{"id":"https://openalex.org/W3132791073","doi":"https://doi.org/10.5220/0010215803620369","title":"Long-term Behaviour Recognition in Videos with Actor-focused Region Attention","display_name":"Long-term Behaviour Recognition in Videos with Actor-focused Region Attention","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3132791073","doi":"https://doi.org/10.5220/0010215803620369","mag":"3132791073"},"language":"en","primary_location":{"id":"doi:10.5220/0010215803620369","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010215803620369","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0010215803620369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076227712","display_name":"Luca Ballan","orcid":null},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Luca Ballan","raw_affiliation_strings":["Department of Math, University of Padova, Italy, --- Select a Country ---","Intelligent Imaging, TNO, Oude Waalsdorperweg 63, The Hague, The Netherlands, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Department of Math, University of Padova, Italy, --- Select a Country ---","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Intelligent Imaging, TNO, Oude Waalsdorperweg 63, The Hague, The Netherlands, --- Select a Country ---","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019393740","display_name":"Ombretta Strafforello","orcid":"https://orcid.org/0000-0002-5258-8534"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ombretta Strafforello","raw_affiliation_strings":["Delft University of Technology, The Netherlands, --- Select a Country ---","Intelligent Imaging, TNO, Oude Waalsdorperweg 63, The Hague, The Netherlands, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Intelligent Imaging, TNO, Oude Waalsdorperweg 63, The Hague, The Netherlands, --- Select a Country ---","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113660188","display_name":"Klamer Schutte","orcid":"https://orcid.org/0000-0002-9954-0685"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Klamer Schutte","raw_affiliation_strings":["Intelligent Imaging, TNO, Oude Waalsdorperweg 63, The Hague, The Netherlands, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Intelligent Imaging, TNO, Oude Waalsdorperweg 63, The Hague, The Netherlands, --- Select a Country ---","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076227712"],"corresponding_institution_ids":["https://openalex.org/I138689650"],"apc_list":null,"apc_paid":null,"fwci":0.1937,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.45969965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"362","last_page":"369"},"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":0.9965000152587891,"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":0.9952999949455261,"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/discriminative-model","display_name":"Discriminative model","score":0.8715072870254517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8044030666351318},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.683351993560791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.675234854221344},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6612932085990906},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5990593433380127},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5723817944526672},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.5668370723724365},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5497562885284424},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5480294227600098},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5268306136131287},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5252344608306885},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5076147317886353},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.49625450372695923},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49087268114089966},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4729235768318176},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4268789291381836},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.28188663721084595},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07919555902481079}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8715072870254517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044030666351318},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.683351993560791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.675234854221344},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6612932085990906},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5990593433380127},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5723817944526672},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.5668370723724365},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5497562885284424},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5480294227600098},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5268306136131287},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5252344608306885},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5076147317886353},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.49625450372695923},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49087268114089966},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4729235768318176},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4268789291381836},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.28188663721084595},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07919555902481079},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0010215803620369","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010215803620369","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:bdc14b3b-f4e5-410c-a7df-4565e5bbdc33","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:bdc14b3b-f4e5-410c-a7df-4565e5bbdc33","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"},{"id":"pmh:oai:zenodo.org:131971","is_oa":true,"landing_page_url":"https://www.openaccessrepository.it/record/131971","pdf_url":null,"source":{"id":"https://openalex.org/S4306402478","display_name":"INFM-OAR (INFN Catania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210116497","host_organization_name":"Istituto Nazionale di Fisica Nucleare, Sezione di Catania","host_organization_lineage":["https://openalex.org/I4210116497"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"doi:10.5220/0010215803620369","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010215803620369","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1250097850","display_name":null,"funder_award_id":"P16-25","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G629491556","display_name":null,"funder_award_id":"(NWO)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2053987602","https://openalex.org/W2099614498","https://openalex.org/W2136853139","https://openalex.org/W2292288263","https://openalex.org/W2608988379","https://openalex.org/W2770804203","https://openalex.org/W2806331055","https://openalex.org/W2943833595","https://openalex.org/W2948048211","https://openalex.org/W2951864506","https://openalex.org/W2952686080","https://openalex.org/W2955874753","https://openalex.org/W2963091558","https://openalex.org/W2963524571","https://openalex.org/W2963559058","https://openalex.org/W2963722382","https://openalex.org/W3000279895","https://openalex.org/W3003720578","https://openalex.org/W3128636476","https://openalex.org/W4287825490","https://openalex.org/W4297796628"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W1975325338","https://openalex.org/W2182357018","https://openalex.org/W3181401746","https://openalex.org/W2982423860"],"abstract_inverted_index":{"<p>Long-Term":[0],"activities":[1,15],"involve":[2],"humans":[3],"performing":[4],"complex,":[5],"minutes-long":[6,63],"actions.":[7],"Differently":[8],"than":[9],"in":[10,27,110,136],"traditional":[11],"action":[12],"recognition,":[13],"complex":[14],"are":[16,90,113],"normally":[17],"composed":[18],"of":[19,22,56,160],"a":[20,36,84,93,169],"set":[21],"sub-actions,":[23],"that":[24,40,105,118,144],"can":[25,41],"appear":[26],"different":[28],"order,":[29],"duration,":[30],"and":[31,52,58,138,153],"quantity.":[32],"These":[33,88],"aspects":[34],"introduce":[35,125],"large":[37],"intra-class":[38],"variability,":[39],"be":[42],"hard":[43],"to":[44,49,130],"model.":[45],"Our":[46,141],"approach":[47],"aims":[48],"adaptively":[50],"capture":[51],"learn":[53],"the":[54,76,102,106,111,116,122,132,145,158],"importance":[55],"spatial":[57],"temporal":[59],"video":[60,81],"regions":[61,82],"for":[62],"activity":[64,173],"classification.":[65],"Inspired":[66],"by":[67,101],"previous":[68],"work":[69],"on":[70,167],"Region":[71,154],"Attention,":[72,155],"our":[73],"architecture":[74],"embeds":[75],"spatio-temporal":[77],"features":[78,89],"from":[79],"multiple":[80],"into":[83],"compact":[85],"fixed-length":[86],"representation.":[87],"extracted":[91],"with":[92,150],"3D":[94,162],"convolutional":[95],"backbone":[96],"specially":[97],"fine-tuned.":[98],"Additionally,":[99],"driven":[100],"prior":[103],"assumption":[104],"most":[107],"discriminative":[108],"locations":[109],"videos":[112],"centered":[114],"around":[115],"human":[117],"is":[119],"carrying":[120],"out":[121],"activity,":[123],"we":[124],"an":[126],"Actor":[127,151],"Focus":[128,152],"mechanism":[129],"enhance":[131],"feature":[133],"extraction":[134],"both":[135],"training":[137],"inference":[139],"phase.":[140],"experiments":[142],"show":[143],"Multi-Regional":[146],"fine-tuned":[147],"3D-CNN,":[148],"topped":[149],"largely":[156],"improves":[157],"performance":[159],"baseline":[161],"architectures,":[163],"achieving":[164],"state-of-the-art":[165],"results":[166],"Breakfast,":[168],"well":[170],"known":[171],"long-term":[172],"recognition":[174],"benchmark.</p>":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}