{"id":"https://openalex.org/W2981808500","doi":"https://doi.org/10.1109/iccv.2019.00015","title":"Hierarchical Self-Attention Network for Action Localization in Videos","display_name":"Hierarchical Self-Attention Network for Action Localization in Videos","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2981808500","doi":"https://doi.org/10.1109/iccv.2019.00015","mag":"2981808500"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2019.00015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","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/A5040156484","display_name":"Rizard Renanda Adhi Pramono","orcid":"https://orcid.org/0000-0002-6668-5167"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Rizard Renanda Adhi Pramono","raw_affiliation_strings":["National Taiwan University of Science and Technology, Taipei, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taipei, Taiwan, R.O.C","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077826217","display_name":"Yie\u2010Tarng Chen","orcid":"https://orcid.org/0000-0002-7221-1603"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yie-Tarng Chen","raw_affiliation_strings":["National Taiwan University of Science and Technology, Taipei, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taipei, Taiwan, R.O.C","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111446401","display_name":"Wen\u2010Hsien Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Hsien Fang","raw_affiliation_strings":["National Taiwan University of Science and Technology, Taipei, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taipei, Taiwan, R.O.C","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040156484"],"corresponding_institution_ids":["https://openalex.org/I154864474"],"apc_list":null,"apc_paid":null,"fwci":2.9355,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.93168277,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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":0.9998999834060669,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9901000261306763,"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":0.988099992275238,"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":0.8432321548461914},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.7253419160842896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6494101285934448},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6167165040969849},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5916405320167542},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5134295225143433},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4935542345046997},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.48002615571022034},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45981961488723755},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44614192843437195},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4116794466972351},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3892977833747864},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.264864981174469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8432321548461914},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.7253419160842896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6494101285934448},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6167165040969849},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5916405320167542},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5134295225143433},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4935542345046997},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.48002615571022034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45981961488723755},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44614192843437195},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4116794466972351},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3892977833747864},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.264864981174469},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv.2019.00015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","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":71,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W639708223","https://openalex.org/W1867429401","https://openalex.org/W1923332106","https://openalex.org/W1932624639","https://openalex.org/W1947481528","https://openalex.org/W1967750361","https://openalex.org/W1983364832","https://openalex.org/W2025547231","https://openalex.org/W2034014085","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2139501017","https://openalex.org/W2156303437","https://openalex.org/W2225887246","https://openalex.org/W2407521645","https://openalex.org/W2461621749","https://openalex.org/W2519080876","https://openalex.org/W2557283755","https://openalex.org/W2557728737","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2579024533","https://openalex.org/W2605111198","https://openalex.org/W2611596598","https://openalex.org/W2613718673","https://openalex.org/W2618799552","https://openalex.org/W2752386593","https://openalex.org/W2770446450","https://openalex.org/W2776652812","https://openalex.org/W2796633859","https://openalex.org/W2883697687","https://openalex.org/W2894666173","https://openalex.org/W2895738954","https://openalex.org/W2896457183","https://openalex.org/W2905765182","https://openalex.org/W2950800384","https://openalex.org/W2962722947","https://openalex.org/W2962790054","https://openalex.org/W2962803561","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963161140","https://openalex.org/W2963246338","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963524571","https://openalex.org/W2963736028","https://openalex.org/W2963823258","https://openalex.org/W2964233791","https://openalex.org/W2964318666","https://openalex.org/W2978135654","https://openalex.org/W3106250896","https://openalex.org/W4295238618","https://openalex.org/W4385245566","https://openalex.org/W6600983433","https://openalex.org/W6620707391","https://openalex.org/W6639126518","https://openalex.org/W6682864246","https://openalex.org/W6714138976","https://openalex.org/W6722278271","https://openalex.org/W6727074247","https://openalex.org/W6739901393","https://openalex.org/W6742044253","https://openalex.org/W6743837088","https://openalex.org/W6751741970","https://openalex.org/W6753838523","https://openalex.org/W6754935294","https://openalex.org/W6755002552","https://openalex.org/W6755207826","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2130674020","https://openalex.org/W2093748878","https://openalex.org/W2333771223","https://openalex.org/W2120056845","https://openalex.org/W1981531423","https://openalex.org/W2035264131","https://openalex.org/W1679012645","https://openalex.org/W3036468168","https://openalex.org/W2070318884","https://openalex.org/W2011939812"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,65,87],"novel":[4],"Hierarchical":[5],"Self-Attention":[6],"Network":[7],"(HISAN)":[8],"to":[9,23,44,58,72,111],"generate":[10],"spatial-temporal":[11],"tubes":[12],"for":[13],"action":[14,62,134],"localization":[15,135],"in":[16,131],"videos.":[17],"The":[18],"essence":[19],"of":[20,38,41,48,76,115,133],"HISAN":[21],"is":[22,70,91],"combine":[24],"the":[25,49,74,97,103,108,113,121,128,140],"two-stream":[26,104],"convolutional":[27],"neural":[28],"network":[29],"(CNN)":[30],"with":[31],"hierarchical":[32],"bidirectional":[33,42],"self-attention":[34,43],"mechanism,":[35],"which":[36,93],"comprises":[37],"two":[39],"levels":[40],"efficaciously":[45],"capture":[46],"both":[47],"long-term":[50],"temporal":[51],"dependency":[52],"information":[53,57,101],"and":[54,99,136,143],"spatial":[55],"context":[56],"render":[59],"more":[60],"precise":[61],"localization.":[63],"Also,":[64],"sequence":[66],"rescoring":[67],"(SR)":[68],"algorithm":[69],"employed":[71],"resolve":[73],"dilemma":[75],"inconsistent":[77],"detection":[78],"scores":[79],"incurred":[80],"by":[81],"occlusion":[82],"or":[83],"background":[84],"clutter.":[85],"Moreover,":[86],"new":[88,122],"fusion":[89],"scheme":[90],"invoked,":[92],"integrates":[94],"not":[95],"only":[96],"appearance":[98],"motion":[100,109],"from":[102],"network,":[105],"but":[106],"also":[107],"saliency":[110],"mitigate":[112],"effect":[114],"camera":[116],"motion.":[117],"Simulations":[118],"reveal":[119],"that":[120],"approach":[123],"achieves":[124],"competitive":[125],"performance":[126],"as":[127],"state-of-the-art":[129],"works":[130],"terms":[132],"recognition":[137],"accuracy":[138],"on":[139],"widespread":[141],"UCF101-24":[142],"J-HMDB":[144],"datasets.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}