{"id":"https://openalex.org/W2143926884","doi":"https://doi.org/10.1145/2388676.2388684","title":"Multimodal human behavior analysis","display_name":"Multimodal human behavior analysis","publication_year":2012,"publication_date":"2012-10-22","ids":{"openalex":"https://openalex.org/W2143926884","doi":"https://doi.org/10.1145/2388676.2388684","mag":"2143926884"},"language":"en","primary_location":{"id":"doi:10.1145/2388676.2388684","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2388676.2388684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Multimodal interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/86099","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100566791","display_name":"Yale Song","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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yale Song","raw_affiliation_strings":["Massachusettes Institute of Technology, Cambridge, MA, USA","Massachusettes Institute of Technology,, CAMBRIDGE, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Massachusettes Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusettes Institute of Technology,, CAMBRIDGE, MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081398601","display_name":"Louis\u2013Philippe Morency","orcid":"https://orcid.org/0000-0001-6376-7696"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis-Philippe Morency","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","[University of Southern California Los, Angeles, CA, USA]"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[University of Southern California Los, Angeles, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112777557","display_name":"Randall Davis","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Randall Davis","raw_affiliation_strings":["Massachusettes Institute of Technology, Cambridge, MA, USA","Massachusettes Institute of Technology,, CAMBRIDGE, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Massachusettes Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusettes Institute of Technology,, CAMBRIDGE, MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100566791"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":4.7068,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.96752796,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9980000257492065,"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":0.9847000241279602,"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/modalities","display_name":"Modalities","score":0.713570237159729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6908988952636719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6275863647460938},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.5970619320869446},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.5806151628494263},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.47896483540534973},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.4765496850013733},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.454059362411499},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44401946663856506},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.432148814201355},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4300456643104553},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4248141646385193},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16654551029205322}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.713570237159729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6908988952636719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6275863647460938},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.5970619320869446},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.5806151628494263},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.47896483540534973},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.4765496850013733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.454059362411499},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44401946663856506},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.432148814201355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4300456643104553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4248141646385193},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16654551029205322},{"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/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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2388676.2388684","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2388676.2388684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Multimodal interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/86099","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/86099","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/86099","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/86099","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2114676203","display_name":"HCC: Small: Enabling and Exploring Natural Interaction","funder_award_id":"1018055","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2713275084","display_name":"CIF: Medium: Collaborative Research: Content Delivery over Heterogeneous Networks: Fundamental Limits and Distributed Algorithms","funder_award_id":"1409106","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4212692802","display_name":null,"funder_award_id":"IIS-1118018","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4584167293","display_name":null,"funder_award_id":"N000140910625","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1513861746","https://openalex.org/W1560724230","https://openalex.org/W2093192785","https://openalex.org/W2100235303","https://openalex.org/W2101534792","https://openalex.org/W2104051600","https://openalex.org/W2111645492","https://openalex.org/W2112039577","https://openalex.org/W2125838338","https://openalex.org/W2147880316","https://openalex.org/W2156503193","https://openalex.org/W3029645440","https://openalex.org/W4285719527","https://openalex.org/W4293775970"],"related_works":["https://openalex.org/W4388821065","https://openalex.org/W4389505417","https://openalex.org/W2962931510","https://openalex.org/W4380551887","https://openalex.org/W4285159263","https://openalex.org/W2904518532","https://openalex.org/W4280529741","https://openalex.org/W4293919860","https://openalex.org/W2963650472","https://openalex.org/W4387634401"],"abstract_inverted_index":{"Multimodal":[0],"human":[1],"behavior":[2],"analysis":[3],"is":[4],"a":[5,22,45,53,59,73,110],"challenging":[6],"task":[7,111],"due":[8],"to":[9,25,48,52,88],"the":[10,63,67,97,122],"presence":[11],"of":[12,62,81,96,112],"complex":[13],"nonlinear":[14,46,133],"correlations":[15],"and":[16,35,57,93,114,137],"interactions":[17],"across":[18,69,102,142],"modalities.":[19,70,143],"We":[20,71,105],"present":[21],"novel":[23],"approach":[24,43,108],"this":[26],"problem":[27],"based":[28],"on":[29,109],"Kernel":[30],"Canonical":[31],"Correlation":[32],"Analysis":[33],"(KCCA)":[34],"Multi-view":[36],"Hidden":[37],"Conditional":[38],"Random":[39],"Fields":[40],"(MV-HCRF).":[41],"Our":[42],"uses":[44],"kernel":[47],"map":[49],"multimodal":[50],"data":[51,64],"high-dimensional":[54],"feature":[55],"space":[56],"finds":[58],"new":[60],"projection":[61],"that":[65,129],"maximizes":[66],"correlation":[68],"use":[72],"multi-chain":[74],"structured":[75],"graphical":[76],"model":[77],"with":[78],"disjoint":[79],"sets":[80],"latent":[82],"variables,":[83],"one":[84],"set":[85],"per":[86],"modality,":[87],"jointly":[89],"learn":[90],"both":[91],"view-shared":[92],"view-specific":[94],"sub-structures":[95],"projected":[98],"data,":[99],"capturing":[100,132],"interaction":[101,141],"modalities":[103],"explicitly.":[104],"evaluate":[106],"our":[107],"agreement":[113],"disagreement":[115],"recognition":[116],"from":[117],"nonverbal":[118],"audio-visual":[119],"cues":[120],"using":[121],"Canal":[123],"9":[124],"dataset.":[125],"Experimental":[126],"results":[127],"show":[128],"KCCA":[130],"makes":[131],"hidden":[134],"dynamics":[135],"easier":[136],"MV-HCRF":[138],"helps":[139],"learning":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}