","https://openalex.org/W2130239535","https://openalex.org/W1970906983","https://openalex.org/W4392904679","https://openalex.org/W2405275421"],"abstract_inverted_index":{"Great":[0],"interest":[1],"is":[2,16,73],"recently":[3],"shown":[4],"in":[5,9,92],"behavior":[6,91],"modeling,":[7],"especially":[8],"public":[10],"surveillance":[11],"tasks.":[12],"In":[13],"general":[14],"it":[15],"agreed":[17],"upon":[18],"the":[19,40],"benefits":[20],"of":[21,23,35,83],"use":[22],"several":[24],"input":[25],"cues":[26],"as":[27,67],"audio":[28],"and":[29,33,60,70,89],"video.":[30],"Yet,":[31],"synchronization":[32],"fusion":[34],"these":[36],"information":[37],"sources":[38],"remains":[39],"main":[41],"challenge.":[42],"We":[43],"therefore":[44],"show":[45,96],"results":[46],"for":[47,54],"a":[48,81,97],"feature":[49,56,71],"space":[50,57],"combination,":[51],"which":[52],"allows":[53],"overall":[55],"optimization.":[58],"Audio":[59],"video":[61],"features":[62],"are":[63],"thereby":[64],"firstly":[65],"derived":[66],"low-level-descriptors.":[68],"Synchronization":[69],"combination":[72],"achieved":[74],"by":[75],"multivariate":[76],"time-series":[77],"analysis.":[78],"Test-runs":[79],"on":[80],"database":[82],"aggressive,":[84],"cheerful,":[85],"intoxicated,":[86],"nervous,":[87],"neutral,":[88],"tired":[90],"an":[93],"airplane":[94],"situation":[95],"significant":[98],"improvement":[99],"over":[100],"each":[101],"single":[102],"modality.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}
