{"id":"https://openalex.org/W3175651474","doi":"https://doi.org/10.1109/icmew53276.2021.9455975","title":"Multimodal Feature Fusion Model For Rgb-D Action Recognition","display_name":"Multimodal Feature Fusion Model For Rgb-D Action Recognition","publication_year":2021,"publication_date":"2021-06-21","ids":{"openalex":"https://openalex.org/W3175651474","doi":"https://doi.org/10.1109/icmew53276.2021.9455975","mag":"3175651474"},"language":"en","primary_location":{"id":"doi:10.1109/icmew53276.2021.9455975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew53276.2021.9455975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","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/A5024728288","display_name":"Weiyao Xu","orcid":"https://orcid.org/0000-0001-9372-8225"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Weiyao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing Laboratory of Advanced Information Networks, Beijing Key Laboratory of Network System Architecture and Convergence,Beijing,China,100876"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing Laboratory of Advanced Information Networks, Beijing Key Laboratory of Network System Architecture and Convergence,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003011685","display_name":"Muqing Wu","orcid":"https://orcid.org/0000-0002-9653-4677"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Muqing","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing Laboratory of Advanced Information Networks, Beijing Key Laboratory of Network System Architecture and Convergence,Beijing,China,100876"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing Laboratory of Advanced Information Networks, Beijing Key Laboratory of Network System Architecture and Convergence,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100769198","display_name":"Min Zhao","orcid":"https://orcid.org/0000-0002-7324-9187"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Min","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing Laboratory of Advanced Information Networks, Beijing Key Laboratory of Network System Architecture and Convergence,Beijing,China,100876"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing Laboratory of Advanced Information Networks, Beijing Key Laboratory of Network System Architecture and Convergence,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103238810","display_name":"Ting Xia","orcid":"https://orcid.org/0000-0002-5030-514X"},"institutions":[{"id":"https://openalex.org/I4210159676","display_name":"Zaozhuang University","ror":"https://ror.org/05x21tp94","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210159676"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xia Ting","raw_affiliation_strings":["Zaozhuang University,Zaozhuang,China,277160"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zaozhuang University,Zaozhuang,China,277160","institution_ids":["https://openalex.org/I4210159676"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9966999888420105,"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":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7723495960235596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7528389692306519},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.7261683344841003},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6457927227020264},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6318436861038208},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5112721920013428},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.453476220369339},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.448220819234848},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4162895083427429},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33574995398521423}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7723495960235596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7528389692306519},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7261683344841003},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6457927227020264},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6318436861038208},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5112721920013428},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.453476220369339},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.448220819234848},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4162895083427429},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33574995398521423},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew53276.2021.9455975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew53276.2021.9455975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327558","display_name":"Beijing Key Laboratory of Network System Architecture and Convergence","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2056898157","https://openalex.org/W2156303437","https://openalex.org/W2342662179","https://openalex.org/W2510185399","https://openalex.org/W2565070966","https://openalex.org/W2894879265","https://openalex.org/W2902073357","https://openalex.org/W2902976851","https://openalex.org/W2904658540","https://openalex.org/W2944006115","https://openalex.org/W2948058585","https://openalex.org/W2963076818","https://openalex.org/W2963155035","https://openalex.org/W2964134613","https://openalex.org/W2981923053","https://openalex.org/W2989763126","https://openalex.org/W3003443105","https://openalex.org/W3008546095","https://openalex.org/W3034552520","https://openalex.org/W3035225512","https://openalex.org/W3035413240","https://openalex.org/W3044180073","https://openalex.org/W3109392981","https://openalex.org/W3133191957","https://openalex.org/W6682864246","https://openalex.org/W6756206234","https://openalex.org/W6762557054","https://openalex.org/W6769627599"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W2095030957","https://openalex.org/W2066827917","https://openalex.org/W2884201223"],"abstract_inverted_index":{"Due":[0],"to":[1,107,121,137],"the":[2,20,29,33,69,95,112,123,144],"variation":[3],"and":[4,53,76,86,99,101],"complexity":[5],"of":[6,19,97],"video":[7],"data,":[8],"human":[9],"action":[10,25,64],"recognition":[11,26,47],"is":[12,89,119],"still":[13],"a":[14,45,79,114,138],"challenging":[15],"task.":[16],"However,":[17],"most":[18],"methods":[21,73],"based":[22,49],"on":[23,50,128],"RGB-D":[24,63],"simply":[27],"fuse":[28,60],"multimodal":[30,80],"features,":[31],"ignoring":[32],"potential":[34,105],"semantic":[35],"relationship":[36],"between":[37],"different":[38],"modals.":[39],"In":[40,111],"this":[41],"paper,":[42],"we":[43,67],"propose":[44],"multi-modal":[46,61],"model":[48],"Bilinear":[51],"Pooling":[52],"Attention":[54],"Network":[55],"(BPAN),":[56],"which":[57,91],"could":[58,92],"effectively":[59,93],"for":[62,74],"recognition.":[65],"Firstly,":[66],"adopt":[68],"efficient":[70],"data":[71],"preprocessing":[72],"RGB":[75,85,98],"skeleton.":[77],"Then,":[78],"fusion":[81,109],"network":[82],"BPAN":[83],"combining":[84],"skeleton":[87],"sequence":[88],"proposed,":[90],"compress":[94],"features":[96],"skeleton,":[100],"project":[102],"them":[103],"into":[104],"subspace":[106],"obtain":[108,122],"features.":[110],"end,":[113],"fully":[115],"connected":[116],"three-layer":[117],"perceptron":[118],"adopted":[120],"final":[124],"classification.":[125],"Experimental":[126],"results":[127],"two":[129],"datasets":[130],"demonstrate":[131],"that":[132],"our":[133],"proposed":[134],"method":[135],"leads":[136],"more":[139],"favorable":[140],"performance":[141],"compared":[142],"with":[143],"state-of-the-art":[145],"methods.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}