{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:29:22Z","timestamp":1761895762564,"version":"build-2065373602"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11208926","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking Cross-Modality Fusion Mamba from a Frequency Domain Perspective"],"prefix":"10.1109","author":[{"given":"Zeyu","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang Normal University,Computer Science and Technology,JinHua,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiying","family":"Xu","sequence":"additional","affiliation":[{"name":"Zhejiang Normal University,Computer Science and Technology,JinHua,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Liu","sequence":"additional","affiliation":[{"name":"Nankai University,College of Computer Science,TianJin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang Normal University,Computer Science and Technology,JinHua,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinzhong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang Normal University,Computer Science and Technology,JinHua,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang Normal University,JinHua,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbo","family":"Li","sequence":"additional","affiliation":[{"name":"Geekplus Technology,BeiJing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref2"},{"article-title":"Multispectral pedestrian detection via simultaneous detection and segmentation","year":"2018","author":"Li","key":"ref3"},{"article-title":"Gfd-ssd: Gated fusion double ssd for multispectral pedestrian detection","year":"2019","author":"Zheng","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108786"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109913"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"article-title":"Mamba: Linear-time sequence modeling with selective state spaces","year":"2024","author":"Gu","key":"ref8"},{"article-title":"Efficiently modeling long sequences with structured state spaces","year":"2021","author":"Gu","key":"ref9"},{"article-title":"Vmamba: Visual state space model","year":"2024","author":"Liu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91979-4_2"},{"article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","year":"2024","author":"Zhu","key":"ref12"},{"key":"ref13","article-title":"Fast fourier convolution","author":"Chi","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 (NeurIPS)"},{"article-title":"Deep residual fourier transformation for single image deblurring","year":"2021","author":"Mao","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_19"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_21"},{"key":"ref17","first-page":"8.0.0","article-title":"Ultralytics YOLO","author":"Jocher","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.73"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00046"},{"article-title":"Removal and selection: Improving rgb-infrared object detection via coarse-to-fine fusion","year":"2024","author":"Zhao","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.034"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3418213"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.02.012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_1"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11208926.pdf?arnumber=11208926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:58:34Z","timestamp":1761890314000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11208926","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}