{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:05:29Z","timestamp":1790269529655,"version":"4.1.0"},"reference-count":118,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Samsung Research Funding and Incubation Center of Samsung Electronics","award":["SRFC-IT2401-05"],"award-info":[{"award-number":["SRFC-IT2401-05"]}],"id":[{"id":"https:\/\/ror.org\/020m7t761","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3690455","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T20:02:34Z","timestamp":1778011354000},"page":"11511-11525","source":"Crossref","is-referenced-by-count":0,"title":["Spectral-Adaptive Modulation Networks for Visual Perception"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1581-4990","authenticated-orcid":false,"given":"Guhnoo","family":"Yun","sequence":"first","affiliation":[{"name":"Korea University (KU)","place":["Seoul, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2329-7375","authenticated-orcid":false,"given":"Juhan","family":"Yoo","sequence":"additional","affiliation":[{"name":"Dong-A University","place":["Busan, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kijung","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University (KU)","place":["Seoul, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1239-3365","authenticated-orcid":false,"given":"Jeongho","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University (KU)","place":["Seoul, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul Hongsuck","family":"Seo","sequence":"additional","affiliation":[{"name":"Korea University","place":["Seoul, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4345-8308","authenticated-orcid":false,"given":"Dong Hwan","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University (KU)","place":["Seoul, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref3","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref5","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref6","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref11","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5244\/c.35.204"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3552458.3556443"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00306"},{"key":"ref19","first-page":"23296","article-title":"Intriguing properties of vision transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Naseer"},{"key":"ref20","article-title":"Are convolutional neural networks or transformers more like human vision?","author":"Tuli","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.79"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"ref23","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chu","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref27","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tolstikhin"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3145427"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01066"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3303397"},{"key":"ref32","first-page":"4296","article-title":"FNet: Mixing tokens with fourier transforms","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Lee-Thorp","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263824"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29457"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0603"},{"key":"ref36","article-title":"Image as set of points","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Ma","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2797"},{"key":"ref38","article-title":"ResNet strikes back: An improved training procedure in timm","author":"Wightman","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01166"},{"key":"ref41","article-title":"More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401450"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0752"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3329173"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"ref47","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref48","article-title":"A battle of network structures: An empirical study of CNN, transformer, and MLP","author":"Zhao","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1057"},{"key":"ref51","article-title":"How do vision transformers work?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Park"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_1"},{"key":"ref53","article-title":"Anti-oversmoothing in deep vision transformers via the fourier domain analysis: From theory to practice","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1016"},{"key":"ref56","first-page":"7687","article-title":"Revealing the dark secrets of extremely large kernel convnets on robustness","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00562"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref63","first-page":"5416","article-title":"Blending anti-aliasing into vision transformer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Qian"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref66","article-title":"CycleMLP: A MLP-like architecture for dense prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2022"},{"key":"ref67","first-page":"20989","article-title":"Sparse and continuous attention mechanisms","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Martins"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.375"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20142"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00353"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TE.1969.4320436"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/NSSMIC.1993.373563"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00556"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2235192"},{"key":"ref77","article-title":"Analyzing the expressive power of graph neural networks in a spectral perspective","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Balcilar"},{"key":"ref78","volume-title":"Spectral Graph Theory","volume":"92","author":"Chung","year":"1997"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298681"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2197"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1057"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0181"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0304"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"ref85","article-title":"Graph-structured data viewed through a fourier lens","author":"Ekambaram","year":"2014"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738172"},{"key":"ref87","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref88","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref89","article-title":"Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Geirhos"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_23"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref92","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref98","article-title":"Multigrain: A unified image embedding for classes and instances","author":"Berman","year":"2019"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00815"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref101","article-title":"Normformer: Improved transformer pretraining with extra normalization","author":"Shleifer","year":"2021"},{"key":"ref102","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref103","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref104","article-title":"Large batch optimization for deep learning: Training bert in 76 minutes","author":"You","year":"2019"},{"key":"ref105","article-title":"PyTorch image models","author":"Wightman","year":"2019"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref108","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist. JMLR Workshop Conf. Proc.","author":"Glorot"},{"key":"ref109","article-title":"MMDetection: Open MMLab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref112","article-title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"issue":"140","key":"ref113","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"issue":"240","key":"ref114","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref115","article-title":"Toolbox of model-vs-human","year":"2021"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"ref117","first-page":"62429","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3273"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11506226.pdf?arnumber=11506226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:33:08Z","timestamp":1790267588000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11506226\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":118,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3690455","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":[[2026,10]]}}}