{"id":"https://openalex.org/W2531648894","doi":"https://doi.org/10.1145/2988257.2988264","title":"Multi-Modal Audio, Video and Physiological Sensor Learning for Continuous Emotion Prediction","display_name":"Multi-Modal Audio, Video and Physiological Sensor Learning for Continuous Emotion Prediction","publication_year":2016,"publication_date":"2016-10-12","ids":{"openalex":"https://openalex.org/W2531648894","doi":"https://doi.org/10.1145/2988257.2988264","mag":"2531648894"},"language":"en","primary_location":{"id":"doi:10.1145/2988257.2988264","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2988257.2988264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Workshop on Audio/Visual Emotion Challenge","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/A5111908794","display_name":"Kevin Brady","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kevin Brady","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory, Lexingon, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory, Lexingon, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012323997","display_name":"Youngjune Gwon","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youngjune Gwon","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110620480","display_name":"Pooya Khorrami","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pooya Khorrami","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045340838","display_name":"Elizabeth Godoy","orcid":"https://orcid.org/0009-0001-4520-8396"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Godoy","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061064027","display_name":"William M. Campbell","orcid":"https://orcid.org/0000-0003-1657-5872"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Campbell","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026993630","display_name":"Charlie K. Dagli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charlie Dagli","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas S. Huang","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5111908794"],"corresponding_institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":18.3378,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.99502104,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9965000152587891,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7716361880302429},{"id":"https://openalex.org/keywords/arousal","display_name":"Arousal","score":0.6137853860855103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5757799744606018},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.5677233934402466},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.5385708808898926},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5306134819984436},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5107548236846924},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47487422823905945},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4459993541240692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716361880302429},{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.6137853860855103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5757799744606018},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.5677233934402466},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.5385708808898926},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5306134819984436},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5107548236846924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47487422823905945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4459993541240692},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2988257.2988264","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2988257.2988264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Workshop on Audio/Visual Emotion Challenge","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W87274615","https://openalex.org/W178970520","https://openalex.org/W211912913","https://openalex.org/W1531532259","https://openalex.org/W1810943226","https://openalex.org/W1964757081","https://openalex.org/W1976235033","https://openalex.org/W1990778070","https://openalex.org/W2005418748","https://openalex.org/W2005876975","https://openalex.org/W2015645277","https://openalex.org/W2021913835","https://openalex.org/W2037441721","https://openalex.org/W2041823554","https://openalex.org/W2045528981","https://openalex.org/W2062632672","https://openalex.org/W2076948628","https://openalex.org/W2081835714","https://openalex.org/W2104074072","https://openalex.org/W2105464873","https://openalex.org/W2115252128","https://openalex.org/W2118858186","https://openalex.org/W2146194791","https://openalex.org/W2150409012","https://openalex.org/W2195207531","https://openalex.org/W2202011751","https://openalex.org/W2247869531","https://openalex.org/W2277498883","https://openalex.org/W2281407413","https://openalex.org/W2343253662","https://openalex.org/W2395544453","https://openalex.org/W2399733683","https://openalex.org/W2400979883","https://openalex.org/W6677618333"],"related_works":["https://openalex.org/W2029072726","https://openalex.org/W91913183","https://openalex.org/W1987182177","https://openalex.org/W2736893848","https://openalex.org/W1544055438","https://openalex.org/W3003450285","https://openalex.org/W2085024878","https://openalex.org/W2087245461","https://openalex.org/W4361008003","https://openalex.org/W4310841718"],"abstract_inverted_index":{"The":[0,29,179],"automatic":[1],"determination":[2],"of":[3,18,54,59,82,102,108,168,173,201,209,222],"emotional":[4],"state":[5,155],"from":[6,139],"multimedia":[7,23],"content":[8],"is":[9,159],"an":[10,80,193],"inherently":[11],"challenging":[12],"problem":[13],"with":[14,131,192],"a":[15,37,57,100,154],"broad":[16],"range":[17],"applications":[19],"including":[20,105],"biomedical":[21],"diagnostics,":[22],"retrieval,":[24],"and":[25,42,51,73,92,111,121,141,150,176,206],"human":[26],"computer":[27],"interfaces.":[28],"Audio":[30],"Video":[31],"Emotion":[32,85],"Challenge":[33,86],"(AVEC)":[34],"2016":[35],"provides":[36,79],"well-defined":[38],"framework":[39],"for":[40,47,65,114,161,199,207],"developing":[41],"rigorously":[43],"evaluating":[44],"innovative":[45],"approaches":[46,145],"estimating":[48],"the":[49,63,106,118,166,170,174,183,188,219,226],"arousal":[50,128,175,200],"valence":[52,177,208],"states":[53],"emotion":[55,116],"as":[56],"function":[58],"time.":[60],"It":[61,98],"presents":[62],"opportunity":[64],"investigating":[66],"multimodal":[67],"solutions":[68],"that":[69,164],"include":[70,126],"audio,":[71,119],"video,":[72,120],"physiological":[74,122],"sensor":[75],"signals.":[76],"This":[77],"paper":[78],"overview":[81],"our":[83],"AVEC":[84],"system,":[87],"which":[88],"uses":[89],"multi-feature":[90],"learning":[91,144],"fusion":[93,163],"across":[94],"all":[95],"available":[96],"modalities.":[97],"includes":[99],"number":[101],"technical":[103],"contributions,":[104],"development":[107],"novel":[109],"high-":[110],"low-level":[112],"features":[113,125,136],"modeling":[115,127],"in":[117,129,225],"channels.":[123],"Low-level":[124],"audio":[130],"minimal":[132],"prosodic-based":[133],"descriptors.":[134],"High-level":[135],"are":[137],"derived":[138],"supervised":[140],"unsupervised":[142],"machine":[143],"based":[146],"on":[147,187,217],"sparse":[148],"coding":[149],"deep":[151],"learning.":[152],"Finally,":[153],"space":[156],"estimation":[157],"approach":[158],"applied":[160],"score":[162],"demonstrates":[165],"importance":[167],"exploiting":[169,218],"time-series":[171],"nature":[172,221],"states.":[178],"resulting":[180],"system":[181],"outperforms":[182],"baseline":[184],"systems":[185],"[10]":[186],"test":[189],"evaluation":[190],"set":[191],"achieved":[194],"Concordant":[195],"Correlation":[196],"Coefficient":[197],"(CCC)":[198],"0.770":[202],"vs":[203,211],"0.702":[204],"(baseline)":[205],"0.687":[210],"0.638.":[212],"Future":[213],"work":[214],"will":[215],"focus":[216],"time-varying":[220],"individual":[223],"channels":[224],"multi-modal":[227],"framework.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":14}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}