{"id":"https://openalex.org/W4390484015","doi":"https://doi.org/10.1145/3595916.3626362","title":"Multi-region CNN-Transformer for Micro-gesture Recognition in Face and Upper Body","display_name":"Multi-region CNN-Transformer for Micro-gesture Recognition in Face and Upper Body","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390484015","doi":"https://doi.org/10.1145/3595916.3626362"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626362","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626362","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626362","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626362","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103222069","display_name":"Keita Suzuki","orcid":"https://orcid.org/0009-0006-7963-3952"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Keita Suzuki","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":"https://orcid.org/0009-0006-7963-3952","affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063110877","display_name":"Satoshi Suzuki","orcid":"https://orcid.org/0000-0002-1423-3767"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Suzuki","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":"https://orcid.org/0000-0002-1423-3767","affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":"https://orcid.org/0000-0002-2415-4149","affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061074419","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0002-3971-0654"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":"https://orcid.org/0000-0002-3971-0654","affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082466886","display_name":"Naoki Makishima","orcid":"https://orcid.org/0000-0002-7065-315X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Makishima","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":"https://orcid.org/0000-0002-7065-315X","affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103222069"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.164,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52784907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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/T11448","display_name":"Face recognition and analysis","score":0.9926999807357788,"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/gesture","display_name":"Gesture","score":0.7103016376495361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7079769968986511},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.6576230525970459},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6026294231414795},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.5708706378936768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5199795365333557},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.49859070777893066},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4945509135723114},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4540092349052429},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37623029947280884},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13812196254730225},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08774611353874207},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.053774356842041016}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7103016376495361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7079769968986511},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.6576230525970459},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6026294231414795},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.5708706378936768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5199795365333557},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.49859070777893066},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4945509135723114},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4540092349052429},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37623029947280884},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13812196254730225},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08774611353874207},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.053774356842041016},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595916.3626362","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626362","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626362","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626362","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626362","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626362","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390484015.pdf","grobid_xml":"https://content.openalex.org/works/W4390484015.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1487133565","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2115252128","https://openalex.org/W2546875627","https://openalex.org/W2602856279","https://openalex.org/W2799041689","https://openalex.org/W2912083425","https://openalex.org/W2913668833","https://openalex.org/W2962850830","https://openalex.org/W2963252191","https://openalex.org/W2963631961","https://openalex.org/W3124054989","https://openalex.org/W3174203196","https://openalex.org/W3186300478","https://openalex.org/W4213019189","https://openalex.org/W4242177601"],"related_works":["https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735","https://openalex.org/W2384651879"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,9,30,36,64,77,122],"novel":[4,123],"task":[5],"that":[6,132],"recognizes":[7],"from":[8,136],"video":[10],"unintentional":[11],"micro-gestures":[12],"(UMGs),":[13],"which":[14],"are":[15],"movements":[16],"made":[17],"by":[18,84],"people":[19],"unconsciously":[20],"and":[21,58,76,113,162],"unintentionally.":[22],"Recognizing":[23],"UMGs":[24,96],"is":[25,38,99,148],"crucial":[26],"because":[27,97],"they":[28],"reveal":[29],"person\u2019s":[31],"underlying":[32],"psychological":[33],"state.":[34],"Since":[35],"UMG":[37,126,181],"composed":[39],"of":[40,145,171],"subtle":[41,151],"sequential":[42],"movements,":[43,107],"the":[44,56,73,81,85,88,111,128,157,169,172],"recognition":[45],"model":[46,93,124],"must":[47],"be":[48],"able":[49],"to":[50,69,79,102,149],"capture":[51,70,103,150],"accurate":[52],"information":[53,71],"in":[54,72,87,106,110,153],"both":[55],"spatial":[57,74],"temporal":[59,89],"directions.":[60],"Therefore,":[61],"we":[62,120],"utilize":[63],"convolutional":[65],"neural":[66],"network":[67],"(CNN)":[68],"direction":[75],"Transformer":[78],"merge":[80],"features":[82],"extracted":[83],"CNN":[86],"direction.":[90],"However,":[91],"this":[92,118,184],"often":[94],"misrecognizes":[95],"it":[98],"not":[100],"possible":[101],"slight":[104],"differences":[105],"such":[108,155],"as":[109,156],"face":[112],"mouth":[114,163],"regions.":[115],"To":[116],"address":[117],"issue,":[119],"propose":[121],"for":[125,164,183],"recognition,":[127],"Multi-Region":[129],"CNN-Transformer":[130],"model,":[131],"inputs":[133],"cropped":[134],"videos":[135],"multiple":[137],"upper":[138,158],"body":[139],"regions":[140,154],"simultaneously.":[141],"The":[142],"key":[143],"advance":[144],"our":[146,178],"method":[147,174],"changes":[152],"body,":[159],"face,":[160],"head,":[161],"recognizing":[165],"UMGs.":[166],"We":[167],"demonstrate":[168],"effectiveness":[170],"proposed":[173],"through":[175],"experiments":[176],"using":[177],"newly":[179],"created":[180],"dataset":[182],"task.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}