{"id":"https://openalex.org/W4403956941","doi":"https://doi.org/10.3389/fnbot.2024.1457843","title":"LS-VIT: Vision Transformer for action recognition based on long and short-term temporal difference","display_name":"LS-VIT: Vision Transformer for action recognition based on long and short-term temporal difference","publication_year":2024,"publication_date":"2024-10-31","ids":{"openalex":"https://openalex.org/W4403956941","doi":"https://doi.org/10.3389/fnbot.2024.1457843","pmid":"https://pubmed.ncbi.nlm.nih.gov/39544849"},"language":"en","primary_location":{"id":"doi:10.3389/fnbot.2024.1457843","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2024.1457843","pdf_url":"https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2024.1457843/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2024.1457843/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102836087","display_name":"Dong Chen","orcid":"https://orcid.org/0009-0002-0543-963X"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]},{"id":"https://openalex.org/I4210151929","display_name":"Nanning Normal University","ror":"https://ror.org/04dx82x73","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Chen","raw_affiliation_strings":["College of Computer Science and Engineering, Guangxi Normal University, Guilin, China","College of Physics and Electronic Engineering, Nanning Normal University, Nanning, China","Guangxi Key Laboratory of Functional Information Materials and Intelligent Information Processing, Nanning, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"College of Physics and Electronic Engineering, Nanning Normal University, Nanning, China","institution_ids":["https://openalex.org/I4210151929"]},{"raw_affiliation_string":"Guangxi Key Laboratory of Functional Information Materials and Intelligent Information Processing, Nanning, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911341","display_name":"Peisong Wu","orcid":"https://orcid.org/0000-0003-2264-7828"},"institutions":[{"id":"https://openalex.org/I4210151929","display_name":"Nanning Normal University","ror":"https://ror.org/04dx82x73","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peisong Wu","raw_affiliation_strings":["College of Physics and Electronic Engineering, Nanning Normal University, Nanning, China","Guangxi Key Laboratory of Functional Information Materials and Intelligent Information Processing, Nanning, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Engineering, Nanning Normal University, Nanning, China","institution_ids":["https://openalex.org/I4210151929"]},{"raw_affiliation_string":"Guangxi Key Laboratory of Functional Information Materials and Intelligent Information Processing, Nanning, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054884987","display_name":"Mingdong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151929","display_name":"Nanning Normal University","ror":"https://ror.org/04dx82x73","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingdong Chen","raw_affiliation_strings":["College of Physics and Electronic Engineering, Nanning Normal University, Nanning, China","Guangxi Key Laboratory of Functional Information Materials and Intelligent Information Processing, Nanning, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Engineering, Nanning Normal University, Nanning, China","institution_ids":["https://openalex.org/I4210151929"]},{"raw_affiliation_string":"Guangxi Key Laboratory of Functional Information Materials and Intelligent Information Processing, Nanning, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100606199","display_name":"M. Wu","orcid":"https://orcid.org/0009-0002-6588-513X"},"institutions":[{"id":"https://openalex.org/I4210151929","display_name":"Nanning Normal University","ror":"https://ror.org/04dx82x73","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengtao Wu","raw_affiliation_strings":["College of Physics and Electronic Engineering, Nanning Normal University, Nanning, China","Guangxi Key Laboratory of Functional Information Materials and Intelligent Information Processing, Nanning, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Engineering, Nanning Normal University, Nanning, China","institution_ids":["https://openalex.org/I4210151929"]},{"raw_affiliation_string":"Guangxi Key Laboratory of Functional Information Materials and Intelligent Information Processing, Nanning, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383402","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0001-7975-8188"},"institutions":[{"id":"https://openalex.org/I4210151929","display_name":"Nanning Normal University","ror":"https://ror.org/04dx82x73","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["College of Physics and Electronic Engineering, Nanning Normal University, Nanning, China","Guangxi Key Laboratory of Functional Information Materials and Intelligent Information Processing, Nanning, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Engineering, Nanning Normal University, Nanning, China","institution_ids":["https://openalex.org/I4210151929"]},{"raw_affiliation_string":"Guangxi Key Laboratory of Functional Information Materials and Intelligent Information Processing, Nanning, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041698589","display_name":"Chuanqi Li","orcid":"https://orcid.org/0009-0003-4503-0625"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuanqi Li","raw_affiliation_strings":["College of Computer Science and Engineering, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5041698589"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":{"value":2950,"currency":"USD","value_usd":2950},"apc_paid":{"value":2950,"currency":"USD","value_usd":2950},"fwci":1.7755,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86629768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"18","issue":null,"first_page":"1457843","last_page":"1457843"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9944999814033508,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9922999739646912,"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":0.827595591545105},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.6812759041786194},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6399439573287964},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6308819055557251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.575354814529419},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.49679043889045715},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4949461817741394},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4760827124118805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35127130150794983},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1343931257724762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827595591545105},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6812759041786194},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6399439573287964},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6308819055557251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.575354814529419},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.49679043889045715},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4949461817741394},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4760827124118805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35127130150794983},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1343931257724762},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fnbot.2024.1457843","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2024.1457843","pdf_url":"https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2024.1457843/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},{"id":"pmid:39544849","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39544849","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in neurorobotics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11560894","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11560894","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11560894/pdf/fnbot-18-1457843.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Neurorobot","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:531958709a7e48db81d1089c7dad1b9f","is_oa":true,"landing_page_url":"https://doaj.org/article/531958709a7e48db81d1089c7dad1b9f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"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":"Frontiers in Neurorobotics, Vol 18 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fnbot.2024.1457843","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2024.1457843","pdf_url":"https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2024.1457843/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327297","display_name":"Education Department of Guangxi Zhuang Autonomous Region","ror":"https://ror.org/00kx48s25"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403956941.pdf","grobid_xml":"https://content.openalex.org/works/W4403956941.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W2016053056","https://openalex.org/W2108598243","https://openalex.org/W2156303437","https://openalex.org/W2156798932","https://openalex.org/W2342662179","https://openalex.org/W2507009361","https://openalex.org/W2746726611","https://openalex.org/W2770804203","https://openalex.org/W2799146007","https://openalex.org/W2883429621","https://openalex.org/W2963015194","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2981385151","https://openalex.org/W2984192355","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2996901793","https://openalex.org/W3035303837","https://openalex.org/W3035413240","https://openalex.org/W3037046522","https://openalex.org/W3094502228","https://openalex.org/W3103366418","https://openalex.org/W3121523901","https://openalex.org/W3126721948","https://openalex.org/W3133696297","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3170874841","https://openalex.org/W3175528717","https://openalex.org/W3205497712","https://openalex.org/W4214516465","https://openalex.org/W4214612132","https://openalex.org/W4237044863","https://openalex.org/W4281752744","https://openalex.org/W4286212078","https://openalex.org/W4308545581","https://openalex.org/W4312276384","https://openalex.org/W4312560592","https://openalex.org/W4322731056","https://openalex.org/W4366976451","https://openalex.org/W4391263123","https://openalex.org/W6600983433","https://openalex.org/W6682864246","https://openalex.org/W6751349269","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790307280","https://openalex.org/W6790690058"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W2276271130","https://openalex.org/W2367393702","https://openalex.org/W4390190241","https://openalex.org/W4386141546","https://openalex.org/W4283332100"],"abstract_inverted_index":{"Over":[0],"the":[1,27,67,73,121,129,133,153,176,196],"past":[2],"few":[3],"years,":[4],"a":[5,92,142],"growing":[6],"number":[7],"of":[8,21,29,69,76],"researchers":[9],"have":[10],"dedicated":[11],"their":[12],"efforts":[13],"to":[14,37,49,66,135,145],"focusing":[15],"on":[16],"temporal":[17,46,163],"modeling.":[18],"The":[19],"advent":[20],"transformer-based":[22],"methods":[23],"has":[24,195],"notably":[25],"advanced":[26],"field":[28],"2D":[30],"image-based":[31],"vision":[32],"tasks.":[33],"However,":[34],"with":[35,132],"respect":[36],"3D":[38,84],"video":[39,50,88],"tasks":[40],"such":[41],"as":[42,91],"action":[43,207],"recognition,":[44],"applying":[45],"transformations":[47],"directly":[48,161],"data":[51,70],"significantly":[52],"increases":[53],"both":[54],"computational":[55],"and":[56,72,82,104,206],"memory":[57],"demands.":[58],"This":[59,111,150],"surge":[60],"in":[61],"resource":[62],"consumption":[63],"is":[64],"due":[65],"multiplication":[68],"patches":[71],"added":[74],"complexity":[75],"self-aware":[77],"computations.":[78],"Accordingly,":[79],"building":[80],"efficient":[81],"precise":[83],"self-attentive":[85],"models":[86],"for":[87,95,156,198],"content":[89],"represents":[90],"major":[93],"challenge":[94],"transformers.":[96],"In":[97],"our":[98],"research,":[99],"we":[100,140],"introduce":[101],"an":[102],"Long":[103],"Short-term":[105],"Temporal":[106],"Difference":[107],"Vision":[108],"Transformer":[109],"(LS-VIT).":[110],"method":[112],"incorporates":[113],"short-term":[114,137],"motion":[115,148,158,169],"details":[116],"into":[117],"images":[118],"by":[119,160],"weighting":[120],"difference":[122],"across":[123,182],"several":[124],"consecutive":[125],"frames,":[126],"thereby":[127],"equipping":[128],"original":[130],"image":[131],"ability":[134],"model":[136],"motions.":[138],"Concurrently,":[139],"integrate":[141],"module":[143,151],"designed":[144],"understand":[146],"long-term":[147,157],"details.":[149],"enhances":[152],"model's":[154],"capacity":[155],"modeling":[159],"integrating":[162],"differences":[164],"from":[165],"various":[166],"segments":[167],"via":[168],"excitation.":[170],"Our":[171],"thorough":[172],"analysis":[173],"confirms":[174],"that":[175,193],"LS-VIT":[177,194],"achieves":[178],"high":[179],"recognition":[180],"accuracy":[181],"multiple":[183],"benchmarks":[184],"(e.g.,":[185],"UCF101,":[186],"HMDB51,":[187],"Kinetics-400).":[188],"These":[189],"research":[190],"results":[191],"indicate":[192],"potential":[197],"further":[199],"optimization,":[200],"which":[201],"can":[202],"improve":[203],"real-time":[204],"performance":[205],"prediction":[208],"capabilities.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}