{"id":"https://openalex.org/W4390736386","doi":"https://doi.org/10.1007/s00521-023-09186-5","title":"Multimodal fusion for audio-image and video action recognition","display_name":"Multimodal fusion for audio-image and video action recognition","publication_year":2024,"publication_date":"2024-01-09","ids":{"openalex":"https://openalex.org/W4390736386","doi":"https://doi.org/10.1007/s00521-023-09186-5"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-023-09186-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-09186-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-09186-5.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-09186-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036110830","display_name":"Muhammad Bilal Shaikh","orcid":"https://orcid.org/0000-0001-9042-5018"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Muhammad Bilal Shaikh","raw_affiliation_strings":["Center for Artificial Intelligence and Machine Learning (CAIML), School of Science, Edith Cowan University, Perth, Australia","School of Engineering, Edith Cowan University, 270 Joondalup Drive, Joondalup, WA, 6027, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9042-5018","affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Machine Learning (CAIML), School of Science, Edith Cowan University, Perth, Australia","institution_ids":["https://openalex.org/I12079687"]},{"raw_affiliation_string":"School of Engineering, Edith Cowan University, 270 Joondalup Drive, Joondalup, WA, 6027, Australia","institution_ids":["https://openalex.org/I12079687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056138775","display_name":"Douglas Chai","orcid":"https://orcid.org/0000-0002-9004-7608"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Douglas Chai","raw_affiliation_strings":["School of Engineering, Edith Cowan University, 270 Joondalup Drive, Joondalup, WA, 6027, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Edith Cowan University, 270 Joondalup Drive, Joondalup, WA, 6027, Australia","institution_ids":["https://openalex.org/I12079687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034900636","display_name":"Syed Mohammed Shamsul Islam","orcid":"https://orcid.org/0000-0002-3200-2903"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Syed Mohammed Shamsul Islam","raw_affiliation_strings":["Center for Artificial Intelligence and Machine Learning (CAIML), School of Science, Edith Cowan University, Perth, Australia","School of Science, Edith Cowan University, 270 Joondalup Drive, Joondalup, WA, 6027, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Machine Learning (CAIML), School of Science, Edith Cowan University, Perth, Australia","institution_ids":["https://openalex.org/I12079687"]},{"raw_affiliation_string":"School of Science, Edith Cowan University, 270 Joondalup Drive, Joondalup, WA, 6027, Australia","institution_ids":["https://openalex.org/I12079687"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069697936","display_name":"Naveed Akhtar","orcid":"https://orcid.org/0000-0003-3406-673X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Naveed Akhtar","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Melbourne Connect, 700 Swanston Street, Carlton, WA, 3053, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Melbourne Connect, 700 Swanston Street, Carlton, WA, 3053, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036110830"],"corresponding_institution_ids":["https://openalex.org/I12079687"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":9.1486,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.98630037,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"36","issue":"10","first_page":"5499","last_page":"5513"},"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":0.9922000169754028,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8657788634300232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6456592082977295},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.594897449016571},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.576732873916626},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5623950362205505},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5605925917625427},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48119503259658813},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4780069887638092},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4722941219806671},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4454553425312042},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4438306391239166},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4211089015007019},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4114205241203308},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39107251167297363},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37675100564956665},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14936187863349915},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.14336413145065308},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.08333823084831238},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.06947562098503113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8657788634300232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6456592082977295},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.594897449016571},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.576732873916626},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5623950362205505},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5605925917625427},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48119503259658813},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4780069887638092},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4722941219806671},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4454553425312042},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4438306391239166},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4211089015007019},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4114205241203308},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39107251167297363},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37675100564956665},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14936187863349915},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.14336413145065308},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.08333823084831238},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.06947562098503113},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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":2,"locations":[{"id":"doi:10.1007/s00521-023-09186-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-09186-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-09186-5.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},{"id":"pmh:oai:ro.ecu.edu.au:ecuworks2022-2026-4399","is_oa":true,"landing_page_url":"https://ro.ecu.edu.au/ecuworks2022-2026/3398","pdf_url":null,"source":{"id":"https://openalex.org/S2765015692","display_name":"Australasian Journal of Paramedicine","issn_l":"2202-7270","issn":["2202-7270"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research outputs 2022 to 2026","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/s00521-023-09186-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-09186-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-09186-5.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G3104612030","display_name":null,"funder_award_id":"PM/HRDI-UESTPs/UETs-457 I/Phase-1/Batch-VI/2018","funder_id":"https://openalex.org/F4320322799","funder_display_name":"Higher Education Commission, Pakistan"},{"id":"https://openalex.org/G3406409465","display_name":null,"funder_award_id":"NIPG-2021-001","funder_id":"https://openalex.org/F4320315885","funder_display_name":"Australian Government"},{"id":"https://openalex.org/G7966873392","display_name":null,"funder_award_id":"NIPG-2021-001","funder_id":"https://openalex.org/F4320337300","funder_display_name":"Office of National Intelligence"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320320988","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22"},{"id":"https://openalex.org/F4320322799","display_name":"Higher Education Commission, Pakistan","ror":"https://ror.org/038y3sz68"},{"id":"https://openalex.org/F4320337300","display_name":"Office of National Intelligence","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390736386.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1655480174","https://openalex.org/W1950117310","https://openalex.org/W2032337854","https://openalex.org/W2117539524","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2342662179","https://openalex.org/W2425380982","https://openalex.org/W2465313502","https://openalex.org/W2507009361","https://openalex.org/W2592728162","https://openalex.org/W2608988379","https://openalex.org/W2619697695","https://openalex.org/W2658040354","https://openalex.org/W2736544854","https://openalex.org/W2770804203","https://openalex.org/W2772452219","https://openalex.org/W2776601846","https://openalex.org/W2789221157","https://openalex.org/W2795068264","https://openalex.org/W2795627216","https://openalex.org/W2807436399","https://openalex.org/W2832876791","https://openalex.org/W2892166671","https://openalex.org/W2893911272","https://openalex.org/W2894558420","https://openalex.org/W2955425717","https://openalex.org/W2962899219","https://openalex.org/W2963066927","https://openalex.org/W2963218601","https://openalex.org/W2963457877","https://openalex.org/W2964109005","https://openalex.org/W2964121744","https://openalex.org/W2968627699","https://openalex.org/W2969083552","https://openalex.org/W2971680695","https://openalex.org/W2980492205","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2990541775","https://openalex.org/W3004911477","https://openalex.org/W3005865003","https://openalex.org/W3025948831","https://openalex.org/W3034658206","https://openalex.org/W3034768625","https://openalex.org/W3091959638","https://openalex.org/W3168640669","https://openalex.org/W3174760001","https://openalex.org/W3175419009","https://openalex.org/W3182657421","https://openalex.org/W3210279979","https://openalex.org/W3214007456","https://openalex.org/W4210655669","https://openalex.org/W4214777631","https://openalex.org/W4220894980","https://openalex.org/W4226025707","https://openalex.org/W4283645969","https://openalex.org/W4293211772","https://openalex.org/W4316660066","https://openalex.org/W6847397134"],"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/W4243305035","https://openalex.org/W1537496349","https://openalex.org/W2379407973","https://openalex.org/W2350267540"],"abstract_inverted_index":{"Abstract":[0],"Multimodal":[1,41],"Human":[2],"Action":[3,45],"Recognition":[4],"(MHAR)":[5],"is":[6],"an":[7,114,146],"important":[8],"research":[9],"topic":[10],"in":[11],"computer":[12],"vision":[13],"and":[14,32,43,58,74,94,105,109,131,149,153,160],"event":[15],"recognition":[16],"fields.":[17],"In":[18],"this":[19,163],"work,":[20],"we":[21,39],"address":[22],"the":[23,65,101,122],"problem":[24],"of":[25,55,67,103],"MHAR":[26,120],"by":[27],"developing":[28],"a":[29,85,126],"novel":[30],"audio-image":[31,141],"video":[33,62,106],"fusion-based":[34,98],"deep":[35],"learning":[36],"framework":[37,99],"that":[38,136],"call":[40],"Audio-Image":[42],"Video":[44],"Recognizer":[46],"(MAiVAR).":[47],"We":[48,83],"extract":[49],"temporal":[50],"information":[51,60],"using":[52],"image":[53],"representations":[54],"audio":[56,104],"signals":[57],"spatial":[59],"from":[61],"modality":[63],"with":[64,117,139],"help":[66],"Convolutional":[68],"Neutral":[69],"Networks":[70],"(CNN)-based":[71],"feature":[72,107],"extractors":[73],"fuse":[75],"these":[76],"features":[77,125],"to":[78,112],"recognize":[79],"respective":[80],"action":[81],"classes.":[82],"apply":[84],"high-level":[86],"weights":[87],"assignment":[88],"algorithm":[89],"for":[90,162],"improving":[91],"audio-visual":[92,119],"interaction":[93],"convergence.":[95],"This":[96],"proposed":[97,123],"utilizes":[100],"influence":[102],"maps":[108],"uses":[110],"them":[111],"classify":[113],"action.":[115],"Compared":[116],"state-of-the-art":[118],"techniques,":[121],"approach":[124],"simpler":[127],"yet":[128],"more":[129,132],"accurate":[130],"generalizable":[133],"architecture,":[134],"one":[135],"performs":[137],"better":[138],"different":[140],"representations.":[142],"The":[143],"system":[144],"achieves":[145],"accuracy":[147],"87.9%":[148],"79.0%":[150],"on":[151],"UCF51":[152],"Kinetics":[154],"Sounds":[155],"datasets,":[156],"respectively.":[157],"All":[158],"code":[159],"models":[161],"paper":[164],"will":[165],"be":[166],"available":[167],"at":[168],"https://tinyurl.com/4ps2ux6n":[169],".":[170]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":7}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}