{"id":"https://openalex.org/W4312509322","doi":"https://doi.org/10.1109/cvpr52688.2022.01323","title":"TubeR: Tubelet Transformer for Video Action Detection","display_name":"TubeR: Tubelet Transformer for Video Action Detection","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4312509322","doi":"https://doi.org/10.1109/cvpr52688.2022.01323"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52688.2022.01323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.01323","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5072790694","display_name":"Jiaojiao Zhao","orcid":"https://orcid.org/0000-0002-4448-7602"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jiaojiao Zhao","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003300255","display_name":"Yanyi Zhang","orcid":"https://orcid.org/0000-0001-5238-1712"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yanyi Zhang","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406079","display_name":"Xinyu Li","orcid":"https://orcid.org/0000-0001-5398-3707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Li","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353664","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0003-4417-614X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048015379","display_name":"Bing Shuai","orcid":"https://orcid.org/0000-0001-5811-9950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bing Shuai","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078029945","display_name":"Mingze Xu","orcid":"https://orcid.org/0000-0002-0671-4122"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingze Xu","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100761545","display_name":"Chunhui Liu","orcid":"https://orcid.org/0000-0002-9397-7042"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunhui Liu","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029670387","display_name":"Kaustav Kundu","orcid":"https://orcid.org/0000-0002-1262-4465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaustav Kundu","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005925571","display_name":"Yuanjun Xiong","orcid":"https://orcid.org/0000-0002-6391-4921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanjun Xiong","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044605684","display_name":"Davide Modolo","orcid":"https://orcid.org/0000-0002-7625-7748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davide Modolo","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068126329","display_name":"Ivan Marsic","orcid":"https://orcid.org/0000-0002-1033-6865"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ivan Marsic","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024508073","display_name":"Cees G. M. Snoek","orcid":"https://orcid.org/0000-0001-9092-1556"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cees G.M. Snoek","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002114219","display_name":"Joseph Tighe","orcid":"https://orcid.org/0000-0002-0716-8119"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph Tighe","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.1179,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.97699811,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13588","last_page":"13597"},"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":0.9976000189781189,"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":0.9973999857902527,"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":0.7542150616645813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6352418661117554},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5910804867744446},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5555658936500549},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5268591642379761},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4957362115383148},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4900742769241333},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4753679633140564},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4359486699104309},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4321577250957489},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4280547797679901},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.42235037684440613},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32256019115448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7542150616645813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6352418661117554},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5910804867744446},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5555658936500549},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5268591642379761},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4957362115383148},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4900742769241333},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4753679633140564},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4359486699104309},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4321577250957489},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4280547797679901},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.42235037684440613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32256019115448},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52688.2022.01323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.01323","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W639708223","https://openalex.org/W1797109199","https://openalex.org/W1923332106","https://openalex.org/W2018068650","https://openalex.org/W2034014085","https://openalex.org/W2097342496","https://openalex.org/W2145943327","https://openalex.org/W2222512263","https://openalex.org/W2519080876","https://openalex.org/W2611596598","https://openalex.org/W2618799552","https://openalex.org/W2619947201","https://openalex.org/W2883275382","https://openalex.org/W2895738954","https://openalex.org/W2908510526","https://openalex.org/W2949343965","https://openalex.org/W2955874753","https://openalex.org/W2962722947","https://openalex.org/W2962790054","https://openalex.org/W2962803561","https://openalex.org/W2963091558","https://openalex.org/W2963529931","https://openalex.org/W2963563276","https://openalex.org/W2964207322","https://openalex.org/W2984287396","https://openalex.org/W2990503944","https://openalex.org/W2990818246","https://openalex.org/W3034572008","https://openalex.org/W3035029089","https://openalex.org/W3035422918","https://openalex.org/W3037777866","https://openalex.org/W3092462694","https://openalex.org/W3094702047","https://openalex.org/W3096609285","https://openalex.org/W3096824106","https://openalex.org/W3100712674","https://openalex.org/W3109173645","https://openalex.org/W3121523901","https://openalex.org/W3173407577","https://openalex.org/W3197341423","https://openalex.org/W3204116406","https://openalex.org/W3212973774","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4287776244","https://openalex.org/W4385245566","https://openalex.org/W6600983433","https://openalex.org/W6681511049","https://openalex.org/W6722278271","https://openalex.org/W6727074247","https://openalex.org/W6734051801","https://openalex.org/W6739901393","https://openalex.org/W6753598266","https://openalex.org/W6753784496","https://openalex.org/W6755002552","https://openalex.org/W6757817989","https://openalex.org/W6761461645","https://openalex.org/W6772548311","https://openalex.org/W6776840935","https://openalex.org/W6777846773","https://openalex.org/W6778485988","https://openalex.org/W6780165341","https://openalex.org/W6784094891","https://openalex.org/W6784353115","https://openalex.org/W6798038150","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W1891287906","https://openalex.org/W2941155331","https://openalex.org/W2013076218","https://openalex.org/W4362599043","https://openalex.org/W2726222394","https://openalex.org/W3106494386","https://openalex.org/W2100518354","https://openalex.org/W4221141247","https://openalex.org/W4312421085"],"abstract_inverted_index":{"We":[0],"propose":[1,32,98],"TubeR:":[2],"a":[3,40,50,55,61,71,99],"simple":[4],"solution":[5],"for":[6,120,140],"spatio-temporal":[7,68,87],"video":[8,41,72,142],"action":[9,37,45,112,116,125,130,152],"detection.":[10],"Different":[11],"from":[12,49],"existing":[13],"methods":[14],"that":[15],"depend":[16],"on":[17,149,163],"either":[18],"an":[19,36,115],"offline":[20],"actor":[21],"detector":[22],"or":[23,29,94],"hand-designed":[24],"actor-positional":[25,83],"hypotheses":[26,84],"like":[27],"proposals":[28],"anchors,":[30],"we":[31,97],"to":[33,64,81,104,110],"directly":[34,128],"detect":[35],"tubelet":[38],"in":[39,85],"by":[42],"simultaneously":[43],"performing":[44],"localization":[46],"and":[47,59,107,114,135,157],"recognition":[48],"single":[51],"representation.":[52],"TubeR":[53,127,144],"learns":[54],"set":[56],"of":[57,70],"tubelet-queries":[58],"utilizes":[60],"tubelet-attention":[62],"module":[63],"model":[65,78],"the":[66,77,86,122,146],"dynamic":[67],"nature":[69],"clip,":[73],"which":[74],"effectively":[75],"reinforces":[76],"capacity":[79],"compared":[80],"using":[82],"space.":[88],"For":[89],"videos":[90],"containing":[91],"transitional":[92],"states":[93],"scene":[95],"changes,":[96],"context":[100,109],"aware":[101],"classification":[102],"head":[103,119],"utilize":[105],"short-term":[106],"long-term":[108],"strengthen":[111],"classification,":[113],"switch":[117],"regression":[118],"detecting":[121],"precise":[123],"temporal":[124],"extent.":[126],"produces":[129],"tubelets":[131],"with":[132],"variable":[133],"lengths":[134],"even":[136],"maintains":[137],"good":[138],"results":[139],"long":[141],"clips.":[143],"outperforms":[145],"previous":[147],"state-of-the-art":[148],"commonly":[150],"used":[151],"detection":[153],"datasets":[154],"AVA,":[155],"UCF101-24":[156],"JHMDB51-21.":[158],"Code":[159],"will":[160],"be":[161],"available":[162],"GluonCV(https://cv.gluon.ai/).":[164]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}