{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:24:47Z","timestamp":1778171087748,"version":"3.51.4"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Basic Research Project Basic Research Key Project","award":["JCYJ20241202124430041"],"award-info":[{"award-number":["JCYJ20241202124430041"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3526054","type":"journal-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T20:20:59Z","timestamp":1736886059000},"page":"455-467","source":"Crossref","is-referenced-by-count":7,"title":["A Pyramid Fusion MLP for Dense Prediction"],"prefix":"10.1109","volume":"34","author":[{"given":"Qiuyu","family":"Huang","sequence":"first","affiliation":[{"name":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3038-5891","authenticated-orcid":false,"given":"Zequn","family":"Jie","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7331-6132","authenticated-orcid":false,"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8673-2218","authenticated-orcid":false,"given":"Shenqi","family":"Lai","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00527"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00090"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01066"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/111"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00144"},{"key":"ref7","first-page":"1","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref8","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref13","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tolstikhin"},{"key":"ref14","first-page":"1","article-title":"AS-MLP: An axial shifted MLP architecture for vision","volume-title":"Proc. ICLR","author":"Lian"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_14"},{"key":"ref16","first-page":"3172","article-title":"Raftmlp: How much can be done without attention and with less spatial locality?","volume-title":"Proc. ACCV","author":"Tatsunami"},{"key":"ref17","first-page":"297","article-title":"S2-mlp: Spatial-shift MLP architecture for vision","volume-title":"Proc. WACV","author":"Yu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20133"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25376"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3303397"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3211006"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3145427"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3341700"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00066"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20142"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref36","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3088639"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3246999"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref41","first-page":"1","article-title":"On the connection between local attention and dynamic depth-wise convolution","volume-title":"Proc. ICLR","author":"Han"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"ref44","first-page":"4203","article-title":"Focal modulation networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref45","first-page":"1","article-title":"More ConvNets in the 2020s: Scaling up kernels beyond 51\u00d751 using sparsity","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref47","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. ICML","author":"Touvron"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref50","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3318967"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293763"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00532"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00550"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref60","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref61","first-page":"1","article-title":"Hivit: A simpler and more efficient design of hierarchical vision transformer","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref62","first-page":"1","article-title":"Reversible column networks","volume-title":"Proc. ICLR","author":"Cai"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00531"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"ref67","first-page":"1","article-title":"Efficient modulation for vision networks","volume-title":"Proc. ICLR","author":"Ma"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"ref70","first-page":"15909","article-title":"Repvit: Revisiting mobile CNN from vit perspective","volume-title":"Proc. CVPR","author":"Wang"},{"key":"ref71","first-page":"1","article-title":"Moganet: Multi-order gated aggregation network","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref72","first-page":"15234","article-title":"Lightweight vision transformer with bidirectional interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"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","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_23"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref83","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. AISTATS","author":"Glorot"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10841959.pdf?arnumber=10841959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T06:30:59Z","timestamp":1737441059000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10841959\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3526054","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}