{"id":"https://openalex.org/W4402753877","doi":"https://doi.org/10.1109/cvpr52733.2024.01739","title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","display_name":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402753877","doi":"https://doi.org/10.1109/cvpr52733.2024.01739"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5083585691","display_name":"Alexey A. Gritsenko","orcid":"https://orcid.org/0000-0003-1799-2301"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexey A. Gritsenko","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111029128","display_name":"Xuehan Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuehan Xiong","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010814788","display_name":"Josip Djolonga","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josip Djolonga","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102906366","display_name":"Mostafa Dehghani","orcid":"https://orcid.org/0000-0002-9772-1095"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mostafa Dehghani","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100722234","display_name":"Chen Sun","orcid":"https://orcid.org/0000-0001-8772-9627"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Sun","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044677020","display_name":"Mario Lu\u010di\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mario Lu\u010di\u0107","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035108037","display_name":"Anurag Arnab","orcid":"https://orcid.org/0000-0002-5216-4838"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Arnab","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":6.8381,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.97809593,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"18373","last_page":"18383"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9998000264167786,"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":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.5903159379959106},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5363569855690002},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.18185710906982422},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17765477299690247},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09490713477134705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5903159379959106},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5363569855690002},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.18185710906982422},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17765477299690247},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09490713477134705}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.01739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2034014085","https://openalex.org/W2108598243","https://openalex.org/W2193145675","https://openalex.org/W2222512263","https://openalex.org/W2557728737","https://openalex.org/W2611596598","https://openalex.org/W2618799552","https://openalex.org/W2619947201","https://openalex.org/W2768489488","https://openalex.org/W2806331055","https://openalex.org/W2883275382","https://openalex.org/W2899663614","https://openalex.org/W2951702519","https://openalex.org/W2955874753","https://openalex.org/W2961193895","https://openalex.org/W2962688385","https://openalex.org/W2962722947","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963563276","https://openalex.org/W2963703197","https://openalex.org/W2984287396","https://openalex.org/W2985693775","https://openalex.org/W2990503944","https://openalex.org/W3021385015","https://openalex.org/W3096609285","https://openalex.org/W3096824106","https://openalex.org/W3106250896","https://openalex.org/W3109173645","https://openalex.org/W3123394884","https://openalex.org/W3162565403","https://openalex.org/W3171516518","https://openalex.org/W3172752666","https://openalex.org/W3173407577","https://openalex.org/W3173459793","https://openalex.org/W3203086442","https://openalex.org/W3204116406","https://openalex.org/W4214482673","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4285028122","https://openalex.org/W4302009995","https://openalex.org/W4309396261","https://openalex.org/W4310921506","https://openalex.org/W4312509322","https://openalex.org/W4312558481","https://openalex.org/W4312772544","https://openalex.org/W4319299890","https://openalex.org/W4386057769","https://openalex.org/W4387969909","https://openalex.org/W6620707391","https://openalex.org/W6739901393","https://openalex.org/W6755002552","https://openalex.org/W6755207826","https://openalex.org/W6763711422","https://openalex.org/W6791353385","https://openalex.org/W6798160016","https://openalex.org/W6804424445","https://openalex.org/W6810265253","https://openalex.org/W6839632867","https://openalex.org/W6846313647"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"The":[0],"most":[1],"performant":[2],"spatio-temporal":[3,108],"action":[4,41,109],"localisation":[5,110],"models":[6],"use":[7],"external":[8,13],"person":[9],"proposals":[10],"and":[11,30,39,100,116],"complex":[12],"memory":[14],"banks.":[15],"We":[16,95],"propose":[17],"a":[18,34],"fully":[19],"end-to-end,":[20],"purely-transformer":[21],"based":[22],"model":[23,48,78],"that":[24],"directly":[25],"ingests":[26],"an":[27],"input":[28],"video,":[29],"outputs":[31],"tubelets":[32,71],"-":[33],"sequence":[35],"of":[36,86,92],"bounding":[37],"boxes":[38],"the":[40,73,84,103],"classes":[42],"at":[43],"each":[44],"frame.":[45],"Our":[46],"flexible":[47],"can":[49],"be":[50],"trained":[51],"with":[52,112],"either":[53],"sparse":[54,114],"bounding-box":[55],"supervision":[56],"on":[57,105],"individual":[58],"frames,":[59],"or":[60,88],"full":[61,117],"tubelet":[62,118],"annotations.":[63,119],"And":[64],"in":[65,83,90],"both":[66,113],"cases,":[67],"it":[68],"predicts":[69],"coherent":[70],"as":[72],"output.":[74],"Moreover,":[75],"our":[76],"end-to-end":[77],"requires":[79],"no":[80],"additional":[81],"pre-processing":[82],"form":[85],"proposals,":[87],"post-processing":[89],"terms":[91],"non-maximal":[93],"suppression.":[94],"perform":[96],"extensive":[97],"ablation":[98],"experiments,":[99],"significantly":[101],"advance":[102],"state-of-the-art":[104],"five":[106],"different":[107],"benchmarks":[111],"keyframes":[115]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":7}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}