{"id":"https://openalex.org/W2933934000","doi":"https://doi.org/10.1109/icassp.2019.8683720","title":"Learning Temporal Information from Spatial Information Using CapsNets for Human Action Recognition","display_name":"Learning Temporal Information from Spatial Information Using CapsNets for Human Action Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2933934000","doi":"https://doi.org/10.1109/icassp.2019.8683720","mag":"2933934000"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Learning_temporal_information_from_spatial_information_using_CapsNets_for_human_action_recognition/20746468","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079661654","display_name":"Abdullah M. Algamdi","orcid":null},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Abdullah M. Algamdi","raw_affiliation_strings":["Dept. of Computer Science, University of Warwick, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634965","display_name":"V\u00edctor S\u00e1nchez","orcid":"https://orcid.org/0000-0002-7089-7031"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Victor Sanchez","raw_affiliation_strings":["Dept. of Computer Science, University of Warwick, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075200053","display_name":"Chang\u2010Tsun Li","orcid":"https://orcid.org/0000-0003-4735-6138"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chang-Tsun Li","raw_affiliation_strings":["School of Information Technology, Deakin University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2903,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.83971129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3867","last_page":"3871"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9975000023841858,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.813201904296875},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7205929756164551},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.7158589363098145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.715049147605896},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6822407841682434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5983328223228455},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5572691559791565},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5509516000747681},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.46471700072288513},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.44846946001052856},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.43456345796585083},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34760481119155884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3366019129753113},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07420626282691956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.813201904296875},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7205929756164551},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.7158589363098145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.715049147605896},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6822407841682434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5983328223228455},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5572691559791565},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5509516000747681},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46471700072288513},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.44846946001052856},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.43456345796585083},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34760481119155884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3366019129753113},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07420626282691956},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":3,"locations":[{"id":"doi:10.1109/icassp.2019.8683720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:wrap.warwick.ac.uk:114383","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400665","display_name":"Warwick Research Archive Portal (University of Warwick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39555362","host_organization_name":"University of Warwick","host_organization_lineage":["https://openalex.org/I39555362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Item"},{"id":"pmh:oai:figshare.com:article/20746468","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Learning_temporal_information_from_spatial_information_using_CapsNets_for_human_action_recognition/20746468","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":null,"raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20746468","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Learning_temporal_information_from_spatial_information_using_CapsNets_for_human_action_recognition/20746468","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":null,"raw_type":"Conference contribution"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1836465849","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2034328688","https://openalex.org/W2095705004","https://openalex.org/W2101194540","https://openalex.org/W2112796928","https://openalex.org/W2122476475","https://openalex.org/W2156303437","https://openalex.org/W2308045930","https://openalex.org/W2342662179","https://openalex.org/W2504108613","https://openalex.org/W2519080876","https://openalex.org/W2606538621","https://openalex.org/W2785994986","https://openalex.org/W2797472209","https://openalex.org/W2809361304","https://openalex.org/W2810685774","https://openalex.org/W2884745705","https://openalex.org/W2891845086","https://openalex.org/W2949117887","https://openalex.org/W2963384288","https://openalex.org/W2963524571","https://openalex.org/W2963574257","https://openalex.org/W2963703618","https://openalex.org/W2963823258","https://openalex.org/W2964318666","https://openalex.org/W3101197104","https://openalex.org/W4249279051","https://openalex.org/W4290379497","https://openalex.org/W4295238618","https://openalex.org/W6638667902","https://openalex.org/W6639736908","https://openalex.org/W6674330103","https://openalex.org/W6674985822","https://openalex.org/W6678029491","https://openalex.org/W6682864246","https://openalex.org/W6743446608","https://openalex.org/W6748053814","https://openalex.org/W6750207810","https://openalex.org/W6751741970","https://openalex.org/W6752812278"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2468279273","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372"],"abstract_inverted_index":{"Capsule":[0],"Networks":[1,16],"(CapsNets)":[2],"are":[3],"recently":[4],"introduced":[5],"to":[6,25,59],"overcome":[7],"some":[8,72],"of":[9,12,73,82,105],"the":[10,30,61,66,74,80,83,92,106,109,121],"shortcomings":[11],"traditional":[13,103],"Convolutional":[14],"Neural":[15],"(CNNs).":[17],"CapsNets":[18],"replace":[19],"neurons":[20],"in":[21],"CNNs":[22],"with":[23,101],"vectors":[24],"retain":[26],"spatial":[27,93],"relationships":[28],"among":[29],"features.":[31,76],"In":[32],"this":[33],"paper,":[34],"we":[35],"propose":[36,56],"a":[37,102],"CapsNet":[38,111],"architecture":[39,85],"that":[40],"employs":[41],"individual":[42],"video":[43,98],"frames":[44],"for":[45],"human":[46],"action":[47,113],"recognition":[48,114],"without":[49],"explicitly":[50],"extracting":[51],"motion":[52],"information.":[53],"We":[54,77],"also":[55],"weight":[57],"pooling":[58],"reduce":[60],"computational":[62],"complexity":[63],"and":[64,118,123],"improve":[65],"classification":[67],"accuracy":[68],"by":[69,90,116],"appropriately":[70],"removing":[71],"extracted":[75,95],"show":[78],"how":[79],"capsules":[81],"proposed":[84,110],"can":[86],"encode":[87],"temporal":[88],"information":[89],"using":[91],"features":[94],"from":[96],"several":[97],"frames.":[99],"Compared":[100],"CNN":[104],"same":[107],"complexity,":[108],"improves":[112],"performance":[115],"12.11%":[117],"22.29%":[119],"on":[120],"KTH":[122],"UCF-sports":[124],"datasets,":[125],"respectively.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}