{"id":"https://openalex.org/W4375801629","doi":"https://doi.org/10.1109/thms.2023.3266037","title":"A Multitemporal Scale and Spatial\u2013Temporal Transformer Network for Temporal Action Localization","display_name":"A Multitemporal Scale and Spatial\u2013Temporal Transformer Network for Temporal Action Localization","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375801629","doi":"https://doi.org/10.1109/thms.2023.3266037"},"language":"en","primary_location":{"id":"doi:10.1109/thms.2023.3266037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2023.3266037","pdf_url":null,"source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Human-Machine Systems","raw_type":"journal-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/A5048947531","display_name":"Zan Gao","orcid":"https://orcid.org/0000-0003-2182-5741"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]},{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zan Gao","raw_affiliation_strings":["Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","Key Laboratory of Computer Vision and System, Ministry of Education, Tianjin University of Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-2182-5741","affiliations":[{"raw_affiliation_string":"Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I4210142748","https://openalex.org/I152269853"]},{"raw_affiliation_string":"Key Laboratory of Computer Vision and System, Ministry of Education, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080551725","display_name":"Xinglei Cui","orcid":"https://orcid.org/0000-0002-2459-8057"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinglei Cui","raw_affiliation_strings":["Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I4210142748","https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042406159","display_name":"Tao Zhuo","orcid":"https://orcid.org/0000-0001-8860-1887"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhuo","raw_affiliation_strings":["Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-8860-1887","affiliations":[{"raw_affiliation_string":"Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I4210142748","https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068843001","display_name":"Zhiyong Cheng","orcid":"https://orcid.org/0000-0003-1109-5028"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Cheng","raw_affiliation_strings":["Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-1109-5028","affiliations":[{"raw_affiliation_string":"Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I4210142748","https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081485810","display_name":"An-An Liu","orcid":"https://orcid.org/0000-0001-5755-9145"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An-An Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5755-9145","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-7735","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055627037","display_name":"Shengyong Chen","orcid":"https://orcid.org/0000-0002-6705-3831"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenyong Chen","raw_affiliation_strings":["Key Laboratory of Computer Vision and System, Ministry of Education, Tianjin University of Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-6705-3831","affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer Vision and System, Ministry of Education, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5048947531"],"corresponding_institution_ids":["https://openalex.org/I136765683","https://openalex.org/I152269853","https://openalex.org/I4210142748"],"apc_list":null,"apc_paid":null,"fwci":1.6485,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85899611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"53","issue":"3","first_page":"569","last_page":"580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.993399977684021,"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/T11227","display_name":"Diabetic Foot Ulcer Assessment and Management","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7567149996757507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6330046653747559},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5838921666145325},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5672439932823181},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4875151813030243},{"id":"https://openalex.org/keywords/temporal-scales","display_name":"Temporal scales","score":0.47310924530029297},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43745359778404236},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4218364953994751},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.41875356435775757},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07085168361663818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567149996757507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6330046653747559},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5838921666145325},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5672439932823181},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4875151813030243},{"id":"https://openalex.org/C2777489503","wikidata":"https://www.wikidata.org/wiki/Q7698936","display_name":"Temporal scales","level":2,"score":0.47310924530029297},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43745359778404236},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4218364953994751},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.41875356435775757},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07085168361663818},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/thms.2023.3266037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2023.3266037","pdf_url":null,"source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Human-Machine Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1592249304","display_name":null,"funder_award_id":"62020106004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1616174128","display_name":null,"funder_award_id":"62171145","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5230037210","display_name":null,"funder_award_id":"61906108","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5370040448","display_name":null,"funder_award_id":"92048301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8806062088","display_name":null,"funder_award_id":"61872270","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1536680647","https://openalex.org/W1927052826","https://openalex.org/W2072070523","https://openalex.org/W2336403884","https://openalex.org/W2344034899","https://openalex.org/W2486996822","https://openalex.org/W2593722617","https://openalex.org/W2597958930","https://openalex.org/W2604114396","https://openalex.org/W2766402183","https://openalex.org/W2884561390","https://openalex.org/W2905706796","https://openalex.org/W2952435096","https://openalex.org/W2962677524","https://openalex.org/W2962766617","https://openalex.org/W2962876901","https://openalex.org/W2963247196","https://openalex.org/W2963524571","https://openalex.org/W2964107628","https://openalex.org/W2964121718","https://openalex.org/W2964214371","https://openalex.org/W2964216549","https://openalex.org/W2971915722","https://openalex.org/W2983918066","https://openalex.org/W2986407524","https://openalex.org/W2997410994","https://openalex.org/W2997706915","https://openalex.org/W2999794487","https://openalex.org/W3007751154","https://openalex.org/W3010801020","https://openalex.org/W3012573144","https://openalex.org/W3034623254","https://openalex.org/W3069380482","https://openalex.org/W3094502228","https://openalex.org/W3100481960","https://openalex.org/W3106041614","https://openalex.org/W3110589170","https://openalex.org/W3110854813","https://openalex.org/W3111420154","https://openalex.org/W3128626728","https://openalex.org/W3137592945","https://openalex.org/W3171707680","https://openalex.org/W3172837290","https://openalex.org/W3174569083","https://openalex.org/W3176444885","https://openalex.org/W3176641851","https://openalex.org/W3179107710","https://openalex.org/W3202076256","https://openalex.org/W3215017813","https://openalex.org/W4200630755","https://openalex.org/W4205260486","https://openalex.org/W4213183958","https://openalex.org/W4214612132","https://openalex.org/W4221160129","https://openalex.org/W4230270698","https://openalex.org/W4284965682","https://openalex.org/W4312305353","https://openalex.org/W4313555695","https://openalex.org/W4385245566","https://openalex.org/W6722654596","https://openalex.org/W6736356174","https://openalex.org/W6739901393","https://openalex.org/W6775096394","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6798533924"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2119949815"],"abstract_inverted_index":{"Temporal":[0],"action":[1,46,59,87,158,181],"localization":[2],"plays":[3],"an":[4,198],"important":[5],"role":[6],"in":[7,17,191],"video":[8,67,142],"analysis,":[9],"which":[10,89],"aims":[11],"to":[12,110,116,120,136,161,173],"localize":[13],"and":[14,177,195,200,218,234,251],"classify":[15],"actions":[16,24,91],"untrimmed":[18],"videos.":[19],"Previous":[20],"methods":[21],"often":[22,70],"predict":[23],"on":[25,92,214,222,238],"a":[26,30,39,49,76,93,132,154,169,192],"feature":[27,94,105],"space":[28,95],"of":[29,38,57,66,96,107,126,141,179,248],"single":[31],"temporal":[32,36,86,98,124],"scale.":[33],"However,":[34],"the":[35,54,58,63,122,127,138,145,164,175,207,215,223,239,242],"features":[37,147],"low-level":[40,117],"scale":[41,51,125],"lack":[42],"sufficient":[43],"semantics":[44,112],"for":[45,85,156],"classification,":[47],"while":[48],"high-level":[50,114],"cannot":[52],"provide":[53],"rich":[55],"details":[56],"boundaries.":[60],"In":[61],"addition,":[62],"long-range":[64,139,149],"dependencies":[65,140,150],"frames":[68],"are":[69,151,188],"ignored.":[71],"To":[72],"address":[73],"these":[74,185],"issues,":[75],"novel":[77],"multitemporal-scale":[78],"spatial\u2013temporal":[79,133],"transformer":[80,134],"(MSST)":[81],"network":[82],"is":[83],"proposed":[84,208,243],"localization,":[88],"predicts":[90],"multiple":[97],"scales.":[99,118],"Specifically,":[100],"we":[101,130,167],"first":[102],"use":[103,131],"refined":[104,146],"pyramids":[106],"different":[108],"scales":[109,115],"pass":[111],"from":[113],"Second,":[119],"establish":[121],"long":[123],"entire":[128],"video,":[129],"encoder":[135],"capture":[137],"frames.":[143],"Then,":[144],"with":[148,227],"fed":[152],"into":[153],"classifier":[155],"coarse":[157],"prediction.":[159],"Finally,":[160],"further":[162],"improve":[163],"prediction":[165],"accuracy,":[166],"propose":[168],"frame-level":[170],"self-attention":[171],"module":[172],"refine":[174],"classification":[176],"boundaries":[178],"each":[180],"instance.":[182],"Most":[183],"importantly,":[184],"three":[186],"modules":[187],"jointly":[189],"explored":[190],"unified":[193],"framework,":[194],"MSST":[196],"has":[197],"anchor-free":[199],"end-to-end":[201],"architecture.":[202],"Extensive":[203],"experiments":[204],"show":[205],"that":[206],"method":[209,244],"can":[210,245],"outperform":[211],"state-of-the-art":[212],"approaches":[213],"THUMOS14":[216,240],"dataset":[217],"achieve":[219,246],"comparable":[220],"performance":[221],"ActivityNet1.3":[224],"dataset.":[225],"Compared":[226],"A2Net":[228],"(TIP20,":[229],"Avg{0.3:0.7}),":[230],"Sub-Action":[231],"(CSVT2022,":[232],"Avg{0.1:0.5}),":[233],"AFSD":[235],"(CVPR21,":[236],"Avg{0.3:0.7})":[237],"dataset,":[241],"improvements":[247],"12.6%,":[249],"17.4%,":[250],"2.2%,":[252],"respectively.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}