{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:05:37Z","timestamp":1783530337973,"version":"3.55.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project of China","award":["2024YFE0100700"],"award-info":[{"award-number":["2024YFE0100700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62495061"],"award-info":[{"award-number":["62495061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62522607"],"award-info":[{"award-number":["62522607"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276145"],"award-info":[{"award-number":["62276145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Support Program of Tianjin, China","award":["23JCZDJC01050"],"award-info":[{"award-number":["23JCZDJC01050"]}]},{"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"}]},{"DOI":"10.13039\/501100004945","name":"Nankai University","doi-asserted-by":"publisher","award":["070-63253220"],"award-info":[{"award-number":["070-63253220"]}],"id":[{"id":"10.13039\/501100004945","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3658114","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T20:29:16Z","timestamp":1769545756000},"page":"7195-7208","source":"Crossref","is-referenced-by-count":5,"title":["DFormer++: Improving RGBD Representation Learning for Semantic Segmentation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9988-3509","authenticated-orcid":false,"given":"Bo-Wen","family":"Yin","sequence":"first","affiliation":[{"name":"VCIP, School of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiao-Long","family":"Cao","sequence":"additional","affiliation":[{"name":"VCIP, School of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0136-9603","authenticated-orcid":false,"given":"Dan","family":"Xu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (HKUST), Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-8758","authenticated-orcid":false,"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"VCIP, School of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8388-8708","authenticated-orcid":false,"given":"Qibin","family":"Hou","sequence":"additional","affiliation":[{"name":"VCIP, School of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"24206","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Akbari"},{"key":"ref2","article-title":"Joint 2D-3D-semantic data for indoor scene understanding","author":"Armeni","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref4","first-page":"4009","article-title":"Adabins: Depth estimation using adaptive bins","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Shariq"},{"key":"ref5","first-page":"1","article-title":"Depth pro: Sharp monocular metric depth in less than a second","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bochkovskii"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.321"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049332"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref10","first-page":"6894","article-title":"An empirical study of adder neural networks for object detection","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Chen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3538473"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref13","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Cheng"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00756"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191977"},{"key":"ref19","article-title":"Multi-modal attention-based fusion model for semantic segmentation of RGB-depth images","author":"Fooladgar","year":"2019"},{"key":"ref20","first-page":"1","article-title":"IS attention better than matrix decomposition?","volume-title":"Proc. Int. Conf. Learn. Represention","author":"Geng"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0084"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487797"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401450"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref30","article-title":"Multi-modal sensor fusion for auto driving perception: A survey","author":"Huang","year":"2022"},{"key":"ref31","first-page":"21753","article-title":"Geminifusion: Efficient pixel-wise multimodal fusion for vision transformer","volume-title":"Proc. Inter. Conf. Mach. Learn.","author":"Jia"},{"key":"ref32","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represention","author":"Diederik Kingma"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3309979"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3558989"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref38","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represention","author":"Loshchilov"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967313"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Inter. Conf. Mach. Learn.","author":"Radford"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892852"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01683"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414008"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00176"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01277"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_9"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref54","first-page":"4835","article-title":"Deep multimodal fusion by channel exchanging","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01749"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_24"},{"key":"ref57","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3438565"},{"key":"ref60","first-page":"1","article-title":"Dformer: Rethinking RGBD representation learning for semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represention","author":"Yin"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3532440"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01847"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.544"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3161852"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3174338"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11365989.pdf?arnumber=11365989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:52:32Z","timestamp":1780948352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11365989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":68,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3658114","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}