{"id":"https://openalex.org/W4396629578","doi":"https://doi.org/10.1109/lsp.2024.3396656","title":"Enhancing Micro Gesture Recognition for Emotion Understanding via Context-Aware Visual-Text Contrastive Learning","display_name":"Enhancing Micro Gesture Recognition for Emotion Understanding via Context-Aware Visual-Text Contrastive Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396629578","doi":"https://doi.org/10.1109/lsp.2024.3396656"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3396656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3396656","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.01885","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100671326","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-7140-0701"},"institutions":[{"id":"https://openalex.org/I63548447","display_name":"Lappeenranta-Lahti University of Technology","ror":"https://ror.org/0208vgz68","country_code":"FI","type":"education","lineage":["https://openalex.org/I63548447"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Deng Li","raw_affiliation_strings":["Computer Vision and Pattern Recognition Laboratory, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland"],"raw_orcid":"https://orcid.org/0000-0002-7140-0701","affiliations":[{"raw_affiliation_string":"Computer Vision and Pattern Recognition Laboratory, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland","institution_ids":["https://openalex.org/I63548447"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059997187","display_name":"Bohao Xing","orcid":"https://orcid.org/0009-0005-5924-4178"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I63548447","display_name":"Lappeenranta-Lahti University of Technology","ror":"https://ror.org/0208vgz68","country_code":"FI","type":"education","lineage":["https://openalex.org/I63548447"]}],"countries":["CN","FI"],"is_corresponding":false,"raw_author_name":"Bohao Xing","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China","Computer Vision and Pattern Recognition Laboratory, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland"],"raw_orcid":"https://orcid.org/0009-0005-5924-4178","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Computer Vision and Pattern Recognition Laboratory, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland","institution_ids":["https://openalex.org/I63548447"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058509635","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-2242-6139"},"institutions":[{"id":"https://openalex.org/I63548447","display_name":"Lappeenranta-Lahti University of Technology","ror":"https://ror.org/0208vgz68","country_code":"FI","type":"education","lineage":["https://openalex.org/I63548447"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["Computer Vision and Pattern Recognition Laboratory, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland"],"raw_orcid":"https://orcid.org/0000-0002-2242-6139","affiliations":[{"raw_affiliation_string":"Computer Vision and Pattern Recognition Laboratory, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland","institution_ids":["https://openalex.org/I63548447"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0874,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.95052776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"1309","last_page":"1313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.7542102932929993},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7462063431739807},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5618962049484253},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4970081150531769},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.49184179306030273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48438960313796997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45731067657470703},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40444520115852356},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38705122470855713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3269869089126587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7542102932929993},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7462063431739807},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5618962049484253},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4970081150531769},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.49184179306030273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48438960313796997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45731067657470703},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40444520115852356},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38705122470855713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3269869089126587},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2024.3396656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3396656","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2405.01885","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.01885","pdf_url":"https://arxiv.org/pdf/2405.01885","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.01885","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.01885","pdf_url":"https://arxiv.org/pdf/2405.01885","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396629578.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1483803373","https://openalex.org/W2078951341","https://openalex.org/W2080830759","https://openalex.org/W2143993797","https://openalex.org/W2745497104","https://openalex.org/W2885005742","https://openalex.org/W2912159753","https://openalex.org/W2956286548","https://openalex.org/W2963076818","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2978017171","https://openalex.org/W2989506443","https://openalex.org/W2990152177","https://openalex.org/W3006913151","https://openalex.org/W3008392994","https://openalex.org/W3034548564","https://openalex.org/W3035050855","https://openalex.org/W3035225512","https://openalex.org/W3035967853","https://openalex.org/W3081152303","https://openalex.org/W3093581966","https://openalex.org/W3120179362","https://openalex.org/W3122081138","https://openalex.org/W3170161070","https://openalex.org/W3177709384","https://openalex.org/W3200367795","https://openalex.org/W3209114384","https://openalex.org/W4312813763","https://openalex.org/W4316660592","https://openalex.org/W4321101505","https://openalex.org/W4361026734","https://openalex.org/W4385245566","https://openalex.org/W6629077732","https://openalex.org/W6683161245","https://openalex.org/W6757817989","https://openalex.org/W6768851824","https://openalex.org/W6791353385"],"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/W3126677997"],"abstract_inverted_index":{"Psychological":[0],"studies":[1],"have":[2],"shown":[3],"that":[4,87,120,147],"Micro":[5,55],"Gestures":[6],"(MG)":[7],"are":[8],"closely":[9],"linked":[10],"to":[11,45,112,160],"human":[12],"emotions.":[13],"MG-based":[14],"emotion":[15,25,51,143],"understanding":[16,26],"has":[17],"attracted":[18],"much":[19],"attention":[20],"because":[21],"it":[22,42],"allows":[23],"for":[24,49,91,100,142],"through":[27],"nonverbal":[28],"body":[29],"gestures":[30],"without":[31],"relying":[32],"on":[33,127,133],"identity":[34],"information":[35,90],"(e.g.,":[36,65],"facial":[37],"and":[38],"electrocardiogram":[39],"data).":[40],"Therefore,":[41],"is":[43],"essential":[44],"recognize":[46],"MG":[47],"effectively":[48],"advanced":[50],"understanding.":[52],"However,":[53],"existing":[54],"Gesture":[56],"Recognition":[57],"(MGR)":[58],"methods":[59],"utilize":[60],"only":[61],"a":[62,79,106],"single":[63],"modality":[64],"RGB":[66],"or":[67],"skeleton)":[68],"while":[69],"overlooking":[70],"crucial":[71],"textual":[72,150],"information.":[73],"In":[74,93],"this":[75],"letter,":[76],"we":[77,104,145],"propose":[78,105],"simple":[80],"but":[81],"effective":[82],"visual-text":[83,101],"contrastive":[84,102],"learning":[85],"solution":[86],"utilizes":[88],"text":[89],"MGR.":[92],"addition,":[94],"instead":[95],"of":[96,140,152],"using":[97,148,162],"handcrafted":[98],"prompts":[99],"learning,":[103],"novel":[107],"module":[108],"called":[109],"Adaptive":[110],"prompting":[111],"generate":[113],"contextaware":[114],"prompts.":[115],"The":[116],"experimental":[117],"results":[118,139,151],"show":[119],"the":[121,138,149],"proposed":[122],"method":[123],"achieves":[124],"state-of-the-art":[125],"performance":[126,156],"two":[128],"public":[129],"datasets.":[130],"Furthermore,":[131],"based":[132],"an":[134],"empirical":[135],"study":[136],"utilizing":[137],"MGR":[141,153],"understanding,":[144],"demonstrate":[146],"significantly":[154],"improves":[155],"by":[157],"6%+":[158],"compared":[159],"directly":[161],"video":[163],"as":[164],"input.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2024-05-04T00:00:00"}