{"id":"https://openalex.org/W4392979958","doi":"https://doi.org/10.1109/access.2024.3379885","title":"Temporal Shift Module-Based Vision Transformer Network for Action Recognition","display_name":"Temporal Shift Module-Based Vision Transformer Network for Action Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392979958","doi":"https://doi.org/10.1109/access.2024.3379885"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3379885","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3379885","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10476575.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10476575.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035641443","display_name":"Kunpeng Zhang","orcid":"https://orcid.org/0009-0004-2447-8786"},"institutions":[{"id":"https://openalex.org/I119203015","display_name":"Shandong University of Technology","ror":"https://ror.org/02mr3ar13","country_code":"CN","type":"education","lineage":["https://openalex.org/I119203015"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kunpeng Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Shandong University of Technology, Zibo, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Shandong University of Technology, Zibo, China","institution_ids":["https://openalex.org/I119203015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102759629","display_name":"M Lyu","orcid":"https://orcid.org/0009-0008-9466-9456"},"institutions":[{"id":"https://openalex.org/I119203015","display_name":"Shandong University of Technology","ror":"https://ror.org/02mr3ar13","country_code":"CN","type":"education","lineage":["https://openalex.org/I119203015"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyan Lyu","raw_affiliation_strings":["College of Computer Science and Technology, Shandong University of Technology, Zibo, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Shandong University of Technology, Zibo, China","institution_ids":["https://openalex.org/I119203015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106710458","display_name":"Xinxin Guo","orcid":"https://orcid.org/0009-0008-9175-9771"},"institutions":[{"id":"https://openalex.org/I119203015","display_name":"Shandong University of Technology","ror":"https://ror.org/02mr3ar13","country_code":"CN","type":"education","lineage":["https://openalex.org/I119203015"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxin Guo","raw_affiliation_strings":["College of Computer Science and Technology, Shandong University of Technology, Zibo, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Shandong University of Technology, Zibo, China","institution_ids":["https://openalex.org/I119203015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768114","display_name":"Liye Zhang","orcid":"https://orcid.org/0000-0002-4300-1789"},"institutions":[{"id":"https://openalex.org/I119203015","display_name":"Shandong University of Technology","ror":"https://ror.org/02mr3ar13","country_code":"CN","type":"education","lineage":["https://openalex.org/I119203015"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liye Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Shandong University of Technology, Zibo, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Shandong University of Technology, Zibo, China","institution_ids":["https://openalex.org/I119203015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331605","display_name":"Cong Liu","orcid":"https://orcid.org/0000-0002-5999-2126"},"institutions":[{"id":"https://openalex.org/I119203015","display_name":"Shandong University of Technology","ror":"https://ror.org/02mr3ar13","country_code":"CN","type":"education","lineage":["https://openalex.org/I119203015"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Liu","raw_affiliation_strings":["College of Computer Science and Technology, Shandong University of Technology, Zibo, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Shandong University of Technology, Zibo, China","institution_ids":["https://openalex.org/I119203015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035641443"],"corresponding_institution_ids":["https://openalex.org/I119203015"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.1805,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.88266022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"47246","last_page":"47257"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7056475877761841},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.6123225688934326},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5556094646453857},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5038132071495056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46142059564590454},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34405505657196045},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.16381984949111938},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.128869891166687},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11692255735397339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056475877761841},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6123225688934326},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5556094646453857},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5038132071495056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46142059564590454},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34405505657196045},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.16381984949111938},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.128869891166687},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11692255735397339},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3379885","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3379885","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10476575.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5f7ad1e65a7e46f3b575fc46cdc0892f","is_oa":true,"landing_page_url":"https://doaj.org/article/5f7ad1e65a7e46f3b575fc46cdc0892f","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":"IEEE Access, Vol 12, Pp 47246-47257 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3379885","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3379885","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10476575.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1572372522","display_name":null,"funder_award_id":"6200127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3088427785","display_name":null,"funder_award_id":"62001272","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3227050338","display_name":null,"funder_award_id":"ZR2023MF015","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7105863566","display_name":null,"funder_award_id":"ZR2023MF015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392979958.pdf","grobid_xml":"https://content.openalex.org/works/W4392979958.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W787785461","https://openalex.org/W1522734439","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W1947481528","https://openalex.org/W2097117768","https://openalex.org/W2194775991","https://openalex.org/W2395611524","https://openalex.org/W2618530766","https://openalex.org/W2619947201","https://openalex.org/W2799176631","https://openalex.org/W2883429621","https://openalex.org/W2962934715","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2963886665","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3018757597","https://openalex.org/W3034572008","https://openalex.org/W3126721948","https://openalex.org/W3127826845","https://openalex.org/W3138516171","https://openalex.org/W3205497712","https://openalex.org/W3210279979","https://openalex.org/W4206913723","https://openalex.org/W4214612132","https://openalex.org/W4214634256","https://openalex.org/W4221167396","https://openalex.org/W4224932472","https://openalex.org/W4281997767","https://openalex.org/W4285428166","https://openalex.org/W4297426812","https://openalex.org/W4297697565","https://openalex.org/W4313118515","https://openalex.org/W4313886816","https://openalex.org/W4321192599","https://openalex.org/W4366351162","https://openalex.org/W4378977025","https://openalex.org/W4379116393","https://openalex.org/W4385245566","https://openalex.org/W4386071476","https://openalex.org/W4386457940","https://openalex.org/W4389611177","https://openalex.org/W6622789128","https://openalex.org/W6637373629","https://openalex.org/W6682864246","https://openalex.org/W6762718338","https://openalex.org/W6788135285","https://openalex.org/W6810265253","https://openalex.org/W6849298952","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"This":[0,107],"paper":[1],"introduces":[2],"a":[3],"novel":[4],"action":[5,25,92,149],"recognition":[6,26,89,150],"model":[7,38],"named":[8],"ViT-Shift,":[9],"which":[10],"combines":[11],"the":[12,18,45,60,77,97,101,125,131,135,162,168],"Time":[13],"Shift":[14],"Module":[15],"(TSM)":[16],"with":[17],"Vision":[19],"Transformer":[20,62],"(ViT)":[21],"architecture.":[22],"Traditional":[23],"video":[24,67,91],"tasks":[27],"face":[28],"significant":[29],"computational":[30,53,120],"challenges,":[31],"requiring":[32],"substantial":[33],"computing":[34],"resources.":[35],"However,":[36],"our":[37],"successfully":[39],"addresses":[40],"this":[41],"issue":[42],"by":[43],"incorporating":[44],"TSM,":[46],"achieving":[47],"outstanding":[48],"performance":[49,86],"while":[50],"significantly":[51],"reducing":[52,119],"costs.":[54],"Our":[55],"approach":[56],"is":[57],"based":[58],"on":[59,146,161,167],"latest":[61],"self-attention":[63],"mechanism,":[64],"applied":[65],"to":[66,90,111,133],"sequence":[68],"processing":[69],"instead":[70],"of":[71,80,105,130,159],"traditional":[72],"convolutional":[73],"methods.":[74],"To":[75],"preserve":[76],"core":[78],"architecture":[79],"ViT":[81],"and":[82,127,165],"transfer":[83],"its":[84],"excellent":[85],"in":[87],"image":[88],"recognition,":[93],"we":[94,155],"strategically":[95],"introduce":[96],"TSM":[98,132],"only":[99],"before":[100],"multi-head":[102],"attention":[103],"layer":[104],"ViT.":[106],"design":[108,124],"allows":[109],"us":[110],"simulate":[112],"temporal":[113],"interactions":[114],"using":[115],"channel":[116],"shifts,":[117],"effectively":[118],"complexity.":[121],"We":[122],"carefully":[123],"position":[126],"shift":[128],"parameters":[129],"maximize":[134],"model\u2019s":[136],"performance.":[137],"Experimental":[138],"results":[139,145],"demonstrate":[140],"that":[141],"ViT-Shift":[142],"achieves":[143],"remarkable":[144],"two":[147],"standard":[148],"datasets.":[151],"With":[152],"ImageNet-21K":[153],"pretraining,":[154],"achieve":[156],"an":[157],"accuracy":[158],"77.55%":[160],"Kinetics-400":[163],"dataset":[164],"93.07%":[166],"UCF-101":[169],"dataset.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}