{"id":"https://openalex.org/W4408355067","doi":"https://doi.org/10.1109/icassp49660.2025.10888662","title":"LkSFocalNets: Video Action Recognition With Large Kernel Selective Focal Networks","display_name":"LkSFocalNets: Video Action Recognition With Large Kernel Selective Focal Networks","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355067","doi":"https://doi.org/10.1109/icassp49660.2025.10888662"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5059946311","display_name":"Jian Xiao","orcid":"https://orcid.org/0000-0002-4412-588X"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Xiao","raw_affiliation_strings":["Communication University of China,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,Beijing,China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100553175","display_name":"Shi Ping","orcid":"https://orcid.org/0009-0003-7744-6246"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Shi","raw_affiliation_strings":["Communication University of China,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,Beijing,China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035762730","display_name":"Qipei Li","orcid":"https://orcid.org/0000-0001-7692-2245"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qipei Li","raw_affiliation_strings":["Communication University of China,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,Beijing,China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.991599977016449,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9629999995231628,"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":0.669333815574646},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.6574770212173462},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5002784729003906},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4747101366519928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44037336111068726},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.412209153175354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07142606377601624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.669333815574646},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6574770212173462},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5002784729003906},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4747101366519928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44037336111068726},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.412209153175354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07142606377601624},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":40,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1923404803","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2553594924","https://openalex.org/W2895243423","https://openalex.org/W2948048211","https://openalex.org/W2963091558","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3034572008","https://openalex.org/W3035303837","https://openalex.org/W3094502228","https://openalex.org/W3108241103","https://openalex.org/W3126721948","https://openalex.org/W3173621652","https://openalex.org/W3216270236","https://openalex.org/W4214516465","https://openalex.org/W4246193833","https://openalex.org/W4312276384","https://openalex.org/W4312560592","https://openalex.org/W4312658081","https://openalex.org/W4312769131","https://openalex.org/W4375868862","https://openalex.org/W4381198761","https://openalex.org/W4386072015","https://openalex.org/W4386076625","https://openalex.org/W4390872179","https://openalex.org/W4390873076","https://openalex.org/W4392903964","https://openalex.org/W4402754139","https://openalex.org/W4402754177","https://openalex.org/W6754337694","https://openalex.org/W6762718338","https://openalex.org/W6787254463","https://openalex.org/W6797263693","https://openalex.org/W6810661123","https://openalex.org/W6810859482"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Video":[0,55],"action":[1],"recognition":[2],"tasks":[3],"face":[4],"the":[5,48,54,63,72,84,97,137],"trade-off":[6],"challenge":[7],"between":[8],"computational":[9,26,93,144],"cost":[10],"and":[11,53,132],"performance.":[12],"Existing":[13],"models":[14,74,131],"often":[15],"compromise":[16],"their":[17],"ability":[18],"to":[19,24,66,117],"capture":[20,67],"extensive":[21],"contextual":[22,69],"information":[23],"reduce":[25],"complexity.":[27,145],"To":[28],"address":[29],"this":[30,32],"issue,":[31],"paper":[33],"proposes":[34],"Large":[35,108],"Kernel":[36,49,109],"Selective":[37,50,110],"Focal":[38,56,111],"Networks":[39],"(LkSFocalNet),":[40],"an":[41],"efficient":[42],"network":[43],"architecture.":[44],"First,":[45],"we":[46,82],"propose":[47],"Block":[51,57],"(KSB)":[52],"(VFB).":[58],"The":[59],"KSB":[60],"dynamically":[61],"adjusts":[62],"receptive":[64],"field":[65],"essential":[68],"information,":[70],"while":[71,95,141],"VFB":[73],"spatio-temporal":[75],"dependencies":[76],"through":[77],"video":[78],"focus":[79],"modulation.":[80],"Additionally,":[81],"present":[83],"Depthwise":[85],"Separable":[86],"Convolution":[87],"Gated":[88],"Unit":[89],"(DsCG),":[90],"which":[91,114],"reduces":[92],"load":[94],"enhancing":[96],"network\u2019s":[98],"robustness.":[99],"Finally,":[100],"these":[101],"three":[102],"blocks":[103],"are":[104],"combined":[105],"into":[106],"a":[107],"Module":[112],"(LkSFM),":[113],"is":[115],"stacked":[116],"form":[118],"LkSFocalNet.":[119],"Experimental":[120],"results":[121],"on":[122,136],"four":[123],"benchmark":[124],"datasets":[125],"demonstrate":[126],"that":[127],"LkSFocalNet":[128],"outperforms":[129],"baseline":[130],"achieves":[133],"state-of-the-art":[134],"performance":[135],"Diving-48":[138],"dataset,":[139],"all":[140],"maintaining":[142],"lower":[143]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}