{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:09:32Z","timestamp":1761894572421,"version":"build-2065373602"},"reference-count":44,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209345","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":["MMPX: Multi-modal Mamba Prompter to Large Vision Foundation Model for RGB-X Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Pengfei","family":"Wu","sequence":"first","affiliation":[{"name":"Nanjing University of Posts and Telecommunications,School of Automation and Artificial Intelligence,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications,School of Automation and Artificial Intelligence,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Gao","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications,School of Automation and Artificial Intelligence,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"Lancaster University,School of Computing and Communications,Lancaster,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3349072"},{"article-title":"Variational probabilistic fusion network for rgb-t semantic segmentation","year":"2023","author":"Lin","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10801872"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27981"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Mamba: Linear-time sequence modeling with selective state spaces","year":"2023","author":"Gu","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00176"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612288"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"article-title":"Dformer: Rethinking rgbd representation learning for semantic segmentation","year":"2023","author":"Yin","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00127"},{"article-title":"Geminifusion: Efficient pixel-wise multimodal fusion for vision transformer","year":"2024","author":"Jia","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00586"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3134828"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00205"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3437415"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"article-title":"Is attention better than matrix decomposition?","year":"2021","author":"Geng","key":"ref27"},{"key":"ref28","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196831"},{"article-title":"Ddd17: End-to-end davis driving dataset","year":"2017","author":"Binas","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/135"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3109518"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636084"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_31"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/487"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208833"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20269"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3086618"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229359"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281419"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272269"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"}],"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\/11209345.pdf?arnumber=11209345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:57Z","timestamp":1761888657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209345","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}