{"id":"https://openalex.org/W3126009523","doi":"https://doi.org/10.1109/cvpr46437.2021.00054","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","display_name":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3126009523","doi":"https://doi.org/10.1109/cvpr46437.2021.00054","mag":"3126009523"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr46437.2021.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.06184","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012128387","display_name":"Toby Perrett","orcid":"https://orcid.org/0000-0002-1676-3729"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Toby Perrett","raw_affiliation_strings":["Department of Computer Science, University of Bristol, UK","University of Bristol Department of Computer Science UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"University of Bristol Department of Computer Science UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044316430","display_name":"Alessandro Masullo","orcid":"https://orcid.org/0000-0002-6510-835X"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alessandro Masullo","raw_affiliation_strings":["Department of Computer Science, University of Bristol, UK","University of Bristol Department of Computer Science UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"University of Bristol Department of Computer Science UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052504255","display_name":"Tilo Burghardt","orcid":"https://orcid.org/0000-0002-8506-012X"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tilo Burghardt","raw_affiliation_strings":["Department of Computer Science, University of Bristol, UK","University of Bristol"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"University of Bristol","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007937949","display_name":"Majid Mirmehdi","orcid":"https://orcid.org/0000-0002-6478-1403"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Majid Mirmehdi","raw_affiliation_strings":["Department of Computer Science, University of Bristol, UK","University of Bristol Department of Computer Science UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"University of Bristol Department of Computer Science UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003103666","display_name":"Dima Damen","orcid":"https://orcid.org/0000-0001-8804-6238"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dima Damen","raw_affiliation_strings":["Department of Computer Science, University of Bristol, UK","University of Bristol Department of Computer Science UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"University of Bristol Department of Computer Science UK","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"475","last_page":"484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9955000281333923,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9921000003814697,"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":0.7197611927986145},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6404028534889221},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6332647800445557},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6298462152481079},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6250186562538147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6204121112823486},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6108060479164124},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.584796667098999},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5483853816986084},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5231308341026306},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.510833740234375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36636942625045776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2703210711479187},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24231606721878052},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08325877785682678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7197611927986145},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6404028534889221},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6332647800445557},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6298462152481079},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6250186562538147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6204121112823486},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6108060479164124},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.584796667098999},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5483853816986084},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5231308341026306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.510833740234375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36636942625045776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2703210711479187},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24231606721878052},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08325877785682678},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/cvpr46437.2021.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.06184","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.06184","pdf_url":"https://arxiv.org/pdf/2101.06184","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":"","raw_type":"text"},{"id":"pmh:oai:research-information.bris.ac.uk:publications/0e50eb4f-330b-4eb4-af49-96c3edb8a1b4","is_oa":true,"landing_page_url":"https://hdl.handle.net/1983/0e50eb4f-330b-4eb4-af49-96c3edb8a1b4","pdf_url":"https://research-information.bris.ac.uk/ws/files/270319066/Toby_Transformer_1_1_.pdf","source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Perrett, T J, Masullo, A, Burghardt, T, Mirmehdi, M & Damen, D 2021, Temporal-Relational CrossTransformers for Few-Shot Action Recognition. in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Conference on Computer Vision and Pattern Recognition (CVPR), Institute of Electrical and Electronics Engineers (IEEE), pp. 475-484. https://doi.org/10.1109/cvpr46437.2021.00054","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:3126009523","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2101.06184","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:research-information.bris.ac.uk:openaire/0e50eb4f-330b-4eb4-af49-96c3edb8a1b4","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/0e50eb4f-330b-4eb4-af49-96c3edb8a1b4","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Perrett, T J, Masullo, A, Burghardt, T, Mirmehdi, M & Damen, D 2021, Temporal-Relational CrossTransformers for Few-Shot Action Recognition. in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Conference on Computer Vision and Pattern Recognition (CVPR), Institute of Electrical and Electronics Engineers (IEEE), pp. 475-484. https://doi.org/10.1109/cvpr46437.2021.00054","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2101.06184","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2101.06184","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.06184","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.06184","pdf_url":"https://arxiv.org/pdf/2101.06184","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2656745747","display_name":null,"funder_award_id":"EP/T004991/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7396137307","display_name":null,"funder_award_id":"EP/R005273/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2126579184","https://openalex.org/W2194775991","https://openalex.org/W2507009361","https://openalex.org/W2561272927","https://openalex.org/W2601450892","https://openalex.org/W2625366777","https://openalex.org/W2770804203","https://openalex.org/W2798592524","https://openalex.org/W2892122929","https://openalex.org/W2894873912","https://openalex.org/W2963341924","https://openalex.org/W2963403868","https://openalex.org/W2963524571","https://openalex.org/W2964111881","https://openalex.org/W2964242760","https://openalex.org/W2970990534","https://openalex.org/W2974429152","https://openalex.org/W2974470310","https://openalex.org/W2981385151","https://openalex.org/W2983156430","https://openalex.org/W2984818716","https://openalex.org/W2990503944","https://openalex.org/W2994785205","https://openalex.org/W2995253937","https://openalex.org/W3021778166","https://openalex.org/W3034587791","https://openalex.org/W3035374961","https://openalex.org/W3037932933","https://openalex.org/W3041485444","https://openalex.org/W3095374178","https://openalex.org/W3099495704","https://openalex.org/W6600983433","https://openalex.org/W6717697761","https://openalex.org/W6724944384","https://openalex.org/W6735236233","https://openalex.org/W6739901393","https://openalex.org/W6746798562","https://openalex.org/W6749916090","https://openalex.org/W6750254146","https://openalex.org/W6754673040","https://openalex.org/W6760378562","https://openalex.org/W6764592398","https://openalex.org/W6766578407","https://openalex.org/W6780226713","https://openalex.org/W6780975210","https://openalex.org/W6789158709"],"related_works":["https://openalex.org/W3173271747","https://openalex.org/W2963996402","https://openalex.org/W2999981474","https://openalex.org/W2954662570","https://openalex.org/W3200749679","https://openalex.org/W3177599622","https://openalex.org/W2928966231","https://openalex.org/W3123394884","https://openalex.org/W2505121268","https://openalex.org/W2626212608","https://openalex.org/W3182022070","https://openalex.org/W3113141731","https://openalex.org/W2935832171","https://openalex.org/W3205215025","https://openalex.org/W2901286235","https://openalex.org/W2618264182","https://openalex.org/W2750400961","https://openalex.org/W2953379097","https://openalex.org/W1901212503","https://openalex.org/W2898226671"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,110],"novel":[3],"approach":[4],"to":[5,36,76,115,119,131],"few-shot":[6,25,91],"action":[7],"recognition,":[8],"finding":[9],"temporally-corresponding":[10],"frame":[11],"tuples":[12,59],"between":[13],"the":[14,19,32,116,127],"query":[15],"and":[16,73,99,136],"videos":[17,135],"in":[18],"support":[20,42,133],"set.":[21],"Distinct":[22],"from":[23,57],"previous":[24],"works,":[26],"we":[27],"construct":[28],"class":[29,47],"prototypes":[30],"using":[31,46],"CrossTransformer":[33],"attention":[34],"mechanism":[35],"observe":[37],"relevant":[38],"sub-sequences":[39,67],"of":[40,60,63,68,93,129],"all":[41],"videos,":[43],"rather":[44],"than":[45],"averages":[48],"or":[49],"single":[50],"best":[51],"matches.":[52],"Video":[53],"representations":[54],"are":[55],"formed":[56],"ordered":[58],"varying":[61],"numbers":[62],"frames,":[64],"which":[65],"allows":[66],"actions":[69],"at":[70],"different":[71],"speeds":[72],"temporal":[74,121],"offsets":[75],"be":[77],"compared.":[78],"<sup":[79],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[80],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[81],"Our":[82],"proposed":[83],"Temporal-Relational":[84],"CrossTransformers":[85],"(TRX)":[86],"achieve":[87],"state-of-the-art":[88],"results":[89],"on":[90,107],"splits":[92],"Kinetics,":[94],"Something-Something":[95],"V2":[96],"(SSv2),":[97],"HMDB51":[98],"UCF101.":[100],"Importantly,":[101],"our":[102],"method":[103],"outperforms":[104],"prior":[105],"work":[106],"SSv2":[108],"by":[109],"wide":[111],"margin":[112],"(12%)":[113],"due":[114],"its":[117],"ability":[118],"model":[120],"relations.":[122],"A":[123],"detailed":[124],"ablation":[125],"showcases":[126],"importance":[128],"matching":[130],"multiple":[132],"set":[134],"learning":[137],"higher-order":[138],"relational":[139],"CrossTransformers.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}