{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T21:17:14Z","timestamp":1784063834359,"version":"3.55.0"},"reference-count":85,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01945","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20922-20933","source":"Crossref","is-referenced-by-count":2,"title":["UniConvNet: Expanding Effective Receptive Field While Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale"],"prefix":"10.1109","author":[{"given":"Yuhao","family":"Wang","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xi","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"20014","article-title":"Xcit: Cross-covariance image transformers","volume":"34","author":"Ali","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00531"},{"key":"ref6","article-title":"Mmdetection: Open mmlab detection toolbox and benchmark","author":"Chen","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00520"},{"key":"ref9","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"MMSegmentation Contributors","year":"2020","journal-title":"Mmsegmentation: Openmmlab semantic segmentation toolbox and benchmark"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref13","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01074"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00527"},{"key":"ref19","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Dosovitskiy","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_21"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref25","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref27","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3243616"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"ref32","article-title":"Moganet: Multi-order gated aggregation network","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0940"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"ref37","article-title":"More convnets in the 2020s: Scaling up kernels beyond 51 x 51 using sparsity","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref41","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Understanding the effective receptive field in deep convolutional neural networks","author":"Luo","year":"2016","journal-title":"Advances In neural information processing systems, 29"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_1"},{"key":"ref45","article-title":"Mobilevit: lightweight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Separable selfattention for mobile vision transformers","author":"Mehta","year":"2022","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0752"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65981-7_12"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref54","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref59","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan","year":"2019"},{"key":"ref60","article-title":"Mixconv: Mixed depthwise convolutional kernels","volume-title":"British Machine Vision Conference","author":"Tan","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref62","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref64","first-page":"5785","article-title":"Fastvit: A fast hybrid vision transformer using structural reparameterization","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Kumar","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01506"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00540"},{"key":"ref73","first-page":"28522","article-title":"Vitae: Vision transformer advanced by exploring intrinsic inductive bias","volume":"34","author":"Xu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref74","article-title":"Moat: Alternating mobile convolution and attention brings strong vision models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yang","year":"2023"},{"key":"ref75","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"Yang","year":"2021","journal-title":"Advances Inneural information processing systems"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444977.pdf?arnumber=11444977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:16:07Z","timestamp":1777612567000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01945","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}