{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:20:37Z","timestamp":1777890037921,"version":"3.51.4"},"reference-count":73,"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\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62322113,62376156"],"award-info":[{"award-number":["62322113,62376156"]}],"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00952","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10218-10228","source":"Crossref","is-referenced-by-count":0,"title":["PVMamba: Parallelizing Vision Mamba via Dynamic State Aggregation"],"prefix":"10.1109","author":[{"given":"Fei","family":"Xie","sequence":"first","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongdao","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijia","family":"Zhang","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref2","article-title":"MMSegmentation Contributors","year":"2020","journal-title":"Mmsegmentation, an open source semantic segmentation toolbox"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref4","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024","journal-title":"ICML"},{"key":"ref5","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1703"},{"key":"ref7","article-title":"Dimba: Transformermamba diffusion models","author":"Fei","year":"2024","journal-title":"arXiv:2406.01159"},{"key":"ref8","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024","journal-title":"ICML"},{"key":"ref9","article-title":"Hippo: Recurrent memory with optimal polynomial projections","author":"Gu","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv:2111.00396"},{"key":"ref11","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","author":"Gu","year":"2021","journal-title":"NeurIPS"},{"key":"ref12","article-title":"On the parameterization and initialization of diagonal state space models","author":"Gu","year":"2022","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2022","journal-title":"ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"ref15","article-title":"Diagonal state spaces are as effective as structured state spaces","author":"Gupta","year":"2022","journal-title":"Neurips"},{"key":"ref16","article-title":"Demystify mamba in vision: A linear attention perspective","author":"Han","year":"2025","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Mambavision: A hybrid mamba-transformer vision backbone","author":"Hatamizadeh","year":"2024","journal-title":"arXiv:2407.08083"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref20","article-title":"Zigma: Zigzag mamba diffusion model","author":"Tao Hu","year":"2024","journal-title":"ECCV"},{"key":"ref21","article-title":"Lightvit: Towards light-weight convolutionfree vision transformers","author":"Huang","year":"2022","journal-title":"arXiv:2207.05557"},{"key":"ref22","article-title":"Localmamba: Visual state space model with windowed selective scan","author":"Huang","year":"2024","journal-title":"arXiv:2403.09338"},{"key":"ref23","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref26","article-title":"Mamband: Selective state space modeling for multi-dimensional data","author":"Li","year":"2024","journal-title":"ECCV"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","article-title":"Swin-umamba: Mamba-based unet with -based pretraining","author":"Liu","year":"2024","journal-title":"MICCAI"},{"key":"ref29","article-title":"Berg","author":"Liu","year":"2016","journal-title":"SSD: Single shot multibox detector. In ECCV"},{"key":"ref30","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2024","journal-title":"Neurips"},{"key":"ref31","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref36","article-title":"U-mamba: Enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024","journal-title":"arXiv:2401.04722"},{"key":"ref37","article-title":"Long range language modeling via gated state spaces","author":"Mehta","year":"2023","journal-title":"ICLR"},{"key":"ref38","article-title":"S4nd: Modeling images and videos as multidimensional signals using state spaces","author":"Nguyen","year":"2022","journal-title":"NeurIPS"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32690"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3767748"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref43","article-title":"Vssd: Vision mamba with non-casual state space duality","author":"Shi","year":"2024","journal-title":"arXiv:2407.18559"},{"key":"ref44","article-title":"Simplified state space layers for sequence modeling","author":"Smith","year":"2022","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref46","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019","journal-title":"ICML"},{"key":"ref47","article-title":"Dim: Diffusion mamba for efficient high-resolution image synthesis","author":"Teng","year":"2024","journal-title":"arXiv:2405.14224"},{"key":"ref48","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021","journal-title":"ICML"},{"key":"ref49","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref52","article-title":"Crossformer: A versatile vision transformer hinging on cross-scale attention","author":"Wang","year":"2022","journal-title":"ICLR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref54","article-title":"Linear statespace control systems","author":"Williams","year":"2007","journal-title":"John Wiley & Sons"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2020.2978386"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref59","article-title":"Early convolutions help transformers see better","author":"Xiao","year":"2021","journal-title":"NeurIPS"},{"key":"ref60","article-title":"Quadmambata: Learning quadtree-based selective scan for visual state space model","author":"Xie","year":"2024","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72111-3_54"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00540"},{"key":"ref64","article-title":"Plainmamba: Improving non-hierarchical mamba in visual recognition","author":"Yang","year":"2024","journal-title":"arXiv:2403.17695"},{"key":"ref65","article-title":"Focal selfattention for local-global interactions in vision transformers","author":"Yang","year":"2021","journal-title":"NeurIPS"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00044"},{"key":"ref68","article-title":"Graph transformer networks","author":"Yun","year":"2019","journal-title":"NeurIPS"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref71","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"ICML"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref73","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"ICLR"}],"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\/11443324.pdf?arnumber=11443324","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:24Z","timestamp":1777613304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443324\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00952","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}