{"id":"https://openalex.org/W1981655197","doi":"https://doi.org/10.1145/2522848.2532593","title":"A multi-modal gesture recognition system using audio, video, and skeletal joint data","display_name":"A multi-modal gesture recognition system using audio, video, and skeletal joint data","publication_year":2013,"publication_date":"2013-11-27","ids":{"openalex":"https://openalex.org/W1981655197","doi":"https://doi.org/10.1145/2522848.2532593","mag":"1981655197"},"language":"en","primary_location":{"id":"doi:10.1145/2522848.2532593","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2522848.2532593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM on International conference on multimodal interaction","raw_type":"proceedings-article"},"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/A5059676452","display_name":"Karthik Nandakumar","orcid":"https://orcid.org/0000-0002-6274-9725"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Karthik Nandakumar","raw_affiliation_strings":["Institute for Infocomm Research, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048137608","display_name":"Kong-Wah Wan","orcid":"https://orcid.org/0000-0002-9844-1108"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kong Wah Wan","raw_affiliation_strings":["Institute for Infocomm Research, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102082692","display_name":"Siu Man Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Siu Man Alice Chan","raw_affiliation_strings":["Institute for Infocomm Research, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014744501","display_name":"Wen Zheng Terence Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wen Zheng Terence Ng","raw_affiliation_strings":["Institute for Infocomm Research, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063101795","display_name":"Jian Gang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jian Gang Wang","raw_affiliation_strings":["Institute for Infocomm Research, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057104857","display_name":"Wei\u2010Yun Yau","orcid":"https://orcid.org/0000-0001-5709-9169"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Yun Yau","raw_affiliation_strings":["Institute for Infocomm Research, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"475","last_page":"482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/gesture","display_name":"Gesture","score":0.9215004444122314},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.7718053460121155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7313457727432251},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7061560153961182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6158918142318726},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5753927826881409},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5429593324661255},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5342833995819092},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5238066911697388},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4600858688354492},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42289164662361145},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.371776819229126}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.9215004444122314},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.7718053460121155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7313457727432251},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7061560153961182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6158918142318726},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5753927826881409},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5429593324661255},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5342833995819092},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5238066911697388},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4600858688354492},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42289164662361145},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.371776819229126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2522848.2532593","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2522848.2532593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM on International conference on multimodal interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W203345490","https://openalex.org/W1568650776","https://openalex.org/W1993014362","https://openalex.org/W1993229407","https://openalex.org/W2020163092","https://openalex.org/W2061272711","https://openalex.org/W2098339052","https://openalex.org/W2110575115","https://openalex.org/W2112628161","https://openalex.org/W2115515280","https://openalex.org/W2116022929","https://openalex.org/W2148154194","https://openalex.org/W2168392347","https://openalex.org/W2984211736","https://openalex.org/W3100876745","https://openalex.org/W6770274813"],"related_works":["https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2028966255","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W2466763065","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W1994032303"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,9,16,37,55,66,99,115,137,146,151,179,184,208,217,224,232,250],"gesture":[4,40,166,194,244],"recognition":[5,195],"system":[6,26,196,219],"developed":[7],"by":[8],"Institute":[10],"for":[11,15,31,126,165],"Infocomm":[12],"Research":[13],"(I2R)":[14],"2013":[17],"ICMI":[18],"CHALEARN":[19],"Multi-modal":[20],"Gesture":[21],"Recognition":[22],"Challenge.":[23],"The":[24,192],"proposed":[25,193,218],"adopts":[27],"a":[28,60,91,119,140,169],"multi-modal":[29],"approach":[30],"detecting":[32],"as":[33,35,247],"well":[34],"recognizing":[36],"gestures.":[38,64,215,253],"Automated":[39],"detection":[41],"is":[42,124,143,172,197,220,245],"performed":[43],"using":[44],"both":[45,154],"audio":[46,116],"signals":[47,117],"and":[48,70,83,118,156,182],"information":[49],"about":[50],"hand":[51],"joints":[52,85],"obtained":[53],"from":[54,74,114,145,177],"Kinect":[56,157],"sensor":[57],"to":[58,89,135,174,199,222,237],"segment":[59],"sample":[61],"into":[62,96],"individual":[63],"Once":[65],"gestures":[67,102,187,226],"are":[68,87,112,133,163,234],"detected":[69],"segmented,":[71],"features":[72],"extracted":[73,113,144],"three":[75,180],"different":[76],"modalities,":[77,158],"namely,":[78],"audio,":[79],"2-dimensional":[80],"video":[81],"(RGB),":[82],"skeletal":[84,147],"(Kinect)":[86],"used":[88,125,134,164],"classify":[90],"given":[92],"sequence":[93,185],"of":[94,98,153,186,205,231,249],"frames":[95],"one":[97,248],"20":[100,251],"known":[101,225,252],"or":[103],"an":[104,201,242],"unrecognized":[105,243],"gesture.":[106],"Mel":[107],"frequency":[108],"cepstral":[109],"coefficients":[110],"(MFCC)":[111],"Hidden":[120],"Markov":[121],"Model":[122],"(HMM)":[123],"classification.":[127,167],"While":[128,216],"Space-Time":[129],"Interest":[130],"Points":[131],"(STIP)":[132],"represent":[136],"RGB":[138,155],"modality,":[139],"covariance":[141],"descriptor":[142],"joint":[148],"data.":[149],"In":[150],"case":[152],"Support":[159],"Vector":[160],"Machines":[161],"(SVM)":[162],"Finally,":[168],"fusion":[170],"scheme":[171],"applied":[173],"accumulate":[175],"evidence":[176],"all":[178],"modalities":[181],"predict":[183],"in":[188],"each":[189],"test":[190,210],"sample.":[191],"able":[198,221],"achieve":[200],"average":[202],"edit":[203],"distance":[204],"0.2074":[206],"over":[207],"275":[209],"samples":[211],"containing":[212],"2,742":[213],"unlabeled":[214],"recognize":[223],"with":[227],"high":[228],"accuracy,":[229],"most":[230],"errors":[233],"caused":[235],"due":[236],"insertion,":[238],"which":[239],"occurs":[240],"when":[241],"misclassified":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}