{"id":"https://openalex.org/W2619082050","doi":"https://doi.org/10.1109/cvpr.2017.502","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","display_name":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2619082050","doi":"https://doi.org/10.1109/cvpr.2017.502","mag":"2619082050"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2017.502","doi":"https://doi.org/10.1109/cvpr.2017.502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2017.502","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1705.07750","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057909195","display_name":"Jo\u00e3o Carreira","orcid":"https://orcid.org/0000-0002-0207-1254","observed_orcids":["https://orcid.org/0000-0002-0207-1254"]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joao Carreira","raw_affiliation_strings":["DeepMind","[DeepMind]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"[DeepMind]","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573","observed_orcids":["https://orcid.org/0000-0002-8945-8573"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":["DeepMind","Department of Engineering Science, University of Oxford","[DeepMind, Department of Engineering Science, University of Oxford]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"Department of Engineering Science, University of Oxford","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"[DeepMind, Department of Engineering Science, University of Oxford]","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":158.681,"has_fulltext":true,"cited_by_count":9510,"citation_normalized_percentile":{"value":0.99950304,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4724","last_page":"4733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.00019999999494757503,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/human-action-recognition","display_name":"human action recognition","score":0.8889999985694885},{"id":"https://openalex.org/keywords/i3d","display_name":"I3D","score":0.8539999723434448},{"id":"https://openalex.org/keywords/two-stream-architecture","display_name":"dual-stream architecture","score":0.734000027179718},{"id":"https://openalex.org/keywords/spatiotemporal-feature-extraction","display_name":"spatiotemporal feature extraction","score":0.8349999785423279},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.7379999756813049},{"id":"https://openalex.org/keywords/video-classification","display_name":"video classification","score":0.6179999709129333},{"id":"https://openalex.org/keywords/ucf101","display_name":"UCF101","score":0.8960000276565552},{"id":"https://openalex.org/keywords/hmdb51","display_name":"HMDB51","score":0.9430000185966492},{"id":"https://openalex.org/keywords/youtube-videos","display_name":"YouTube videos","score":0.38600000739097595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.837685227394104},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7272685766220093},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7259336709976196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6163535118103027},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5193861126899719},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5049694180488586},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4714924991130829},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4602595269680023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45523667335510254},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44919607043266296},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4204503893852234},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cvpr.2017.502","doi":"https://doi.org/10.1109/cvpr.2017.502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2017.502","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1705.07750","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.07750","pdf_url":"https://arxiv.org/pdf/1705.07750","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"mag:2619082050","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1705.07750","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1705.07750","doi":"https://doi.org/10.48550/arxiv.1705.07750","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1705.07750","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1705.07750","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.07750","pdf_url":"https://arxiv.org/pdf/1705.07750","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2619082050.pdf","grobid_xml":"https://content.openalex.org/works/W2619082050.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W237546731","https://openalex.org/W639708223","https://openalex.org/W1522734439","https://openalex.org/W1567708943","https://openalex.org/W1578985305","https://openalex.org/W1586730761","https://openalex.org/W1686810756","https://openalex.org/W1923332106","https://openalex.org/W1923404803","https://openalex.org/W1926645898","https://openalex.org/W1944615693","https://openalex.org/W1947481528","https://openalex.org/W2016053056","https://openalex.org/W2102605133","https://openalex.org/W2105101328","https://openalex.org/W2115749350","https://openalex.org/W2126579184","https://openalex.org/W2135658380","https://openalex.org/W2142194269","https://openalex.org/W2156303437","https://openalex.org/W2158169396","https://openalex.org/W2161381512","https://openalex.org/W2165715280","https://openalex.org/W2194775991","https://openalex.org/W2271840356","https://openalex.org/W2308045930","https://openalex.org/W2326533993","https://openalex.org/W2342662179","https://openalex.org/W2462996230","https://openalex.org/W2484328966","https://openalex.org/W2507009361","https://openalex.org/W2519080876","https://openalex.org/W2553594924","https://openalex.org/W2619947201","https://openalex.org/W2949117887","https://openalex.org/W2953084276","https://openalex.org/W2963246338"],"related_works":["https://openalex.org/W24089286","https://openalex.org/W2194775991","https://openalex.org/W1522734439","https://openalex.org/W2619947201","https://openalex.org/W2105101328","https://openalex.org/W2952186347","https://openalex.org/W2308045930","https://openalex.org/W2126579184","https://openalex.org/W2949117887","https://openalex.org/W2016053056","https://openalex.org/W1983364832","https://openalex.org/W1947481528","https://openalex.org/W2953084276","https://openalex.org/W1686810756","https://openalex.org/W2950971447","https://openalex.org/W2980823292","https://openalex.org/W2142194269","https://openalex.org/W1522301498","https://openalex.org/W3183673044","https://openalex.org/W2747474452"],"abstract_inverted_index":{"The":[0],"paucity":[1],"of":[2,38,50,85,126],"videos":[3],"in":[4,36,171],"current":[5,79],"action":[6,57,86,172],"classification":[7,87,130],"datasets":[8,100],"(UCF-101":[9],"and":[10,59,65,91,123,153,178],"HMDB-51)":[11],"has":[12,47],"made":[13],"it":[14,137],"difficult":[15],"to":[16,139],"identify":[17],"good":[18],"video":[19,146],"architectures,":[20],"as":[21],"most":[22],"methods":[23],"obtain":[24],"similar":[25],"performance":[26,94],"on":[27,77,82,88,96,103,118,162,176,180],"existing":[28],"small-scale":[29],"benchmarks.":[30],"This":[31],"paper":[32],"re-evaluates":[33],"state-of-the-art":[34,170],"architectures":[35,80],"light":[37],"the":[39,83,97,169],"new":[40,109],"Kinetics":[41,46],"Human":[42],"Action":[43],"Video":[44],"dataset.":[45],"two":[48],"orders":[49],"magnitude":[51],"more":[52],"data,":[53],"with":[54],"400":[55,61],"human":[56],"classes":[58],"over":[60],"clips":[62],"per":[63],"class,":[64],"is":[66,116],"collected":[67],"from":[68,145],"realistic,":[69],"challenging":[70],"YouTube":[71],"videos.":[72],"We":[73,105,157],"provide":[74],"an":[75],"analysis":[76],"how":[78,92],"fare":[81],"task":[84],"this":[89],"dataset":[90],"much":[93],"improves":[95],"smaller":[98],"benchmark":[99],"after":[101,160],"pre-training":[102,161],"Kinetics.":[104],"also":[106],"introduce":[107],"a":[108],"Two-Stream":[110],"Inflated":[111],"3D":[112],"ConvNet":[113,120],"(I3D)":[114],"that":[115],"based":[117],"2D":[119],"inflation:":[121],"filters":[122],"pooling":[124],"kernels":[125],"very":[127],"deep":[128],"image":[129],"ConvNets":[131],"are":[132],"expanded":[133],"into":[134],"3D,":[135],"making":[136],"possible":[138],"learn":[140],"seamless":[141],"spatio-temporal":[142],"feature":[143],"extractors":[144],"while":[147],"leveraging":[148],"successful":[149],"ImageNet":[150],"architecture":[151],"designs":[152],"even":[154],"their":[155],"parameters.":[156],"show":[158],"that,":[159],"Kinetics,":[163],"I3D":[164],"models":[165],"considerably":[166],"improve":[167],"upon":[168],"classification,":[173],"reaching":[174],"80.2%":[175],"HMDB-51":[177],"97.9%":[179],"UCF-101.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":667},{"year":2025,"cited_by_count":1221},{"year":2024,"cited_by_count":1415},{"year":2023,"cited_by_count":1491},{"year":2022,"cited_by_count":1314},{"year":2021,"cited_by_count":1412},{"year":2020,"cited_by_count":996},{"year":2019,"cited_by_count":700},{"year":2018,"cited_by_count":275},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-18T09:31:52.927876","created_date":"2025-10-10T00:00:00"}