{"id":"https://openalex.org/W7131819382","doi":"https://doi.org/10.1109/tmm.2026.3668511","title":"MSF-Mamba: Motion-Aware State Fusion Mamba for Efficient Micro-Gesture Recognition","display_name":"MSF-Mamba: Motion-Aware State Fusion Mamba for Efficient Micro-Gesture Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131819382","doi":"https://doi.org/10.1109/tmm.2026.3668511"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2026.3668511","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668511","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tmm.2026.3668511","any_repository_has_fulltext":false},"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, Department of Computational Engineering, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision and Pattern Recognition Laboratory, Department of Computational Engineering, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland","institution_ids":["https://openalex.org/I63548447"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127003000","display_name":"Jun Shao","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Shao","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"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/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":"Bohao Xing","raw_affiliation_strings":["Computer Vision and Pattern Recognition Laboratory, Department of Computational Engineering, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision and Pattern Recognition Laboratory, Department of Computational Engineering, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland","institution_ids":["https://openalex.org/I63548447"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rong Gao","orcid":"https://orcid.org/0009-0007-8938-8222"},"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":"Rong Gao","raw_affiliation_strings":["Computer Vision and Pattern Recognition Laboratory, Department of Computational Engineering, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland"],"raw_orcid":"https://orcid.org/0009-0007-8938-8222","affiliations":[{"raw_affiliation_string":"Computer Vision and Pattern Recognition Laboratory, Department of Computational Engineering, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland","institution_ids":["https://openalex.org/I63548447"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127245830","display_name":"Bihan Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bihan Wen","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6874-6453","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127317972","display_name":"Heikki K\u00e4lvi\u00e4inen","orcid":null},"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":"Heikki K\u00e4lvi\u00e4inen","raw_affiliation_strings":["Computer Vision and Pattern Recognition Laboratory, Department of Computational Engineering, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland"],"raw_orcid":"https://orcid.org/0000-0002-0790-6847","affiliations":[{"raw_affiliation_string":"Computer Vision and Pattern Recognition Laboratory, Department of Computational Engineering, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland","institution_ids":["https://openalex.org/I63548447"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127011790","display_name":"Xin Liu","orcid":null},"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, Department of Computational Engineering, 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, Department of Computational Engineering, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland","institution_ids":["https://openalex.org/I63548447"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.2465,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96440678,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"5912","last_page":"5923"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.8270999789237976,"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":0.8270999789237976,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.07320000231266022,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.01600000075995922,"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/weighting","display_name":"Weighting","score":0.5275999903678894},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5133000016212463},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5029000043869019},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49239999055862427},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.43639999628067017},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.362199991941452},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.3499000072479248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025000095367432},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5275999903678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.516700029373169},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2026.3668511","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668511","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/212186","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/212186","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":{"id":"doi:10.1109/tmm.2026.3668511","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668511","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1140376778","display_name":null,"funder_award_id":"202307960007","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G5373244593","display_name":null,"funder_award_id":"202306250014","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G741692903","display_name":null,"funder_award_id":"202406250043","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Micro-gesture":[0],"recognition":[1],"(MGR)":[2],"targets":[3],"the":[4,80,104,110,194,204,239],"identification":[5],"of":[6,16,124,206,285],"subtle":[7,221],"and":[8,12,19,107,217,234,251,266,272,279,287],"fine-grained":[9],"human":[10],"motions":[11],"requires":[13],"accurate":[14],"modeling":[15,148],"both":[17],"long-range":[18,37],"local":[20,32,114,146,151,212],"spatiotemporal":[21,115,147,213],"dependencies.":[22,116],"While":[23],"convolutional":[24],"neural":[25],"networks":[26],"(CNNs)":[27],"are":[28],"effective":[29],"at":[30],"capturing":[31],"patterns,":[33],"they":[34],"struggle":[35],"with":[36,98,145],"dependencies":[38],"due":[39],"to":[40,73,83,112],"their":[41],"limited":[42],"receptive":[43],"fields.":[44],"Transformer-based":[45],"models":[46,71,253],"address":[47,203],"this":[48],"limitation":[49],"through":[50],"self-attention":[51],"mechanisms":[52],"but":[53],"suffer":[54],"from":[55],"high":[56,256],"computational":[57],"costs.":[58],"Recently,":[59],"Mamba":[60,82,92,144,208],"has":[61],"shown":[62],"promise":[63],"as":[64,95,183,185],"an":[65,186],"efficient":[66],"model,":[67],"leveraging":[68],"state":[69,99,138,160,181],"space":[70],"(SSMs)":[72],"enable":[74],"linear-time":[75],"processing.":[76],"However,":[77],"directly":[78],"applying":[79],"vanilla":[81,207],"MGR":[84,230],"may":[85],"not":[86],"be":[87,293],"optimal.":[88],"This":[89],"is":[90,127],"because":[91],"processes":[93],"inputs":[94],"1D":[96],"sequences,":[97],"updates":[100],"relying":[101],"solely":[102],"on":[103,164,227,270,277],"previous":[105,119],"state,":[106],"thus":[108],"lacks":[109],"ability":[111],"model":[113],"In":[117],"addition,":[118],"methods":[120],"lack":[121],"a":[122,158,170],"design":[123,156],"motion-awareness,":[125],"which":[126,142],"crucial":[128],"in":[129],"MGR.":[130,225],"To":[131],"overcome":[132],"these":[133],"limitations,":[134],"we":[135],"propose":[136],"motion-aware":[137,159,180,211],"fusion":[139,161],"mamba":[140],"(MSF-Mamba),":[141],"enhances":[143],"by":[149,209,264],"fusing":[150],"contextual":[152],"neighboring":[153],"states.":[154],"Our":[155],"introduces":[157],"module":[162,190],"based":[163],"central":[165],"frame":[166],"difference":[167],"(CFD).":[168],"Furthermore,":[169],"multiscale":[171,179],"version":[172],"named":[173],"MSF-Mamba$^{+}$has":[174],"been":[175],"proposed.":[176],"Specifically,":[177],"MSF-Mamba$^{+}$supports":[178],"fusion,":[182],"well":[184],"adaptive":[187],"scale":[188],"weighting":[189],"that":[191,237],"dynamically":[192],"weighs":[193],"fused":[195],"states":[196],"across":[197],"different":[198],"scales.":[199],"These":[200],"enhancements":[201],"explicitly":[202],"limitations":[205],"enabling":[210],"modeling,":[214],"allowing":[215],"MSF-Mamba":[216,260],"MSF-Mamba$^{+}$to":[218],"effectively":[219],"capture":[220],"motion":[222],"cues":[223],"for":[224],"Experiments":[226],"two":[228],"public":[229],"datasets":[231],"(i.e.,":[232],"SMG":[233,271,278],"iMiGUE)":[235],"demonstrate":[236],"even":[238],"lightweight":[240],"version,":[241],"namely,":[242],"MSF-Mamba,":[243],"achieves":[244],"state-of-the-art":[245],"performance,":[246],"outperforming":[247],"existing":[248],"CNN-,":[249],"Transformer-,":[250],"SSM-based":[252],"while":[254],"maintaining":[255],"efficiency.":[257],"For":[258],"example,":[259],"improves":[261],"Top-1":[262,282],"accuracy":[263,283],"+2.2%":[265],"+1.5%":[267],"over":[268],"VideoMamba":[269,276],"iMiGUE,":[273,280],"respectively.":[274,289],"MSF-Mamba$^{+}$outperforms":[275],"achieving":[281],"improvements":[284],"2.9%":[286],"3.0%,":[288],"The":[290],"code":[291],"will":[292],"accessible":[294],"onhttps://github.com/Leedeng/MSF-Mamba":[295]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2026-02-28T00:00:00"}