{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T17:02:26Z","timestamp":1784912546647,"version":"3.55.0"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100016370","name":"Federal Ministry of Labor and Social Affairs (BMAS) through the AccessibleMaps Project","doi-asserted-by":"publisher","award":["01KM151112"],"award-info":[{"award-number":["01KM151112"]}],"id":[{"id":"10.13039\/501100016370","id-type":"DOI","asserted-by":"publisher"}]},{"name":"\u201cKIT Future Fields\u201d Project"},{"DOI":"10.13039\/501100010570","name":"Ministry of Science, Research and the Arts of Baden-Wurttemberg (MWK) through the Cooperative Graduate School Accessibility through AIBased Assistive Technology","doi-asserted-by":"publisher","award":["BW6-03"],"award-info":[{"award-number":["BW6-03"]}],"id":[{"id":"10.13039\/501100010570","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Federal Ministry of Education and Research (BMBF) through the Fellowship within the IFI Program of the German Academic Exchange Service"},{"name":"HoreKA@KIT Supercomputer Partition"},{"name":"Hangzhou SurImage Technology Company Ltd"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tits.2023.3300537","type":"journal-article","created":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T17:30:04Z","timestamp":1692984604000},"page":"14679-14694","source":"Crossref","is-referenced-by-count":562,"title":["CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation With Transformers"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3471-328X","authenticated-orcid":false,"given":"Jiaming","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huayao","family":"Liu","sequence":"additional","affiliation":[{"name":"NIO, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1090-667X","authenticated-orcid":false,"given":"Kailun","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinxin","family":"Hu","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5245-2277","authenticated-orcid":false,"given":"Ruiping","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rainer","family":"Stiefelhagen","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2909066"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3023331"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3007457"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3161141"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00266"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1364\/OE.416130"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636109"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01597"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049332"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636084"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1117\/12.2535552"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","first-page":"1","article-title":"An image is worth 16\u271716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref22","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. ICML","author":"Touvron"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060707"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref33","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. NeurIPS","author":"Xie"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref35","first-page":"1","article-title":"HRFormer: High-resolution transformer for dense prediction","volume-title":"Proc. NeurIPS","author":"Yuan"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00132"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3252807"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3107672"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108468"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2904733"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2993143"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3109518"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00863"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3134828"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_33"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_24"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.05.012"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3234702"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00357"},{"key":"ref54","article-title":"ConvMLP: Hierarchical convolutional MLPs for vision","author":"Li","year":"2021","journal-title":"arXiv:2109.04454"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO54168.2021.9739390"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00205"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294306"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3066071"},{"key":"ref61","article-title":"Joint 2D\u20133D-semantic data for indoor scene understanding","author":"Armeni","year":"2017","journal-title":"arXiv:1702.01105"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1604.01685"},{"key":"ref64","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. CoRL","author":"Dosovitskiy"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_20"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref67","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.556"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00106"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.161"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.147"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.533"},{"key":"ref73","article-title":"Multi-modal attention-based fusion model for semantic segmentation of RGB-depth images","author":"Fooladgar","year":"2019","journal-title":"arXiv:1912.11691"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3084855"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01188-y"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_28"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2020.3009527"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3056726"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01289"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00533"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00690"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413621"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147664"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01414"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2750080"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.015"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-02773-6"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.353"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00199"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref97","first-page":"1","article-title":"Fast-SCNN: Fast semantic segmentation network","volume-title":"Proc. BMVC","author":"Poudel"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3042065"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00202"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref102","article-title":"HRFuser: A multi-resolution sensor fusion architecture for 2D object detection","author":"Broedermann","year":"2022","journal-title":"arXiv:2206.15157"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10339106\/10231003.pdf?arnumber=10231003","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T22:16:40Z","timestamp":1709331400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10231003\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":104,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tits.2023.3300537","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}