{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:30:50Z","timestamp":1778761850463,"version":"3.51.4"},"reference-count":114,"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022YFC3300705"],"award-info":[{"award-number":["2022YFC3300705"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62331006,62171038,62088101"],"award-info":[{"award-number":["62331006,62171038,62088101"]}],"id":[{"id":"10.13039\/501100001809","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"}]},{"DOI":"10.13039\/501100020963","name":"JST Moonshot R&D","doi-asserted-by":"publisher","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}],"id":[{"id":"10.13039\/501100020963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02100","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22620-22632","source":"Crossref","is-referenced-by-count":2,"title":["Frequency-Dynamic Attention Modulation for Dense Prediction"],"prefix":"10.1109","author":[{"given":"Linwei","family":"Chen","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Gu","sequence":"additional","affiliation":[{"name":"RIKEN AIP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Fu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315561929"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02617"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00531"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3170591"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3449959"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3592621"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01808-8"},{"key":"ref11","first-page":"1","article-title":"When semantic segmentation meets frequency aliasing","volume-title":"Proceedings of International Conference on Learning Representations","author":"Chen","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02809"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00328"},{"key":"ref14","first-page":"1","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proceedings of International Conference on Learning Representations","author":"Chen","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref16","article-title":"Perpixel classification is not all you need for semantic segmentation","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Cheng"},{"key":"ref17","first-page":"4479","article-title":"Fast fourier convolution","volume-title":"Proceedings of Advances in Neural Information Processing Systems","volume":"33","author":"Chi","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222906"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00296"},{"key":"ref20","first-page":"2793","article-title":"Attention is not all you need: Pure attention loses rank doubly exponentially with depth","volume-title":"International conference on machine learning","author":"Dong","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3220423"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2024.9010115"},{"key":"ref25","volume-title":"Digital image processing","author":"Gonzalez","year":"2009"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_3"},{"key":"ref27","first-page":"1","article-title":"Adaptive fourier neural operators: Efficient token mixers for transformers","volume-title":"Proceedings of International Conference on Learning Representations","author":"Guibas","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3062048"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00281"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00599"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19975"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401450"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00556"},{"key":"ref37","first-page":"1","article-title":"The low-rank simplicity bias in deep networks","author":"Huh","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref38","first-page":"1","article-title":"Dilated convolution with learnable spacings","volume-title":"Proceedings of International Conference on Learning Representations","author":"Khalfaoui-Hassani","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.26599\/CVM.2025.9450330"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01983"},{"key":"ref44","first-page":"1","article-title":"Moganet: Multi-order gated aggregation network","author":"Li","year":"2024","journal-title":"ICLR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00187"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02247-9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00028"},{"key":"ref49","first-page":"1","article-title":"Fourier neural operator for parametric partial differential equations","volume-title":"Proceedings of International Conference on Learning Representations","author":"Li","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01135"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.09.007"},{"key":"ref54","volume-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","author":"Liu","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070368"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00021"},{"key":"ref60","article-title":"Oriented object detection with transformer","author":"Ma","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3516"},{"key":"ref62","first-page":"1","article-title":"How do vision transformers work?","volume-title":"Proceedings of International Conference on Learning Representations","author":"Park","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2357"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00924"},{"key":"ref65","volume-title":"Digital image processing algorithms and applications","author":"Pitas","year":"2000"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"ref67","first-page":"980","article-title":"Global filter networks for image classification","volume-title":"Proceedings of Advances in Neural Information Processing Systems","volume":"34","author":"Rao","year":"2021"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01683"},{"key":"ref71","first-page":"1","article-title":"How to train your vit? data, augmentation, and regularization in vision transformers","author":"Steiner","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1982.12308"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29457"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.284"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"issue":"1","key":"ref77","first-page":"1","article-title":"Trim-sod: A multi-modal, multi-task, and multi-scale spacecraft optical dataset","volume":"1","author":"Li","year":"2025","journal-title":"Space: Science & Technology"},{"key":"ref78","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proceedings of International Conference on Machine Learning","author":"Touvron","year":"2021"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_18"},{"key":"ref83","article-title":"Anti-oversmoothing in deep vision transformers via the fourier domain analysis: From theory to practice","volume-title":"International Conference on Learning Representations","author":"Wang"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-7506-7547-5.x5000-3"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00525"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref90","first-page":"1","article-title":"Spatial-mamba: Effective visual state space models via structure-aware state fusion","author":"Xiao","year":"2025","journal-title":"ICLR"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.15203"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-01989-w"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2974745"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0304"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16426"},{"key":"ref97","first-page":"11830","article-title":"Rethinking rotated object detection with gaussian wasserstein distance loss","volume-title":"Proceedings of International Conference on Machine Learning","author":"Yang","year":"2021"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00832"},{"key":"ref99","article-title":"Learning high-precision bounding box for rotated object detection via kullbackleibler divergence","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Yang"},{"key":"ref100","article-title":"A fourier perspective on model robustness in computer vision","volume-title":"Proceedings of Advances in Neural Information Processing Systems","volume":"32","author":"Yin","year":"2019"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3329173"},{"key":"ref102","first-page":"1","article-title":"Mambaout: Do we really need mamba for vision?","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00562"},{"key":"ref105","article-title":"Ars-detr: Aspect ratio sensitive oriented object detection with transformer","author":"Zeng","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0359"},{"key":"ref107","first-page":"1","article-title":"Memory efficient transformer adapter for dense predictions","volume-title":"Proceedings of International Conference on Learning Representations","author":"Zhang","year":"2025"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00708"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.414"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02466-8"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref112","volume-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"ref113","first-page":"1","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"Proceedings of International Conference on Learning Representations","author":"Zhu","year":"2021"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4204"}],"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\/11444658.pdf?arnumber=11444658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:59Z","timestamp":1777611239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444658\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":114,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02100","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}