{"id":"https://openalex.org/W7149014954","doi":"https://doi.org/10.1109/lsp.2026.3680392","title":"MSAW-Net: Dual-Path Fusion Network With Multi-Scale Spatiotemporal Attention Weighting for Human Action Recognition","display_name":"MSAW-Net: Dual-Path Fusion Network With Multi-Scale Spatiotemporal Attention Weighting for Human Action Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7149014954","doi":"https://doi.org/10.1109/lsp.2026.3680392"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2026.3680392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3680392","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":["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/A5132853545","display_name":"Hui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["School of Information and Software Engineering, East China Jiaotong University, Nanchang, China"],"raw_orcid":"https://orcid.org/0000-0003-4061-4456","affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, East China Jiaotong University, Nanchang, China","institution_ids":["https://openalex.org/I13985625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132879789","display_name":"Junhao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhao Li","raw_affiliation_strings":["School of Information and Software Engineering, East China Jiaotong University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, East China Jiaotong University, Nanchang, China","institution_ids":["https://openalex.org/I13985625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028707382","display_name":"Kangli Zeng","orcid":"https://orcid.org/0000-0002-8592-053X"},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangli Zeng","raw_affiliation_strings":["School of Information and Software Engineering, East China Jiaotong University, Nanchang, China"],"raw_orcid":"https://orcid.org/0000-0002-8592-053X","affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, East China Jiaotong University, Nanchang, China","institution_ids":["https://openalex.org/I13985625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128295454","display_name":"Chunhui Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhui Zhao","raw_affiliation_strings":["School of Information and Software Engineering, East China Jiaotong University, Nanchang, China"],"raw_orcid":"https://orcid.org/0000-0002-0254-5763","affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, East China Jiaotong University, Nanchang, China","institution_ids":["https://openalex.org/I13985625"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132896605","display_name":"Hui Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Yang","raw_affiliation_strings":["School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang, China"],"raw_orcid":"https://orcid.org/0000-0003-2560-9528","affiliations":[{"raw_affiliation_string":"School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang, China","institution_ids":["https://openalex.org/I13985625"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I13985625"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42463012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1866","last_page":"1870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9348000288009644,"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":0.9348000288009644,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.006899999920278788,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.005499999970197678,"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":0.6758999824523926},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5914000272750854},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5738999843597412},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4713999927043915},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4424999952316284},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4404999911785126},{"id":"https://openalex.org/keywords/a-weighting","display_name":"A-weighting","score":0.33959999680519104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706000208854675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7177000045776367},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6758999824523926},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5914000272750854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5738999843597412},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32190001010894775},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29249998927116394},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2026.3680392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3680392","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4173934627","display_name":null,"funder_award_id":"62462032","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5472010482","display_name":null,"funder_award_id":"VRLAB2025C10","funder_id":"https://openalex.org/F4320321125","funder_display_name":"Beihang University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321125","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Human":[0],"action":[1,23],"recognition":[2,24],"methods":[3,25],"based":[4],"on":[5,117],"multimodal":[6,33],"channels,":[7],"especially":[8],"the":[9,21,66,71,94,108,118,129,132,146],"strategy":[10],"combining":[11,51],"RGB":[12],"and":[13,38,63,125],"skeleton":[14],"information,":[15],"have":[16],"achieved":[17],"remarkable":[18],"success.":[19],"However,":[20],"existing":[22],"still":[26],"face":[27],"challenges":[28],"in":[29,91],"terms":[30],"of":[31,41,115,131],"insufficient":[32],"fusion,":[34,58],"imperfect":[35],"multi-scale":[36],"modeling,":[37],"inadequate":[39],"preservation":[40],"spatial":[42,105],"information.":[43],"This":[44],"paper":[45],"proposes":[46],"an":[47],"innovative":[48],"framework:":[49],"by":[50],"early":[52],"bidirectional":[53],"lateral":[54],"connections":[55],"with":[56,145],"late":[57],"deep":[59],"interaction":[60],"between":[61],"modalities":[62],"complementarity":[64],"at":[65],"prediction":[67],"layer":[68],"are":[69],"achieved;":[70],"Multi-scale":[72],"Spatiotemporal":[73],"Attention":[74],"Weighting":[75],"(MSAW)":[76],"mechanism":[77],"is":[78,100,153],"designed":[79],"to":[80],"adaptively":[81],"fuse":[82],"spatiotemporal":[83,92],"features":[84],"across":[85],"different":[86],"scales,":[87],"selecting":[88],"key":[89],"frames":[90],"sequences;":[93],"Pixel":[95],"Sub-sampling":[96],"Downsampling":[97],"(PSD)":[98],"module":[99],"proposed,":[101],"which":[102],"effectively":[103],"retains":[104],"details":[106],"during":[107],"strong":[109],"downsampling":[110],"process.":[111],"A":[112],"large":[113],"number":[114],"experiments":[116],"NTU":[119,122],"RGB+D":[120,123],"60,":[121],"120,":[124],"Kinetics-400":[126],"datasets":[127],"verified":[128],"effectiveness":[130],"proposed":[133],"method.":[134],"The":[135],"results":[136],"show":[137],"that":[138],"our":[139],"method":[140],"demonstrates":[141],"stronger":[142],"competitiveness":[143],"compared":[144],"current":[147],"state-of-the-art":[148],"(SOTA)":[149],"methods.":[150],"Our":[151],"code":[152],"available":[154],"at:":[155],"<uri":[156],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/course-prog/MASW</uri>":[158]},"counts_by_year":[],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2026-04-04T00:00:00"}