{"id":"https://openalex.org/W7119016786","doi":"https://doi.org/10.1109/tmm.2026.3651108","title":"Mask-Aware Kernel Learning for Action Recognition","display_name":"Mask-Aware Kernel Learning for Action Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7119016786","doi":"https://doi.org/10.1109/tmm.2026.3651108"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651108","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/A5122023922","display_name":"Kewei Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kewei Wu","raw_affiliation_strings":["School of Computer and Information, the Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7332-5653","affiliations":[{"raw_affiliation_string":"School of Computer and Information, the Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I39774598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057642740","display_name":"Chongjia Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongjia Zhu","raw_affiliation_strings":["School of Computer and Information, the Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0009-6540-1159","affiliations":[{"raw_affiliation_string":"School of Computer and Information, the Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I39774598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122182817","display_name":"Zhao Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Xie","raw_affiliation_strings":["School of Computer and Information, the Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9834-4730","affiliations":[{"raw_affiliation_string":"School of Computer and Information, the Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I39774598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122107418","display_name":"Kun Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Shao","raw_affiliation_strings":["School of Computer and Information, the Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4116-4477","affiliations":[{"raw_affiliation_string":"School of Computer and Information, the Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I39774598"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122154027","display_name":"Dan Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["School of Computer and Information, the Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2594-254X","affiliations":[{"raw_affiliation_string":"School of Computer and Information, the Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I39774598"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0291086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"3121","last_page":"3134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9865999817848206,"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":0.9865999817848206,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.001500000013038516,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0010000000474974513,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/tree-kernel","display_name":"Tree kernel","score":0.8133000135421753},{"id":"https://openalex.org/keywords/multiple-kernel-learning","display_name":"Multiple kernel learning","score":0.7369999885559082},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6402000188827515},{"id":"https://openalex.org/keywords/radial-basis-function-kernel","display_name":"Radial basis function kernel","score":0.5982999801635742},{"id":"https://openalex.org/keywords/string-kernel","display_name":"String kernel","score":0.531499981880188},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.4984999895095825},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4871000051498413},{"id":"https://openalex.org/keywords/graph-kernel","display_name":"Graph kernel","score":0.47279998660087585}],"concepts":[{"id":"https://openalex.org/C140417398","wikidata":"https://www.wikidata.org/wiki/Q16933942","display_name":"Tree kernel","level":5,"score":0.8133000135421753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436000108718872},{"id":"https://openalex.org/C2776879701","wikidata":"https://www.wikidata.org/wiki/Q25048660","display_name":"Multiple kernel learning","level":4,"score":0.7369999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6884999871253967},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.5982999801635742},{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.531499981880188},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.4984999895095825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C100595998","wikidata":"https://www.wikidata.org/wiki/Q11731931","display_name":"Graph kernel","level":5,"score":0.47279998660087585},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C160446489","wikidata":"https://www.wikidata.org/wiki/Q7226642","display_name":"Polynomial kernel","level":4,"score":0.43970000743865967},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4390999972820282},{"id":"https://openalex.org/C134517425","wikidata":"https://www.wikidata.org/wiki/Q16000131","display_name":"Kernel embedding of distributions","level":4,"score":0.4043000042438507},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C182335926","wikidata":"https://www.wikidata.org/wiki/Q17093020","display_name":"Kernel principal component analysis","level":4,"score":0.2533000111579895},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651108","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":[],"awards":[{"id":"https://openalex.org/G4862433228","display_name":null,"funder_award_id":"62272144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5858203771","display_name":null,"funder_award_id":"62576131","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Action":[0],"recognition":[1],"aims":[2],"to":[3,64,98,109,120,144,171],"identify":[4],"an":[5],"action":[6,32,47,67,112,123,148,174,255],"from":[7],"video":[8,25],"frames.":[9],"The":[10,18,58,72,151,200],"actions":[11],"are":[12,154],"usually":[13],"surrounded":[14],"by":[15,50,192,218,235],"irrelevant":[16],"backgrounds.":[17],"action/background":[19],"information":[20],"is":[21,74],"diverse":[22],"in":[23,156],"different":[24],"frames,":[26],"which":[27,44,159,244],"hinders":[28],"learning":[29,49,53,163,206,214,236,248],"the":[30,66,102,111,122,146,173,194,204,246],"implicit":[31,46],"patterns.":[33],"In":[34],"this":[35],"work,":[36],"we":[37,128,179,223],"propose":[38],"a":[39,77,83,91,130,181,189,225],"Mask-aware":[40],"Kernel":[41],"Model":[42],"(MKM),":[43],"ensures":[45,160,203,245],"pattern":[48],"integrating":[51],"kernel":[52,84,87,92,115,131,162,182,205,226,247],"with":[54,140,164,176,197,207,220,240,249],"proper":[55],"cluster":[56,138,152],"relations.":[57],"MKM":[59,73],"provides":[60],"novel":[61],"cluster-aware":[62,161],"kernels":[63,124,175],"enhance":[65],"representation":[68],"for":[69,114,125,253],"frame":[70,126,166],"patches.":[71,150],"deployed":[75],"on":[76,266],"temporal":[78,100,103,107],"Vision":[79,104],"Transformer,":[80],"and":[81,90,273],"introduces":[82,188],"clustering":[85,132],"learner,":[86],"masking":[88,183],"filter,":[89],"attention":[93,227,239],"selector.":[94],"<italic":[95,117,168,210],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[96,118,169,211],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">First</i>,":[97],"learn":[99],"features,":[101],"Transformer":[105],"uses":[106],"correlation":[108],"ensure":[110],"features":[113,217,234],"learning.":[116],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Second</i>,":[119],"analyze":[121,172],"patches,":[127],"design":[129,180,224],"learner":[133],"module.":[134,185,229],"This":[135,186,230],"module":[136,187,231],"learns":[137],"relations":[139,153],"patch-":[141],"wise":[142,238,242,251],"convolutions":[143],"describe":[145],"common":[147],"among":[149],"learned":[155],"each":[157],"frame,":[158],"input":[165],"adaptivity.":[167],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Third</i>,":[170],"spatial":[177,198],"adaptivity,":[178],"filter":[184],"location":[190],"mask":[191,202],"analyzing":[193],"region":[195],"patterns":[196],"convolution.":[199],"patch-level":[201],"region-aware":[208],"selection.":[209],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Fourth</i>,":[212],"after":[213],"multiple":[215,221],"channel":[216],"convolution":[219],"kernels,":[222],"selector":[228],"excites":[232],"kernel-aware":[233],"channel-":[237,241,250],"convolutions,":[243],"selection":[252],"effective":[254],"representation.":[256],"Extensive":[257],"experiments":[258],"demonstrate":[259],"that":[260],"our":[261],"method":[262],"achieves":[263],"state-of-the-art":[264],"performance":[265],"Something-Something":[267],"V1":[268],"&":[269],"V2,":[270],"Kinetics-400,":[271],"UAV-human,":[272],"Diving":[274],"48":[275],"datasets.":[276]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-08T00:00:00"}