{"id":"https://openalex.org/W7155059723","doi":"https://doi.org/10.1109/tcsvt.2026.3686189","title":"3 \u00d7 3 Kernel Is All You Need for Vision","display_name":"3 \u00d7 3 Kernel Is All You Need for Vision","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155059723","doi":"https://doi.org/10.1109/tcsvt.2026.3686189"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3686189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3686189","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5101685414","display_name":"Shenqi Lai","orcid":"https://orcid.org/0000-0001-8673-2218"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenqi Lai","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0001-8673-2218","affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072299293","display_name":"Mengjian Li","orcid":"https://orcid.org/0009-0000-9698-8508"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengjian Li","raw_affiliation_strings":["Zhejiang Laboratory"],"raw_orcid":"https://orcid.org/0009-0000-9698-8508","affiliations":[{"raw_affiliation_string":"Zhejiang Laboratory","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050770348","display_name":"H F Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Liu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-8142-0642","affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014825654","display_name":"Xueming Qian","orcid":"https://orcid.org/0000-0002-3173-6307"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueming Qian","raw_affiliation_strings":["Xi\u2019an Jiaotong University"],"raw_orcid":"https://orcid.org/0000-0002-3173-6307","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037942269","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0001-9817-4065"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0001-9817-4065","affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101651167","display_name":"Yaxiong Wang","orcid":"https://orcid.org/0000-0001-6596-8117"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxiong Wang","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":"https://orcid.org/0000-0001-6596-8117","affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38594658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"8","first_page":"11363","last_page":"11375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13126","display_name":"Scientific Research and Discoveries","score":0.025499999523162842,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13126","display_name":"Scientific Research and Discoveries","score":0.025499999523162842,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12917","display_name":"Astronomy and Astrophysical Research","score":0.020600000396370888,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.016599999740719795,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7067999839782715},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6915000081062317},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6880000233650208},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6478999853134155},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.629800021648407},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6044999957084656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5206000208854675},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.41620001196861267},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.41260001063346863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638000249862671},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7067999839782715},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6915000081062317},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6880000233650208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6481000185012817},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6478999853134155},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.629800021648407},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6044999957084656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3959999978542328},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3544999957084656},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.3165999948978424},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.2718999981880188},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3686189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3686189","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3045806358","display_name":null,"funder_award_id":"62273301","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":67,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2162915993","https://openalex.org/W2179352600","https://openalex.org/W2183341477","https://openalex.org/W2331143823","https://openalex.org/W2519904008","https://openalex.org/W2560023338","https://openalex.org/W2737258237","https://openalex.org/W2806070179","https://openalex.org/W2883780447","https://openalex.org/W2884561390","https://openalex.org/W2884822772","https://openalex.org/W2963026686","https://openalex.org/W2963047834","https://openalex.org/W2963163009","https://openalex.org/W2986661129","https://openalex.org/W2992308087","https://openalex.org/W3035682985","https://openalex.org/W3081227581","https://openalex.org/W3092933908","https://openalex.org/W3138516171","https://openalex.org/W3167976421","https://openalex.org/W3169865585","https://openalex.org/W3170226651","https://openalex.org/W4206760693","https://openalex.org/W4214736485","https://openalex.org/W4226334005","https://openalex.org/W4292258663","https://openalex.org/W4297032809","https://openalex.org/W4308057280","https://openalex.org/W4312443924","https://openalex.org/W4318149008","https://openalex.org/W4321482189","https://openalex.org/W4382240228","https://openalex.org/W4382465803","https://openalex.org/W4385346076","https://openalex.org/W4385764523","https://openalex.org/W4386065422","https://openalex.org/W4386066416","https://openalex.org/W4386075553","https://openalex.org/W4386076083","https://openalex.org/W4386076191","https://openalex.org/W4386076417","https://openalex.org/W4386453438","https://openalex.org/W4388145401","https://openalex.org/W4389977645","https://openalex.org/W4390357613","https://openalex.org/W4390691253","https://openalex.org/W4390871719","https://openalex.org/W4390872564","https://openalex.org/W4390872693","https://openalex.org/W4392901965","https://openalex.org/W4392940314","https://openalex.org/W4399568596","https://openalex.org/W4399884539","https://openalex.org/W4402703046","https://openalex.org/W4402716415","https://openalex.org/W4402727337","https://openalex.org/W4402754177","https://openalex.org/W4402775306","https://openalex.org/W4403844121","https://openalex.org/W4406367270","https://openalex.org/W4409364581","https://openalex.org/W4413147024","https://openalex.org/W4415796023","https://openalex.org/W7160200734"],"related_works":[],"abstract_inverted_index":{"Most":[0],"modern":[1],"Convolutional":[2],"Neural":[3],"Networks":[4],"(CNNs)":[5],"employ":[6],"a":[7,67,143],"multi-branch":[8],"structure":[9],"with":[10,168,187],"various-sized":[11],"convolutions":[12,25,57],"to":[13,123,175],"capture":[14],"long-":[15],"and":[16,30,35,42,62,80,104,128,150,197],"short-range":[17],"dependencies.":[18],"However,":[19],"these":[20],"CNNs":[21],"use":[22],"large":[23,101],"kernel":[24],"(e.g.,":[26,33],"astonishingly":[27],"101":[28,176,178],"kernels)":[29],"specialized":[31],"techniques":[32],"reparameterization":[34],"sparsity),":[36],"increasing":[37],"complexity":[38],"in":[39,180,190],"both":[40],"training":[41],"inference":[43],"stages.":[44],"This":[45],"paper":[46],"focuses":[47],"on":[48,54,132],"designing":[49],"an":[50],"efficient":[51],"CNN":[52,141,163],"based":[53],"pure":[55],"3\u00d73":[56,121,151],"without":[58],"introducing":[59],"complex":[60],"operations":[61],"techniques.":[63],"Specifically,":[64],"we":[65,136],"propose":[66],"Spatial":[68,139],"Pyramid":[69,140],"(SP)":[70],"block,":[71,135],"which":[72],"consists":[73],"of":[74,147,202],"the":[75,81,92,117,133,138,161,209],"Multi-branch":[76],"Residual":[77,83],"(MbR)":[78],"module":[79],"Gated-branch":[82],"(GbR)":[84],"module.":[85],"The":[86],"MbR":[87],"introduces":[88],"multiscale":[89],"pooling":[90],"as":[91],"key":[93],"component,":[94],"thus":[95],"capturing":[96],"long-range":[97],"visual":[98],"cues":[99],"through":[100,107],"down-sampling":[102,109],"rates":[103,110],"shorter-range":[105],"dependencies":[106,125],"low":[108,113],"while":[111],"maintaining":[112],"computational":[114,156],"complexity.":[115],"Besides,":[116,182],"GbR":[118],"uses":[119],"one":[120],"convolution":[122],"refine":[124],"along":[126],"spatial":[127],"channel":[129],"dimensions.":[130],"Based":[131],"SP":[134],"construct":[137],"(SPCNN),":[142],"model":[144],"composed":[145],"exclusively":[146],"Point-Wise":[148],"Convolution":[149],"Depth-Wise":[152],"Convolution.":[153],"Under":[154],"comparable":[155],"complexity,":[157],"SPCNN":[158,184],"significantly":[159],"outperforms":[160],"state-of-the-art":[162,188],"PeLK":[164],"(83.6%":[165],"vs":[166],"82.6%)":[167],"only":[169],"3":[170,172],"\u00d7":[171,177],"kernels":[173,179],"(compared":[174],"PeLK).":[181],"our":[183],"demonstrates":[185],"comparability":[186],"backbones":[189],"lightweight":[191],"models,":[192],"object":[193],"detection,":[194],"instance":[195],"segmentation,":[196],"semantic":[198],"segmentation.":[199],"Moreover,":[200],"evaluations":[201],"four":[203],"image":[204],"retrieval":[205],"benchmarks":[206],"also":[207],"demonstrate":[208],"effectiveness.":[210],"All":[211],"codes":[212],"are":[213],"released":[214],"at":[215],"https://github.com/xiaolai-sqlai/SPCNN.":[216]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-04-22T00:00:00"}