{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:22:53Z","timestamp":1786119773116,"version":"build-2736575974"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62273301"],"award-info":[{"award-number":["62273301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tcsvt.2026.3686189","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:51:13Z","timestamp":1776801073000},"page":"11363-11375","source":"Crossref","is-referenced-by-count":0,"title":["3 \u00d7 3 Kernel Is All You Need for Vision"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8673-2218","authenticated-orcid":false,"given":"Shenqi","family":"Lai","sequence":"first","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9698-8508","authenticated-orcid":false,"given":"Mengjian","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang Laboratory","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8142-0642","authenticated-orcid":false,"given":"Haifeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3173-6307","authenticated-orcid":false,"given":"Xueming","family":"Qian","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9817-4065","authenticated-orcid":false,"given":"Deng","family":"Cai","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6596-8117","authenticated-orcid":false,"given":"Yaxiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology","place":["Hefei, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_23"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00531"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00527"},{"key":"ref6","article-title":"On the connection between local attention and dynamic depth-wise convolution","volume-title":"Proc. ICLR","author":"Han"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3329173"},{"key":"ref9","first-page":"4203","article-title":"Focal modulation networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01166"},{"key":"ref11","article-title":"More Convnets in the 2020s: Scaling up kernels beyond 51$\\times$\n51 using sparsity","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00529"},{"key":"ref13","article-title":"MogaNet: Multi-order gated aggregation network","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"ref15","article-title":"Reversible column networks","volume-title":"Proc. ICLR","author":"Cai"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00597"},{"key":"ref17","article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref18","first-page":"24261","article-title":"MLP-Mixer: An all-MLP Architecture for Vision","volume-title":"Proc. NeurIPS","author":"Tolstikhin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3341806"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"ref21","article-title":"AS-MLP: An axial shifted MLP architecture for vision","volume-title":"Proc. ICLR","author":"Lian"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25376"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/111"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110698"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01506"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3377365"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3088639"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3246999"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3214993"},{"key":"ref36","article-title":"Efficient modulation for vision networks","volume-title":"Proc. CVPR","author":"Ma"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00423"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3526054"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01683"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3273"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.34030"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3342172"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00952"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref50","article-title":"mixup: Beyond Empirical Risk Minimization","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref53","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01844"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3199394"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3410684"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3207895"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01886"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3238642"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25421"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01906"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01014"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312311"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3061265"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3135013"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3352418"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3378453"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_53"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413896"},{"key":"ref78","article-title":"GLU variants improve transformer","author":"Shazeer","year":"2020","journal-title":"arXiv:2002.05202"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11643439\/11489018.pdf?arnumber=11489018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T19:03:52Z","timestamp":1786043032000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11489018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":79,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3686189","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}