{"id":"https://openalex.org/W4408611768","doi":"https://doi.org/10.1109/icaiic64266.2025.10920711","title":"State Space Model Based VideoMAE Enhancement for Efficient Video Action Classification","display_name":"State Space Model Based VideoMAE Enhancement for Efficient Video Action Classification","publication_year":2025,"publication_date":"2025-02-18","ids":{"openalex":"https://openalex.org/W4408611768","doi":"https://doi.org/10.1109/icaiic64266.2025.10920711"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic64266.2025.10920711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic64266.2025.10920711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-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/A5051657843","display_name":"Junbeom Moon","orcid":"https://orcid.org/0000-0001-6785-1692"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Junbeom Moon","raw_affiliation_strings":["School of Computer Science &#x0026; Engineering, Kyungpook National University,Daegu,South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science &#x0026; Engineering, Kyungpook National University,Daegu,South Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106893453","display_name":"Sehwan Heo","orcid":"https://orcid.org/0009-0004-4344-2922"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sehwan Heo","raw_affiliation_strings":["School of Computer Science &#x0026; Engineering, Kyungpook National University,Daegu,South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science &#x0026; Engineering, Kyungpook National University,Daegu,South Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiye Won","orcid":null},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiye Won","raw_affiliation_strings":["School of Computer &#x0026; Engineering, Kyungpook National University,Daegu,South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer &#x0026; Engineering, Kyungpook National University,Daegu,South Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113247793","display_name":"Jaeseok Jang","orcid":"https://orcid.org/0009-0007-8173-8881"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeseok Jang","raw_affiliation_strings":["School of Computer &#x0026; Engineering, Kyungpook National University,Daegu,South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer &#x0026; Engineering, Kyungpook National University,Daegu,South Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077603212","display_name":"Soon Ki Jung","orcid":"https://orcid.org/0000-0003-0239-6785"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soon Ki Jung","raw_affiliation_strings":["School of Computer Science &#x0026; Engineering, Kyungpook National University,Daegu,South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science &#x0026; Engineering, Kyungpook National University,Daegu,South Korea","institution_ids":["https://openalex.org/I31419693"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051657843"],"corresponding_institution_ids":["https://openalex.org/I31419693"],"apc_list":null,"apc_paid":null,"fwci":2.326,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87138709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"0820","last_page":"0824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9936000108718872,"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":0.9936000108718872,"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":0.9901999831199646,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.980400025844574,"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/computer-science","display_name":"Computer science","score":0.6754339337348938},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5044728517532349},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4903743267059326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4458923935890198},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07867589592933655},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.061146944761276245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6754339337348938},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5044728517532349},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4903743267059326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4458923935890198},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07867589592933655},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.061146944761276245},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic64266.2025.10920711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic64266.2025.10920711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2156303437","https://openalex.org/W2619082050","https://openalex.org/W2619947201","https://openalex.org/W3094502228","https://openalex.org/W3208827570","https://openalex.org/W3209374680","https://openalex.org/W3211983881","https://openalex.org/W4221167396","https://openalex.org/W4389326242","https://openalex.org/W4391013663","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Video":[0],"action":[1,143],"classification":[2,121],"is":[3],"a":[4,110,136],"critical":[5],"task":[6],"in":[7,32,48,77,113,119],"computer":[8],"vision,":[9],"with":[10,87],"applications":[11],"spanning":[12],"security":[13],"surveillance,":[14],"sports":[15],"analytics,":[16],"and":[17,80,116,138],"human-computer":[18],"interaction.":[19],"Recent":[20],"advancements,":[21],"such":[22],"as":[23,135],"VideoMAE,":[24],"have":[25],"demonstrated":[26],"the":[27,70,124,130],"effectiveness":[28],"of":[29,132],"transformer-based":[30,106],"architectures":[31],"learning":[33],"spatiotemporal":[34],"representations.":[35],"However,":[36],"their":[37,46],"computational":[38],"inefficiency,":[39],"due":[40],"to":[41,101,104],"quadratic":[42],"time":[43],"complexity,":[44],"limits":[45],"applicability":[47],"resource-constrained":[49],"environments.":[50],"This":[51],"study":[52],"addresses":[53],"these":[54],"limitations":[55],"by":[56,99],"introducing":[57],"Vision":[58,73,94,133],"Mamba,":[59],"an":[60],"efficient":[61],"encoder":[62],"based":[63],"on":[64,123],"bidirectional":[65],"state-space":[66],"models":[67],"(SSMs),":[68],"into":[69],"VideoMAE":[71],"framework.":[72],"Mamba":[74,95,134],"processes":[75],"sequences":[76],"both":[78],"forward":[79],"backward":[81],"directions,":[82],"enabling":[83],"robust":[84],"temporal":[85],"modeling":[86],"linear":[88],"complexity.":[89],"Experimental":[90],"results":[91],"show":[92],"that":[93],"reduces":[96],"memory":[97],"consumption":[98],"up":[100],"48.9%":[102],"compared":[103],"traditional":[105],"methods,":[107],"while":[108],"achieving":[109],"1.59%":[111],"improvement":[112,118],"Top":[114],"1":[115],"2.01%":[117],"Top5":[120],"accuracy":[122],"Kinetics-400":[125],"dataset.":[126],"These":[127],"findings":[128],"underscore":[129],"potential":[131],"scalable":[137],"resource-efficient":[139],"solution":[140],"for":[141],"video":[142],"classification.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
