{"id":"https://openalex.org/W4415272559","doi":"https://doi.org/10.1007/s10462-025-11388-3","title":"CNNs, RNNs and Transformers in human action recognition: a survey and a hybrid model","display_name":"CNNs, RNNs and Transformers in human action recognition: a survey and a hybrid model","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W4415272559","doi":"https://doi.org/10.1007/s10462-025-11388-3"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-025-11388-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11388-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11388-3.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"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":"Artificial Intelligence Review","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/s10462-025-11388-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015776510","display_name":"Khaled Alomar","orcid":"https://orcid.org/0000-0002-8303-3240"},"institutions":[{"id":"https://openalex.org/I240666556","display_name":"Imam Mohammad ibn Saud Islamic University","ror":"https://ror.org/05gxjyb39","country_code":"SA","type":"education","lineage":["https://openalex.org/I240666556"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Khaled Alomar","raw_affiliation_strings":["Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I240666556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082683454","display_name":"Halil Ibrahim Aysel","orcid":"https://orcid.org/0000-0002-4981-0827"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Halil Ibrahim Aysel","raw_affiliation_strings":["Electronics and Computer Science, University of Southampton, Southampton, SO17 1BJ, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Computer Science, University of Southampton, Southampton, SO17 1BJ, UK","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078326698","display_name":"Xiaohao Cai","orcid":"https://orcid.org/0000-0003-0924-2834"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaohao Cai","raw_affiliation_strings":["Electronics and Computer Science, University of Southampton, Southampton, SO17 1BJ, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Computer Science, University of Southampton, Southampton, SO17 1BJ, UK","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015776510","https://openalex.org/A5082683454"],"corresponding_institution_ids":["https://openalex.org/I240666556","https://openalex.org/I43439940"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":20.5954,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.99680433,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"58","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T12740","display_name":"Gait Recognition and Analysis","score":0.9970999956130981,"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/transformer","display_name":"Transformer","score":0.6930999755859375},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5253000259399414},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5029000043869019},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.46320000290870667},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.45730000734329224},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.38280001282691956},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.37560001015663147},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.36320000886917114},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3580999970436096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968999743461609},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6930999755859375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6601999998092651},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.61080002784729},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.46320000290870667},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.45730000734329224},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3353999853134155},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26440000534057617}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10462-025-11388-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11388-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11388-3.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"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":"Artificial Intelligence Review","raw_type":"journal-article"},{"id":"pmh:oai:eprints.soton.ac.uk:507110","is_oa":false,"landing_page_url":"http://doi.org/10.1007/s10462-025-11388-3>).","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s10462-025-11388-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11388-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11388-3.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"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":"Artificial Intelligence Review","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3417980167","display_name":null,"funder_award_id":"IMSIU-DDRSP2501","funder_id":"https://openalex.org/F4320325415","funder_display_name":"Al-Imam Muhammad Ibn Saud Islamic University"}],"funders":[{"id":"https://openalex.org/F4320325415","display_name":"Al-Imam Muhammad Ibn Saud Islamic University","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415272559.pdf","grobid_xml":"https://content.openalex.org/works/W4415272559.grobid-xml"},"referenced_works_count":100,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1753482797","https://openalex.org/W1902237438","https://openalex.org/W1923404803","https://openalex.org/W1927052826","https://openalex.org/W1947481528","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2101926813","https://openalex.org/W2105101328","https://openalex.org/W2107878631","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2119821739","https://openalex.org/W2126579184","https://openalex.org/W2136848157","https://openalex.org/W2143612262","https://openalex.org/W2157331557","https://openalex.org/W2161565164","https://openalex.org/W2161969291","https://openalex.org/W2194775991","https://openalex.org/W2235034809","https://openalex.org/W2325748482","https://openalex.org/W2341313195","https://openalex.org/W2342662179","https://openalex.org/W2507009361","https://openalex.org/W2736596806","https://openalex.org/W2740537152","https://openalex.org/W2766736793","https://openalex.org/W2769581371","https://openalex.org/W2799176631","https://openalex.org/W2810685774","https://openalex.org/W2883429621","https://openalex.org/W2884696388","https://openalex.org/W2894873912","https://openalex.org/W2898716605","https://openalex.org/W2919115771","https://openalex.org/W2962934715","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963246338","https://openalex.org/W2963315828","https://openalex.org/W2963465031","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2971915722","https://openalex.org/W2972546487","https://openalex.org/W2980037812","https://openalex.org/W2981548405","https://openalex.org/W2984287396","https://openalex.org/W2990503944","https://openalex.org/W3003662786","https://openalex.org/W3004473259","https://openalex.org/W3011785450","https://openalex.org/W3013312502","https://openalex.org/W3017361427","https://openalex.org/W3034572008","https://openalex.org/W3035524964","https://openalex.org/W3043386865","https://openalex.org/W3080742155","https://openalex.org/W3088102655","https://openalex.org/W3096609285","https://openalex.org/W3107664750","https://openalex.org/W3151654442","https://openalex.org/W3173590174","https://openalex.org/W3175528717","https://openalex.org/W3181942264","https://openalex.org/W3194397797","https://openalex.org/W3212604410","https://openalex.org/W4206706211","https://openalex.org/W4213019189","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4249279051","https://openalex.org/W4285217742","https://openalex.org/W4285231968","https://openalex.org/W4306955484","https://openalex.org/W4312560592","https://openalex.org/W4313573916","https://openalex.org/W4378895615","https://openalex.org/W4384299378","https://openalex.org/W4384927449","https://openalex.org/W4385571791","https://openalex.org/W4385804842","https://openalex.org/W4386071476","https://openalex.org/W4388602741","https://openalex.org/W4389041134","https://openalex.org/W4389474561","https://openalex.org/W4390190927","https://openalex.org/W4390349622","https://openalex.org/W4392354632","https://openalex.org/W4392523452","https://openalex.org/W4392943193","https://openalex.org/W4401596686","https://openalex.org/W4402307487","https://openalex.org/W4402904000","https://openalex.org/W4403977037","https://openalex.org/W4404007800"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Human":[1],"action":[2],"recognition":[3,165],"(HAR)":[4],"encompasses":[5],"the":[6,28,34,37,65,72,79,98,114,151,159,173,198,208,233,242,263],"task":[7,138],"of":[8,30,39,68,74,81,91,100,175,200,210,217,232,266],"monitoring":[9],"human":[10,143],"activities":[11],"across":[12,130],"various":[13,131],"domains,":[14],"including":[15],"but":[16],"not":[17],"limited":[18],"to":[19,56,106,140,188,202,245,261],"medical,":[20],"educational,":[21],"entertainment,":[22],"visual":[23],"surveillance,":[24],"video":[25],"retrieval,":[26],"and":[27,51,59,127,150,164,183,197,220,230,268],"identification":[29],"anomalous":[31],"activities.":[32],"Over":[33],"past":[35],"decade,":[36],"field":[38],"HAR":[40,69,134],"has":[41,77,94,117],"witnessed":[42,78],"substantial":[43],"progress":[44],"by":[45],"leveraging":[46],"convolutional":[47],"neural":[48,53],"networks":[49,54],"(CNNs)":[50],"recurrent":[52],"(RNNs)":[55],"effectively":[57],"extract":[58],"comprehend":[60],"intricate":[61],"information,":[62],"thereby":[63],"enhancing":[64],"overall":[66],"performance":[67],"systems.":[70],"Recently,":[71],"domain":[73,209],"computer":[75],"vision":[76],"emergence":[80],"Vision":[82],"Transformers":[83],"(ViTs)":[84],"as":[85],"a":[86,136,168,214,227,255],"potent":[87],"solution.":[88],"The":[89],"efficacy":[90],"Transformer":[92],"architecture":[93],"been":[95],"validated":[96],"beyond":[97],"confines":[99],"image":[101],"analysis,":[102],"extending":[103],"their":[104,205],"applicability":[105],"diverse":[107],"video-related":[108],"tasks.":[109],"Notably,":[110],"within":[111],"this":[112,224,237,250,252],"landscape,":[113],"research":[115],"community":[116],"shown":[118],"keen":[119],"interest":[120],"in":[121,142,207,236],"HAR,":[122],"acknowledging":[123],"its":[124],"manifold":[125],"utility":[126],"widespread":[128],"adoption":[129,174],"domains.":[132],"However,":[133],"remains":[135,167],"challenging":[137],"due":[139],"variations":[141],"motion,":[144],"occlusions,":[145],"viewpoint":[146],"differences,":[147],"background":[148],"clutter,":[149],"need":[152],"for":[153],"efficient":[154],"spatio-temporal":[155],"feature":[156],"extraction.":[157],"Additionally,":[158,239],"trade-off":[160],"between":[161],"computational":[162],"efficiency":[163],"accuracy":[166],"significant":[169],"obstacle,":[170],"particularly":[171],"with":[172],"deep":[176],"learning":[177],"models":[178],"requiring":[179],"extensive":[180],"training":[181],"data":[182],"resources.":[184],"This":[185],"article":[186,253],"aims":[187],"present":[189],"an":[190],"encompassing":[191],"survey":[192],"that":[193,259],"focuses":[194],"on":[195],"CNNs":[196,267],"evolution":[199],"RNNs":[201],"ViTs":[203],"given":[204],"importance":[206],"HAR.":[211],"By":[212],"conducting":[213],"thorough":[215],"examination":[216],"existing":[218],"literature":[219],"exploring":[221],"emerging":[222],"trends,":[223],"study":[225],"undertakes":[226],"critical":[228],"analysis":[229],"synthesis":[231],"accumulated":[234],"knowledge":[235],"field.":[238],"it":[240],"investigates":[241],"ongoing":[243],"efforts":[244],"develop":[246],"hybrid":[247,257],"approaches.":[248],"Following":[249],"direction,":[251],"presents":[254],"novel":[256],"model":[258],"seeks":[260],"integrate":[262],"inherent":[264],"strengths":[265],"ViTs.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":31},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-17T00:00:00"}