{"id":"https://openalex.org/W7140177311","doi":"https://doi.org/10.1016/j.procs.2026.03.113","title":"Memory vs. Attention: Investigating LSTM and Transformer Models in Human Action Recognition","display_name":"Memory vs. Attention: Investigating LSTM and Transformer Models in Human Action Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140177311","doi":"https://doi.org/10.1016/j.procs.2026.03.113"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2026.03.113","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.03.113","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2026.03.113","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Isaac Van-Deste","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Isaac Van-Deste","raw_affiliation_strings":["CeDRI, Instituto Polit\u00e9cnico de Bragan\u00e7a, 5300-253, Bragan\u00e7a, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CeDRI, Instituto Polit\u00e9cnico de Bragan\u00e7a, 5300-253, Bragan\u00e7a, Portugal","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ju\u00b4lio Castro Lopes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju\u00b4lio Castro Lopes","raw_affiliation_strings":["CeDRI, Instituto Polit\u00e9cnico de Bragan\u00e7a, 5300-253, Bragan\u00e7a, Portugal","SusTEC, Instituto Polit\u00e9cnico de Bragan\u00e7a, 5300-253, Bragan\u00e7a, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CeDRI, Instituto Polit\u00e9cnico de Bragan\u00e7a, 5300-253, Bragan\u00e7a, Portugal","institution_ids":[]},{"raw_affiliation_string":"SusTEC, Instituto Polit\u00e9cnico de Bragan\u00e7a, 5300-253, Bragan\u00e7a, Portugal","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Rui Pedro Lopes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Pedro Lopes","raw_affiliation_strings":["CeDRI, Instituto Polit\u00e9cnico de Bragan\u00e7a, 5300-253, Bragan\u00e7a, Portugal","SusTEC, Instituto Polit\u00e9cnico de Bragan\u00e7a, 5300-253, Bragan\u00e7a, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CeDRI, Instituto Polit\u00e9cnico de Bragan\u00e7a, 5300-253, Bragan\u00e7a, Portugal","institution_ids":[]},{"raw_affiliation_string":"SusTEC, Instituto Polit\u00e9cnico de Bragan\u00e7a, 5300-253, Bragan\u00e7a, Portugal","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60437231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"278","issue":null,"first_page":"1299","last_page":"1306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9714000225067139,"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":0.9714000225067139,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.0035000001080334187,"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":0.0024999999441206455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.8585000038146973},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.6851999759674072},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5376999974250793},{"id":"https://openalex.org/keywords/accelerometer","display_name":"Accelerometer","score":0.45170000195503235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35850000381469727},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3555000126361847},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3334999978542328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8998000025749207},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8585000038146973},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6851999759674072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6366000175476074},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5376999974250793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4586000144481659},{"id":"https://openalex.org/C89805583","wikidata":"https://www.wikidata.org/wiki/Q192940","display_name":"Accelerometer","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29269999265670776},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2026.03.113","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.03.113","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2026.03.113","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.03.113","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2054041160","https://openalex.org/W2801704870","https://openalex.org/W3194729301","https://openalex.org/W3200080868","https://openalex.org/W4292787291","https://openalex.org/W4323044514","https://openalex.org/W4392567235","https://openalex.org/W4400134933","https://openalex.org/W4402788187","https://openalex.org/W4404439889","https://openalex.org/W4405704751","https://openalex.org/W4408157424","https://openalex.org/W4412450981","https://openalex.org/W4412524406","https://openalex.org/W4413168650"],"related_works":[],"abstract_inverted_index":{"Human":[0],"action":[1,96],"recognition":[2],"is":[3],"a":[4,41,44,47,63,66,71,87,99],"fundamental":[5],"task":[6],"in":[7,13,21,95,107],"computer":[8],"vision":[9],"with":[10,46,65],"many":[11],"applications":[12],"different":[14],"fields.":[15],"Deep":[16],"Learning":[17],"methods":[18],"demonstrate":[19],"efficiency":[20],"learning":[22],"spatiotemporal":[23],"representations":[24],"of":[25,68,74],"data":[26],"from":[27],"skeleton":[28,49],"extraction":[29,50],"to":[30],"accelerometers":[31],"or":[32],"radar.":[33],"This":[34],"article":[35],"compares":[36],"three":[37],"classifiers,":[38],"an":[39],"LSTM,":[40],"Bi-LSTM,":[42],"and":[43,92],"Transformer":[45,94,105],"unique":[48],"method,":[51],"the":[52,55,58,77,82,90,93],"YOLO-PoseV11.":[53],"Using":[54],"N-UCLA":[56],"dataset,":[57],"best":[59],"approach":[60],"relies":[61],"on":[62,104],"Bi-LSTM":[64],"hidden-size":[67],"100,":[69],"achieving":[70],"F1":[72],"score":[73],"74.18%.":[75],"Although":[76],"results":[78],"do":[79],"not":[80],"achieve":[81],"State-Of-The-Art,":[83],"this":[84,108],"paper":[85],"presents":[86],"comparison":[88],"between":[89],"LSTMs":[91],"recognition,":[97],"providing":[98],"base":[100],"for":[101],"future":[102],"research":[103],"networks":[106],"field.":[109]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-03-25T00:00:00"}