{"id":"https://openalex.org/W3128880094","doi":"https://doi.org/10.1109/tmm.2021.3056892","title":"Spatial-Temporal Action Localization With Hierarchical Self-Attention","display_name":"Spatial-Temporal Action Localization With Hierarchical Self-Attention","publication_year":2021,"publication_date":"2021-02-08","ids":{"openalex":"https://openalex.org/W3128880094","doi":"https://doi.org/10.1109/tmm.2021.3056892","mag":"3128880094"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3056892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3056892","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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":["Electronic and Computer Engineering, National Taiwan University of Science, and Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Electronic and Computer Engineering, National Taiwan University of Science, and Technology, Taipei, Taiwan","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":["Electronic and Computer Engineering, National Taiwan University of Science, and Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Electronic and Computer Engineering, National Taiwan University of Science, and Technology, Taipei, Taiwan","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":["Electronic and Computer Engineering, National Taiwan University of Science, and Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Electronic and Computer Engineering, National Taiwan University of Science, and Technology, Taipei, Taiwan","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":1.1627,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.8001102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"625","last_page":"639"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9991999864578247,"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":0.9979000091552734,"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":0.8636876344680786},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.6868139505386353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6604574918746948},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.544562041759491},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5345664620399475},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.519996702671051},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.49135103821754456},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.45357975363731384},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.450251042842865},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4496519863605499},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4269610345363617},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3884347379207611}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8636876344680786},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.6868139505386353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6604574918746948},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.544562041759491},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5345664620399475},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.519996702671051},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.49135103821754456},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.45357975363731384},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.450251042842865},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4496519863605499},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4269610345363617},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3884347379207611},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3056892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3056892","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G5210284438","display_name":null,"funder_award_id":"MOST 109-2221-E-011-116","funder_id":"https://openalex.org/F4320322108","funder_display_name":"Ministry of Science and Technology"},{"id":"https://openalex.org/G5249279939","display_name":null,"funder_award_id":"MOST 109-2221-E-011-131","funder_id":"https://openalex.org/F4320322108","funder_display_name":"Ministry of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320322108","display_name":"Ministry of Science and Technology","ror":"https://ror.org/032e49973"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W639708223","https://openalex.org/W1797109199","https://openalex.org/W1867429401","https://openalex.org/W1923332106","https://openalex.org/W2025547231","https://openalex.org/W2034014085","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2156303437","https://openalex.org/W2225887246","https://openalex.org/W2519080876","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2579024533","https://openalex.org/W2605111198","https://openalex.org/W2609868498","https://openalex.org/W2611596598","https://openalex.org/W2618799552","https://openalex.org/W2770446450","https://openalex.org/W2776652812","https://openalex.org/W2783231089","https://openalex.org/W2796633859","https://openalex.org/W2806331055","https://openalex.org/W2883275382","https://openalex.org/W2883429621","https://openalex.org/W2894666173","https://openalex.org/W2895738954","https://openalex.org/W2896457183","https://openalex.org/W2903027645","https://openalex.org/W2905016804","https://openalex.org/W2905765182","https://openalex.org/W2911896255","https://openalex.org/W2917790938","https://openalex.org/W2947431308","https://openalex.org/W2948048211","https://openalex.org/W2949343965","https://openalex.org/W2950268230","https://openalex.org/W2951183276","https://openalex.org/W2962688385","https://openalex.org/W2962722947","https://openalex.org/W2962790054","https://openalex.org/W2962803115","https://openalex.org/W2962803561","https://openalex.org/W2962934715","https://openalex.org/W2963091558","https://openalex.org/W2963161140","https://openalex.org/W2963299996","https://openalex.org/W2963351448","https://openalex.org/W2963405520","https://openalex.org/W2963529931","https://openalex.org/W2963563276","https://openalex.org/W2963823258","https://openalex.org/W2964062686","https://openalex.org/W2964072322","https://openalex.org/W2964207322","https://openalex.org/W2981808500","https://openalex.org/W2982277552","https://openalex.org/W2988634822","https://openalex.org/W2990503944","https://openalex.org/W2998360624","https://openalex.org/W2999794487","https://openalex.org/W3094702047","https://openalex.org/W3095022195","https://openalex.org/W3096824106","https://openalex.org/W3106250896","https://openalex.org/W3108226879","https://openalex.org/W3108772932","https://openalex.org/W4295238618","https://openalex.org/W4300796266","https://openalex.org/W4385245566","https://openalex.org/W6600983433","https://openalex.org/W6682864246","https://openalex.org/W6739901393","https://openalex.org/W6751741970","https://openalex.org/W6751936687","https://openalex.org/W6752764193","https://openalex.org/W6755207826","https://openalex.org/W6756044931","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W3148227991","https://openalex.org/W1486593826","https://openalex.org/W2771174107","https://openalex.org/W1536965844","https://openalex.org/W2344941099","https://openalex.org/W4322212724","https://openalex.org/W2106788855","https://openalex.org/W3081561710","https://openalex.org/W2477413883","https://openalex.org/W2463773089"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,17,30,73,103,151],"novel":[4],"architecture":[5,14],"for":[6],"spatial-temporal":[7,46],"action":[8,27,99,174],"localization":[9,100],"in":[10,65],"videos.":[11],"The":[12],"new":[13,31,104,186],"first":[15,110],"employs":[16],"two-stream":[18,137],"3D":[19],"convolutional":[20],"neural":[21],"network":[22,138,154],"(3D-CNN)":[23],"to":[24,43,58,62,83,97,115,143,170],"provide":[25],"initial":[26],"detection.":[28],"Next,":[29],"Hierarchical":[32],"Self-Attention":[33],"Network":[34],"(HiSAN),":[35],"the":[36,45,59,67,88,93,112,117,130,136,140,145,157,160,173,182,185],"core":[37],"of":[38,48,69,75,87,147,159,184],"this":[39],"architecture,":[40],"is":[41,107,168],"developed":[42],"learn":[44],"relationships":[47,68],"key":[49],"actors.":[50,71],"Spatial":[51],"Gaussian":[52],"priors":[53],"(SGP)":[54],"are":[55],"also":[56],"imbued":[57],"bidirectional":[60],"self-attention":[61],"enhance":[63],"HiSAN":[64,80],"modelling":[66],"neighboring":[70],"Such":[72],"combination":[74],"3D-CNN":[76],"and":[77,92,127,132,163],"SGP":[78],"augmented":[79],"allows":[81],"us":[82],"effectively":[84],"extract":[85],"both":[86],"spatial":[89,164],"context":[90],"information":[91,134,165],"long-term":[94],"temporal":[95],"dependency":[96],"improve":[98],"accuracy.":[101],"Afterwards,":[102],"fusion":[105],"strategy":[106],"employed,":[108],"which":[109],"re-scores":[111],"bounding":[113],"boxes":[114],"settle":[116],"inconsistent":[118],"detection":[119],"scores":[120],"caused":[121],"by":[122],"background":[123],"clutter":[124],"or":[125],"occlusion,":[126],"then":[128],"aggregates":[129],"motion":[131,141],"appearance":[133,162],"from":[135],"with":[139],"saliency":[142],"alleviate":[144],"impact":[146],"camera":[148],"movement.":[149],"Finally,":[150],"tube":[152],"association":[153],"based":[155],"on":[156,177],"self-similarity":[158],"actors\u2019":[161],"across":[166],"frames":[167],"addressed":[169],"efficaciously":[171],"construct":[172],"tubes.":[175],"Simulations":[176],"four":[178],"widespread":[179],"datasets":[180],"reveal":[181],"efficacy":[183],"approach.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}
