{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T03:50:04Z","timestamp":1782186604100,"version":"3.54.5"},"reference-count":132,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["62331006"],"award-info":[{"award-number":["62331006"]}],"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":["62171038"],"award-info":[{"award-number":["62171038"]}],"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":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L253009"],"award-info":[{"award-number":["L253009"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JST Moonshot R&D, Japan","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tpami.2025.3592621","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T17:55:21Z","timestamp":1753379721000},"page":"9767-9784","source":"Crossref","is-referenced-by-count":25,"title":["Spatial Frequency Modulation for Semantic Segmentation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9639-3237","authenticated-orcid":false,"given":"Linwei","family":"Chen","sequence":"first","affiliation":[{"name":"MIIT Key Laboratory of Complex-field Intelligent Sensing, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6677-694X","authenticated-orcid":false,"given":"Ying","family":"Fu","sequence":"additional","affiliation":[{"name":"MIIT Key Laboratory of Complex-field Intelligent Sensing, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7419-6240","authenticated-orcid":false,"given":"Lin","family":"Gu","sequence":"additional","affiliation":[{"name":"RIKEN AIP, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3998-5989","authenticated-orcid":false,"given":"Dezhi","family":"Zheng","sequence":"additional","affiliation":[{"name":"MIIT Key Laboratory of Complex-field Intelligent Sensing, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6785-0785","authenticated-orcid":false,"given":"Jifeng","family":"Dai","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793510"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2019.111322"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref6","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533846"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01235"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00692"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref15","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1949.232969"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/T-AIEE.1928.5055024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.134"},{"key":"ref21","article-title":"Adversarial machine learning at scale","author":"Kurakin","year":"2016"},{"key":"ref22","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Croce"},{"key":"ref23","first-page":"5301","article-title":"On the spectral bias of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rahaman"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17261"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1049\/ep.1987.0120"},{"key":"ref26","first-page":"7324","article-title":"Making convolutional networks shift-invariant again","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.03.023"},{"key":"ref28","first-page":"1","article-title":"Learning to downsample for segmentation of ultra-high resolution images","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jin"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00492"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01633"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3026069"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2893630"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339628"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.414"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.284"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439270"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3103114"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059911"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01660-2"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.108010"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3220423"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3170591"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.09.007"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3384406"},{"key":"ref49","first-page":"1","article-title":"When semantic segmentation meets frequency aliasing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.05.026"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/rs13020252"},{"key":"ref52","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref54","first-page":"1","article-title":"HRFormer: High-resolution transformer for dense prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref56","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007032"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0261-2"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3062772"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3101395"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00791"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16267"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_31"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00239"},{"key":"ref77","first-page":"1","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jaderberg"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_4"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00222"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01525"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_14"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01748"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3449959"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02809"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00328"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00181"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00556"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511619700"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"issue":"793-800","key":"ref95","first-page":"1","article-title":"Sur la sphere vide","volume":"7","author":"Delaunay","year":"1934","journal-title":"Izv. Akad. Nauk SSSR, Otdelenie Matematicheskii i Estestvennyka Nauk"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1201\/9781439865521"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/235815.235821"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01243"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref104","first-page":"1","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_28"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00531"},{"key":"ref109","first-page":"1","article-title":"MogaNet: Multi-order gated aggregation network","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3329173"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00021"},{"key":"ref112","first-page":"1","article-title":"Spatial-mamba: Effective visual state space models via structure-aware state fusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiao"},{"key":"ref113","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref114","article-title":"A downsampled variant of ImageNet as an alternative to the CIFAR datasets","author":"Chrabaszcz","year":"2017"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00533"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01508"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref123","first-page":"4971","article-title":"SegViT: Semantic segmentation with plain vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref124","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref125","first-page":"1307","article-title":"CondConv: Conditionally parameterized convolutions for efficient inference","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00554"},{"key":"ref127","first-page":"1","article-title":"Efficient inference in fully connected CRFs with Gaussian edge potentials","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kr\u00e4henb\u00fchl"},{"key":"ref128","first-page":"1","article-title":"Guided upsampling network for real-time semantic segmentation","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Mazzini"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00324"},{"key":"ref130","article-title":"Instance segmentation with point supervision","author":"Laradji","year":"2019"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_29"},{"key":"ref132","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11192800\/11095993.pdf?arnumber=11095993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:36:29Z","timestamp":1759772189000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11095993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":132,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3592621","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":[[2025,11]]}}}