{"id":"https://openalex.org/W2999794487","doi":"https://doi.org/10.1109/tmm.2020.2965434","title":"Spatio-Temporal Attention Networks for Action Recognition and Detection","display_name":"Spatio-Temporal Attention Networks for Action Recognition and Detection","publication_year":2020,"publication_date":"2020-01-10","ids":{"openalex":"https://openalex.org/W2999794487","doi":"https://doi.org/10.1109/tmm.2020.2965434","mag":"2999794487"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2020.2965434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.2965434","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5100361867","display_name":"Jun Li","orcid":"https://orcid.org/0000-0002-5009-6536"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["State Key Lab of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5009-6536","affiliations":[{"raw_affiliation_string":"State Key Lab of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024067284","display_name":"Xianglong Liu","orcid":"https://orcid.org/0000-0001-8425-4195"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianglong Liu","raw_affiliation_strings":["Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beihang University, Beijing, China","State Key Lab of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8425-4195","affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Lab of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100629630","display_name":"Wenxuan Zhang","orcid":"https://orcid.org/0000-0002-3947-2991"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Zhang","raw_affiliation_strings":["State Key Lab of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3947-2991","affiliations":[{"raw_affiliation_string":"State Key Lab of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100761766","display_name":"Mingyuan Zhang","orcid":"https://orcid.org/0000-0001-8212-715X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyuan Zhang","raw_affiliation_strings":["State Key Lab of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8212-715X","affiliations":[{"raw_affiliation_string":"State Key Lab of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["Innovation Center, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"Innovation Center, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027171279","display_name":"Nicu Sebe","orcid":"https://orcid.org/0000-0002-6597-7248"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicu Sebe","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6597-7248","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.4745,"has_fulltext":false,"cited_by_count":174,"citation_normalized_percentile":{"value":0.9916307,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"22","issue":"11","first_page":"2990","last_page":"3001"},"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":0.9961000084877014,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9925000071525574,"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/computer-science","display_name":"Computer science","score":0.8738551735877991},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8287132978439331},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7235956192016602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6814658045768738},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6560499668121338},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.6006292700767517},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5124137997627258},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5098627805709839},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4974389374256134},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4946746528148651},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4162352979183197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8738551735877991},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8287132978439331},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7235956192016602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6814658045768738},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6560499668121338},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6006292700767517},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5124137997627258},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5098627805709839},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4974389374256134},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4946746528148651},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4162352979183197},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2020.2965434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.2965434","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:iris.unitn.it:11572/284440","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/284440","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1186537922","display_name":"\u9762\u5411\u89c6\u9891\u5927\u6570\u636e\u68c0\u7d22\u7684\u54c8\u5e0c\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61872021","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8297228719","display_name":null,"funder_award_id":"61690202","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":92,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W45291132","https://openalex.org/W854541894","https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1745334888","https://openalex.org/W1855115939","https://openalex.org/W1944615693","https://openalex.org/W1983364832","https://openalex.org/W2105101328","https://openalex.org/W2122710056","https://openalex.org/W2126579184","https://openalex.org/W2133564696","https://openalex.org/W2156303437","https://openalex.org/W2187772033","https://openalex.org/W2194775991","https://openalex.org/W2342662179","https://openalex.org/W2342776425","https://openalex.org/W2507009361","https://openalex.org/W2519080876","https://openalex.org/W2519750370","https://openalex.org/W2522495877","https://openalex.org/W2578257192","https://openalex.org/W2593722617","https://openalex.org/W2597958930","https://openalex.org/W2607566495","https://openalex.org/W2746726611","https://openalex.org/W2751445731","https://openalex.org/W2752386593","https://openalex.org/W2752782242","https://openalex.org/W2767514117","https://openalex.org/W2777542469","https://openalex.org/W2798345491","https://openalex.org/W2798472916","https://openalex.org/W2809562466","https://openalex.org/W2883429621","https://openalex.org/W2884585870","https://openalex.org/W2884969173","https://openalex.org/W2888003147","https://openalex.org/W2893260909","https://openalex.org/W2904619119","https://openalex.org/W2926312400","https://openalex.org/W2947084868","https://openalex.org/W2957408986","https://openalex.org/W2962876901","https://openalex.org/W2962899219","https://openalex.org/W2962934715","https://openalex.org/W2962965405","https://openalex.org/W2963015194","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963177663","https://openalex.org/W2963216700","https://openalex.org/W2963247196","https://openalex.org/W2963321993","https://openalex.org/W2963420686","https://openalex.org/W2963484593","https://openalex.org/W2963495494","https://openalex.org/W2963524571","https://openalex.org/W2963645879","https://openalex.org/W2963750390","https://openalex.org/W2963820951","https://openalex.org/W2963850050","https://openalex.org/W2963886665","https://openalex.org/W2963901365","https://openalex.org/W2963934593","https://openalex.org/W2964107601","https://openalex.org/W2964214371","https://openalex.org/W2964216549","https://openalex.org/W2964233791","https://openalex.org/W2964308564","https://openalex.org/W2981385151","https://openalex.org/W2981808500","https://openalex.org/W2981860940","https://openalex.org/W2990152177","https://openalex.org/W2992457155","https://openalex.org/W2994508843","https://openalex.org/W3101203783","https://openalex.org/W4294557331","https://openalex.org/W4294566634","https://openalex.org/W4323697410","https://openalex.org/W6600983433","https://openalex.org/W6623517193","https://openalex.org/W6630875275","https://openalex.org/W6679434410","https://openalex.org/W6682864246","https://openalex.org/W6684983439","https://openalex.org/W6686679147","https://openalex.org/W6727508455","https://openalex.org/W6743837088","https://openalex.org/W6755431558","https://openalex.org/W6765575767"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W1998222986","https://openalex.org/W3208297503","https://openalex.org/W3119773509","https://openalex.org/W2182357018","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W4309346246"],"abstract_inverted_index":{"Recently,":[0],"3D":[1,30,105,128],"Convolutional":[2],"Neural":[3],"Network":[4],"(3D":[5],"CNN)":[6],"models":[7],"have":[8],"been":[9],"widely":[10],"studied":[11],"for":[12,69,131],"video":[13,35,47,132],"sequences":[14],"and":[15,22,42,82,93,135,145,154,157,175,184,187],"achieved":[16],"satisfying":[17],"performance":[18,172],"in":[19,91],"action":[20,133,143],"recognition":[21,144],"detection":[23,134,146],"tasks.":[24],"However,":[25],"most":[26],"of":[27,103,182],"the":[28,40,46,51,65,74,79,83,89,100,104,109,126,158,170,179],"existing":[29],"CNNs":[31],"treat":[32],"all":[33],"input":[34],"frames":[36],"equally,":[37],"thus":[38],"ignoring":[39],"spatial":[41,92],"temporal":[43,94],"differences":[44,90],"across":[45],"frames.":[48],"To":[49],"address":[50],"problem,":[52],"we":[53],"propose":[54],"a":[55,120],"spatio-temporal":[56],"attention":[57],"(STA)":[58],"network":[59,166],"that":[60,162],"is":[61],"able":[62],"to":[63],"learn":[64],"discriminative":[66],"feature":[67],"representation":[68],"actions,":[70],"by":[71],"respectively":[72],"characterizing":[73],"beneficial":[75],"information":[76],"at":[77],"both":[78],"frame":[80],"level":[81],"channel":[84],"level.":[85],"By":[86],"simultaneously":[87],"exploiting":[88],"dimensions,":[95],"our":[96,140,164],"STA":[97,114,165],"module":[98,122,167],"enhances":[99],"learning":[101],"capability":[102],"convolutions":[106],"when":[107],"handling":[108],"complex":[110],"videos.":[111],"The":[112],"proposed":[113],"method":[115,141],"can":[116,168],"be":[117],"wrapped":[118],"as":[119],"generic":[121],"easily":[123],"plugged":[124],"into":[125],"state-of-the-art":[127,171],"CNN":[129],"architectures":[130],"recognition.":[136],"We":[137],"extensively":[138],"evaluate":[139],"on":[142,173,191],"tasks":[147],"over":[148],"three":[149],"popular":[150],"datasets":[151],"(UCF-101,":[152],"HMDB-51":[153],"THUMOS":[155,192],"2014),":[156],"experimental":[159],"results":[160],"demonstrate":[161],"adding":[163],"obtain":[169],"UCF-101":[174],"HMDB-51,":[176],"which":[177],"has":[178],"top-1":[180],"accuracies":[181],"98.4%":[183],"81.4%":[185],"respectively,":[186],"achieve":[188],"significant":[189],"improvement":[190],"2014":[193],"dataset":[194],"compared":[195],"against":[196],"original":[197],"models.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":34},{"year":2022,"cited_by_count":33},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":15}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2020-01-23T00:00:00"}