{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:15:52Z","timestamp":1784229352013,"version":"3.55.0"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":"publisher","award":["62225604"],"award-info":[{"award-number":["62225604"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276145"],"award-info":[{"award-number":["62276145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Central Universities Nankai University","award":["070-63223049"],"award-info":[{"award-number":["070-63223049"]}]},{"name":"CAST"},{"name":"Young Elite Scientist Sponsorship","award":["YESS20210377"],"award-info":[{"award-number":["YESS20210377"]}]},{"DOI":"10.13039\/501100004945","name":"Nankai University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004945","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3401450","type":"journal-article","created":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T17:36:51Z","timestamp":1715794611000},"page":"8274-8283","source":"Crossref","is-referenced-by-count":148,"title":["Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8388-8708","authenticated-orcid":false,"given":"Qibin","family":"Hou","sequence":"first","affiliation":[{"name":"School of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8225-6311","authenticated-orcid":false,"given":"Cheng-Ze","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-8758","authenticated-orcid":false,"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6843-0064","authenticated-orcid":false,"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"ByteDance, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_40"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref13","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206108"},{"key":"ref17","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref18","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01166"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref23","first-page":"1140","article-title":"SegNeXt: Rethinking convolutional attention design for semantic segmentation","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Guo","year":"2022"},{"key":"ref24","article-title":"Hornet: Efficient high-order spatial interactions with recursive gated convolutions","author":"Rao","year":"2022"},{"key":"ref25","article-title":"More Convnets in the 2020 s: Scaling up kernels beyond 51x51 using sparsity","author":"Liu","year":"2022"},{"key":"ref26","article-title":"Mixconv: Mixed depthwise convolutional kernels","author":"Tan","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref31","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016"},{"key":"ref32","article-title":"On the connection between local attention and dynamic depth-wise convolution","author":"Han","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00090"},{"key":"ref35","article-title":"High-performance large-scale image recognition without normalization","author":"Brock","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref38","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"Yang","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref40","article-title":"Transformer in transformer","author":"Han","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref43","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref45","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2104.10858"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref50","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021"},{"key":"ref51","article-title":"EfficientViT: Enhanced linear attention for high-resolution low-computation visual recognition","author":"Cai","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_1"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"ref54","article-title":"Stand-alone self-attention in vision models","author":"Ramachandran","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3047209"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref58","article-title":"Gather-excite: Exploiting feature context in convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu","year":"2018"},{"key":"ref59","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tolstikhin","year":"2021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3206148"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3145427"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01388"},{"key":"ref63","article-title":"Demystify transformers & convolutions in modern image deep networks","author":"Hu","year":"2022"},{"key":"ref64","first-page":"14541","article-title":"Fast vision transformers with hilo attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref69","article-title":"Focal modulation networks","author":"Yang","year":"2022"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-41714-6_132447"},{"key":"ref71","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref73","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref74","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref75","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref76","article-title":"mixup: Beyond empirical risk minimization","author":"Zhang","year":"2017"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref85","article-title":"BEit: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref86","article-title":"Mmdetection: Open mmlab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10746266\/10531070.pdf?arnumber=10531070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:18:43Z","timestamp":1732666723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10531070\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":87,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3401450","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}