{"id":"https://openalex.org/W3173459793","doi":"https://doi.org/10.1109/tip.2022.3195321","title":"End-to-End Temporal Action Detection With Transformer","display_name":"End-to-End Temporal Action Detection With Transformer","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3173459793","doi":"https://doi.org/10.1109/tip.2022.3195321","mag":"3173459793","pmid":"https://pubmed.ncbi.nlm.nih.gov/35947570"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3195321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3195321","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.10271","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022801548","display_name":"Xiaolong Liu","orcid":"https://orcid.org/0000-0003-1143-9951"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Liu","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-1143-9951","affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083340374","display_name":"Qimeng Wang","orcid":"https://orcid.org/0000-0002-9715-836X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qimeng Wang","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-9715-836X","affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107062676","display_name":"Yao Hu","orcid":"https://orcid.org/0009-0006-1274-7111"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Hu","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059262797","display_name":"Xu Tang","orcid":"https://orcid.org/0000-0003-1375-0778"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Tang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449697","display_name":"Shiwei Zhang","orcid":"https://orcid.org/0000-0002-6929-5295"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwei Zhang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562162","display_name":"Song Bai","orcid":"https://orcid.org/0000-0002-2570-9118"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Bai","raw_affiliation_strings":["ByteDance Inc., Raffles Quay, Singapore","School of Electronic Information and Communications, Huazhong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-2570-9118","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Raffles Quay, Singapore","institution_ids":[]},{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bai","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3449-5940","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.3494,"has_fulltext":false,"cited_by_count":264,"citation_normalized_percentile":{"value":0.99705457,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"5427","last_page":"5441"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"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":0.9926999807357788,"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":0.826916515827179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6086388230323792},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5662881135940552},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.48929545283317566},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4725192189216614},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4579460024833679},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4322115182876587},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35275423526763916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826916515827179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086388230323792},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5662881135940552},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.48929545283317566},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4725192189216614},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4579460024833679},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4322115182876587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35275423526763916},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2022.3195321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3195321","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:35947570","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35947570","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":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:arXiv.org:2106.10271","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.10271","pdf_url":"https://arxiv.org/pdf/2106.10271","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.10271","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.10271","pdf_url":"https://arxiv.org/pdf/2106.10271","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4132073842","display_name":null,"funder_award_id":"2018YFB1004600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":92,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2336403884","https://openalex.org/W2463824207","https://openalex.org/W2471143248","https://openalex.org/W2472970127","https://openalex.org/W2486996822","https://openalex.org/W2507009361","https://openalex.org/W2519328139","https://openalex.org/W2529163075","https://openalex.org/W2550143307","https://openalex.org/W2593722617","https://openalex.org/W2597958930","https://openalex.org/W2599765304","https://openalex.org/W2604113307","https://openalex.org/W2607566495","https://openalex.org/W2751832138","https://openalex.org/W2755876276","https://openalex.org/W2765277449","https://openalex.org/W2766402183","https://openalex.org/W2805042136","https://openalex.org/W2883915488","https://openalex.org/W2884293275","https://openalex.org/W2884561390","https://openalex.org/W2884969173","https://openalex.org/W2895240652","https://openalex.org/W2908510526","https://openalex.org/W2948229620","https://openalex.org/W2950534130","https://openalex.org/W2952435096","https://openalex.org/W2962677524","https://openalex.org/W2962709777","https://openalex.org/W2962876901","https://openalex.org/W2963150697","https://openalex.org/W2963247196","https://openalex.org/W2963321993","https://openalex.org/W2963351113","https://openalex.org/W2963351448","https://openalex.org/W2963403868","https://openalex.org/W2963524571","https://openalex.org/W2963563276","https://openalex.org/W2964008341","https://openalex.org/W2964214371","https://openalex.org/W2964216549","https://openalex.org/W2964274041","https://openalex.org/W2981851019","https://openalex.org/W2983918066","https://openalex.org/W2986407524","https://openalex.org/W2989042503","https://openalex.org/W2994508843","https://openalex.org/W2998601171","https://openalex.org/W3034623254","https://openalex.org/W3035265375","https://openalex.org/W3069380482","https://openalex.org/W3092462694","https://openalex.org/W3095669214","https://openalex.org/W3096609285","https://openalex.org/W3099758941","https://openalex.org/W3100481960","https://openalex.org/W3106041614","https://openalex.org/W3109715102","https://openalex.org/W3110589170","https://openalex.org/W3111420154","https://openalex.org/W3122239467","https://openalex.org/W3123394884","https://openalex.org/W3126721948","https://openalex.org/W3128626728","https://openalex.org/W3164690902","https://openalex.org/W3168294587","https://openalex.org/W3172347581","https://openalex.org/W3173212682","https://openalex.org/W3176444885","https://openalex.org/W3177433885","https://openalex.org/W3185799881","https://openalex.org/W3189800722","https://openalex.org/W3203848195","https://openalex.org/W3208474254","https://openalex.org/W4225264236","https://openalex.org/W4226142324","https://openalex.org/W4287551379","https://openalex.org/W4312294051","https://openalex.org/W4312747676","https://openalex.org/W4313050661","https://openalex.org/W4385245566","https://openalex.org/W4394666973","https://openalex.org/W6739901393","https://openalex.org/W6745476028","https://openalex.org/W6757817989","https://openalex.org/W6784094891","https://openalex.org/W6789619165","https://openalex.org/W6790307280","https://openalex.org/W6795672903","https://openalex.org/W6839769395"],"related_works":["https://openalex.org/W1556451512","https://openalex.org/W1555349535","https://openalex.org/W4234091740","https://openalex.org/W4213350282","https://openalex.org/W2230171082","https://openalex.org/W2583128298","https://openalex.org/W2022275305","https://openalex.org/W1604115909","https://openalex.org/W2551337514","https://openalex.org/W4283332100"],"abstract_inverted_index":{"Temporal":[0],"action":[1,16,87,104,204],"detection":[2],"(TAD)":[3],"aims":[4],"to":[5,43,112,118,134,155],"determine":[6],"the":[7,11,60,96,107,157,162],"semantic":[8],"label":[9],"and":[10,26,47,55,62,101,148,159,195],"temporal":[12,92,127],"interval":[13],"of":[14,83,138,161],"every":[15],"instance":[17],"in":[18,29,141],"an":[19,71,149,202],"untrimmed":[20],"video.":[21,143],"It":[22],"is":[23,125,213],"a":[24,80,126,135,142,168,184],"fundamental":[25],"challenging":[27],"task":[28,36],"video":[30,97],"understanding.":[31],"Previous":[32],"methods":[33],"tackle":[34],"this":[35,67],"with":[37,106,201],"complicated":[38],"pipelines.":[39],"They":[40],"often":[41],"need":[42],"train":[44],"multiple":[45],"networks":[46],"involve":[48],"hand-designed":[49],"operations,":[50],"such":[51,167],"as":[52],"non-maximal":[53],"suppression":[54],"anchor":[56],"generation,":[57],"which":[58],"limit":[59],"flexibility":[61],"prevent":[63],"end-to-end":[64,72],"learning.":[65],"In":[66],"paper,":[68],"we":[69,114],"propose":[70,115],"Transformer-based":[73],"method":[74],"for":[75,98],"TAD,":[76,113],"termed":[77],"TadTR.":[78],"Given":[79],"small":[81],"set":[82,137],"learnable":[84],"embeddings":[85],"called":[86],"queries,":[88],"TadTR":[89,171],"adaptively":[90],"extracts":[91],"context":[93],"information":[94],"from":[95],"each":[99],"query":[100],"directly":[102],"predicts":[103],"instances":[105],"context.":[108],"To":[109],"adapt":[110],"Transformer":[111],"three":[116],"improvements":[117],"enhance":[119],"its":[120],"locality":[121],"awareness.":[122],"The":[123],"core":[124],"deformable":[128],"attention":[129],"module":[130],"that":[131],"selectively":[132],"attends":[133],"sparse":[136],"key":[139],"snippets":[140],"A":[144],"segment":[145],"refinement":[146],"mechanism":[147],"actionness":[150],"regression":[151],"head":[152],"are":[153],"designed":[154],"refine":[156],"boundaries":[158],"confidence":[160],"predicted":[163],"instances,":[164],"respectively.":[165],"With":[166],"simple":[169],"pipeline,":[170],"requires":[172],"lower":[173],"computation":[174],"cost":[175],"than":[176],"previous":[177],"detectors,":[178],"while":[179],"preserving":[180],"remarkable":[181],"performance.":[182],"As":[183],"self-contained":[185],"detector,":[186],"it":[187,206],"achieves":[188],"state-of-the-art":[189],"performance":[190],"on":[191,210],"THUMOS14":[192],"(56.7%":[193],"mAP)":[194],"HACS":[196],"Segments":[197],"(32.09%":[198],"mAP).":[199],"Combined":[200],"extra":[203],"classifier,":[205],"obtains":[207],"36.75%":[208],"mAP":[209],"ActivityNet-1.3.":[211],"Code":[212],"available":[214],"at":[215],"https://github.com/xlliu7/TadTR.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":77},{"year":2024,"cited_by_count":86},{"year":2023,"cited_by_count":61},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}