{"id":"https://openalex.org/W4411245261","doi":"https://doi.org/10.5244/c.35.207","title":"Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition","display_name":"Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W4411245261","doi":"https://doi.org/10.5244/c.35.207"},"language":"en","primary_location":{"id":"doi:10.5244/c.35.207","doi":"https://doi.org/10.5244/c.35.207","is_oa":false,"landing_page_url":"https://doi.org/10.5244/c.35.207","pdf_url":null,"source":{"id":"https://openalex.org/S7407088578","display_name":"British Machine Vision Conference (BMVC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the British Machine Vision Conference 2021","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.13008","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100619564","display_name":"Hao Ni","orcid":"https://orcid.org/0000-0001-5485-4376","observed_orcids":["https://orcid.org/0000-0001-5485-4376","https://orcid.org/0009-0000-0164-9571"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Ni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049087255","display_name":"Shujian Liao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujian Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071177749","display_name":"Weixin Yang","orcid":"https://orcid.org/0000-0002-6028-3597","observed_orcids":["https://orcid.org/0000-0002-6028-3597"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weixin Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068145301","display_name":"Kevin Schlegel","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Schlegel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033716148","display_name":"Terry Lyons","orcid":"https://orcid.org/0000-0002-9972-2809","observed_orcids":["https://orcid.org/0000-0002-9972-2809"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Terry J Lyons","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9301,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.83712259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9887999892234802,"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":0.9887999892234802,"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":0.008100000210106373,"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/T12290","display_name":"Human Motion and Animation","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/skeleton-based-action-recognition","display_name":"skeleton-based action recognition","score":0.9369999766349792},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.7910000085830688},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"gesture recognition","score":0.5849999785423279},{"id":"https://openalex.org/keywords/non-uniform-sampling","display_name":"non-uniform sampling","score":0.7009999752044678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7344700694084167},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7323876023292542},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.6823562979698181},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6397255063056946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149298906326294},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.41868856549263},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32950758934020996},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2270558476448059},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0702509880065918},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.5244/c.35.207","doi":"https://doi.org/10.5244/c.35.207","is_oa":false,"landing_page_url":"https://doi.org/10.5244/c.35.207","pdf_url":null,"source":{"id":"https://openalex.org/S7407088578","display_name":"British Machine Vision Conference (BMVC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the British Machine Vision Conference 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.13008","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.13008","pdf_url":"https://arxiv.org/pdf/2110.13008","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":"pmh:oai:ora.ox.ac.uk:uuid:4bbc5844-9a07-409d-95fb-d9e1a35772c9","doi":null,"is_oa":true,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:4bbc5844-9a07-409d-95fb-d9e1a35772c9/files/s8g84mn63g","pdf_url":"https://ora.ox.ac.uk/objects/uuid:4bbc5844-9a07-409d-95fb-d9e1a35772c9/files/s8g84mn63g","source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"http://purl.org/coar/resource_type/c_5794"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10138576","doi":null,"is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10138576/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Proceedings of the The British Machine Vision Conference (BMVC) 2021. The British Machine Vision Association: Virtual Conference. (2021)","raw_type":"Proceedings paper"},{"id":"doi:10.48550/arxiv.2110.13008","doi":"https://doi.org/10.48550/arxiv.2110.13008","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.13008","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.13008","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.13008","pdf_url":"https://arxiv.org/pdf/2110.13008","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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1633672591","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3481878861","display_name":null,"funder_award_id":"EP/S026347/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G444630160","display_name":null,"funder_award_id":"EP/N510129/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4500485203","display_name":"The Alan Turing Institute","funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8593039737","display_name":"Unparameterised multi-modal data, high order signatures, and the mathematics of data science","funder_award_id":"EP/S026347/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8597009950","display_name":null,"funder_award_id":"EP/N510129/1","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411245261.pdf","grobid_xml":"https://content.openalex.org/works/W4411245261.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W242877468","https://openalex.org/W616109306","https://openalex.org/W1593543504","https://openalex.org/W1744759976","https://openalex.org/W1792076819","https://openalex.org/W1899985242","https://openalex.org/W2004095444","https://openalex.org/W2021150171","https://openalex.org/W2031334527","https://openalex.org/W2034014085","https://openalex.org/W2108036388","https://openalex.org/W2119818729","https://openalex.org/W2139794777","https://openalex.org/W2143246460","https://openalex.org/W2184544926","https://openalex.org/W2217325140","https://openalex.org/W2263883519","https://openalex.org/W2269155608","https://openalex.org/W2284126738","https://openalex.org/W2510185399","https://openalex.org/W2524629569","https://openalex.org/W2526981417","https://openalex.org/W2530921800","https://openalex.org/W2602311553","https://openalex.org/W2606294640","https://openalex.org/W2716916105","https://openalex.org/W2735590100","https://openalex.org/W2739179646","https://openalex.org/W2770491442","https://openalex.org/W2786632635","https://openalex.org/W2788385411","https://openalex.org/W2793547936","https://openalex.org/W2799211965","https://openalex.org/W2914177721","https://openalex.org/W2940457086","https://openalex.org/W2944006115","https://openalex.org/W2948246283","https://openalex.org/W2954146807","https://openalex.org/W2962961015","https://openalex.org/W2963369114","https://openalex.org/W2964134613","https://openalex.org/W2964650603","https://openalex.org/W2967417633","https://openalex.org/W2970176295","https://openalex.org/W2973161331","https://openalex.org/W2991612390","https://openalex.org/W2994713923","https://openalex.org/W2997014690","https://openalex.org/W3002648974","https://openalex.org/W3004354124","https://openalex.org/W3035050855","https://openalex.org/W3035225512","https://openalex.org/W3047772167","https://openalex.org/W3092754310","https://openalex.org/W3096986660","https://openalex.org/W3100267010","https://openalex.org/W3106415951","https://openalex.org/W4388320797","https://openalex.org/W4391324012","https://openalex.org/W4416013347"],"related_works":["https://openalex.org/W2893690698","https://openalex.org/W4411245363","https://openalex.org/W6965068950","https://openalex.org/W3206873236","https://openalex.org/W3151766654","https://openalex.org/W2602561964","https://openalex.org/W7168378018","https://openalex.org/W3036183338","https://openalex.org/W2911114674","https://openalex.org/W2752434477"],"abstract_inverted_index":{"This":[0],"paper":[1],"contributes":[2],"to":[3,17,23,113],"the":[4,28,44,47,61,95,120,125,134,138,146,169,183],"challenge":[5],"of":[6,46,65,86,94,161],"skeleton-based":[7],"human":[8],"action":[9,157],"recognition":[10],"in":[11,141,159],"videos.":[12],"The":[13,56],"key":[14],"step":[15],"is":[16,43],"develop":[18],"a":[19,37],"generic":[20],"network":[21],"architecture":[22],"extract":[24],"discriminative":[25],"features":[26],"for":[27,71],"spatio-temporal":[29],"skeleton":[30],"data.":[31],"In":[32,165],"this":[33],"paper,":[34],"we":[35,107,167],"propose":[36,108],"novel":[38],"module,":[39],"namely":[40],"Logsig-RNN,":[41],"which":[42,74,98],"combination":[45],"log-signature":[48],"layer":[49],"and":[50,67,83,153,163],"recurrent":[51,96],"type":[52],"neural":[53,104],"networks":[54,143],"(RNNs).":[55],"former":[57],"one":[58],"comes":[59],"from":[60],"mathematically":[62],"principled":[63],"technology":[64],"signatures":[66],"log-signatures":[68],"as":[69,91],"representations":[70],"streamed":[72],"data,":[73],"can":[75,99],"manage":[76],"high":[77],"sample":[78],"rate":[79],"streams,":[80],"non-uniform":[81],"sampling":[82],"time":[84],"series":[85],"variable":[87],"length.":[88],"It":[89],"serves":[90],"an":[92],"enhancement":[93],"layer,":[97],"be":[100],"conveniently":[101],"plugged":[102],"into":[103,124],"networks.":[105],"Besides":[106],"two":[109],"path":[110,116,179],"transformation":[111,180],"layers":[112,181],"significantly":[114],"reduce":[115],"dimension":[117],"while":[118],"retaining":[119],"essential":[121],"information":[122],"fed":[123],"Logsig-RNN":[126,139],"module.":[127],"Finally,":[128],"numerical":[129],"results":[130],"demonstrate":[131],"that":[132],"replacing":[133],"RNN":[135],"module":[136,140],"by":[137,176],"SOTA":[142],"consistently":[144],"improves":[145],"performance":[147],"on":[148,172],"both":[149],"Chalearn":[150],"gesture":[151,174],"data":[152,158,175],"NTU":[154],"RGB+D":[155],"120":[156],"terms":[160],"accuracy":[162,171],"robustness.":[164],"particular,":[166],"achieve":[168],"state-of-the-art":[170],"Chalearn2013":[173],"combining":[177],"simple":[178],"with":[182],"Logsig-RNN.":[184],"Codes":[185],"are":[186],"available":[187],"at":[188],"https://github.com/steveliao93/GCN_LogsigRNN.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}