{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:02:00Z","timestamp":1783530120393,"version":"3.55.0"},"reference-count":57,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02183","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23519-23529","source":"Crossref","is-referenced-by-count":7,"title":["TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba"],"prefix":"10.1109","author":[{"given":"Xiaowen","family":"Ma","sequence":"first","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenliang","family":"Ni","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinghao","family":"Chen","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01166"},{"key":"ref3","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref4","article-title":"Hungry hungry hippos: Towards language modeling with state space models","author":"Daniel","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02094"},{"key":"ref6","author":"Geirhos","year":"2022","journal-title":"Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref8","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","first-page":"1474","article-title":"Hippo: Recurrent memory with optimal polynomial projections","volume":"33","author":"Gu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref11","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume":"34","author":"Gu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2607"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1670"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"ref16","author":"Han","year":"2016","journal-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding"},{"key":"ref17","article-title":"Liquid structural state-space models","author":"Hasani","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00424"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref22","author":"Howard","year":"2017","journal-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref25","author":"Li","year":"2024","journal-title":"Fouriermamba: Fourier learning integration with state space models for image deraining"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0940"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","author":"Liu","year":"2023","journal-title":"More convnets in the 2020s: Scaling up kernels beyond 51 \u00d7 51 using sparsity"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref31","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume-title":"Advances in Neural Information Processing Systems","author":"Luo","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref34","article-title":"Mega: moving average equipped gated attention","author":"Ma","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.01.025"},{"key":"ref36","article-title":"Timepro: Efficient multivariate long-term time series forecasting with variable- and time-aware hyper-state","volume-title":"Forty-second International Conference on Machine Learning","author":"Ma","year":"2025"},{"key":"ref37","article-title":"Long range language modeling via gated state spaces","author":"Mehta","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00941"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32690"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32690"},{"key":"ref41","author":"Qiao","year":"2024","journal-title":"Vl-mamba: Exploring state space models for multimodal learning"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"ref44","article-title":"Multi-scale vmamba: Hierarchy in hierarchy visual state space model","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1707"},{"key":"ref46","author":"Simonyan","year":"2015","journal-title":"Very deep convolutional networks for large-scale image recognition"},{"key":"ref47","article-title":"Simplified state space layers for sequence modeling","author":"Smith","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref48","first-page":"5785","article-title":"Fastvit: A fast hybrid vision transformer using structural reparameterization","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Kumar","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01506"},{"key":"ref51","author":"Xie","year":"2024","journal-title":"Quadmamba: Learning quadtree-based selective scan for visual state space model"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref56","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Forty-first International Conference on Machine Learning","author":"Zhu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e38495"}],"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\/11444801.pdf?arnumber=11444801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:14Z","timestamp":1777611254000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02183","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}