{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T09:23:59Z","timestamp":1771665839424,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,2]]},"DOI":"10.1109\/icar65334.2025.11338696","type":"proceedings-article","created":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:06:47Z","timestamp":1769029607000},"page":"404-411","source":"Crossref","is-referenced-by-count":1,"title":["Diffusion-based RGB-D Semantic Segmentation with Deformable Attention Transformer"],"prefix":"10.1109","author":[{"given":"Minh","family":"Bui","sequence":"first","affiliation":[{"name":"Norwegian University of Science and Technology (NTNU),Trondheim,Norway,7034"}]},{"given":"Kostas","family":"Alexis","sequence":"additional","affiliation":[{"name":"Norwegian University of Science and Technology (NTNU),Trondheim,Norway,7034"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Geminifusion: efficient pixel-wise multimodal fusion for vision transformer","volume-title":"Proceedings of the 41st International Conference on Machine Learning, ser. ICML\u201924","author":"Jia"},{"key":"ref2","article-title":"Rednet: Residual encoder-decoder network for indoor rgb-d semantic segmentation","author":"Jiang","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref5","article-title":"DFormer: Rethinking RGBD representation learning for semantic segmentation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yin"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049332"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3263111"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015780"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref13","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"International Conference on Learning Representations","author":"Baranchuk"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_39"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00861"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00026"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref24","article-title":"Dat++: Spatially dynamic vision transformer with deformable attention","author":"Xia","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref26","article-title":"Deepvit: Towards deeper vision transformer","author":"Zhou","year":"2021"},{"key":"ref27","article-title":"Denoising diffusion probabilistic models","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS \u201920","author":"Ho"},{"key":"ref28","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref30","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref31","article-title":"Analog bits: Generating discrete data using diffusion models with self-conditioning","author":"Chen","year":"2023"},{"key":"ref32","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Nichol"},{"key":"ref33","article-title":"Indoor semantic segmentation using depth information","volume-title":"1st International Conference on Learning Representations","author":"Couprie"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref36","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref38","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Neural Information Processing Systems (NeurIPS)","author":"Xie"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202315"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917728574"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196885"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989538"}],"event":{"name":"2025 IEEE International Conference on Advanced Robotics (ICAR)","location":"San Juan, Argentina","start":{"date-parts":[[2025,12,2]]},"end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 IEEE International Conference on Advanced Robotics (ICAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11338521\/11338600\/11338696.pdf?arnumber=11338696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T07:48:16Z","timestamp":1769068096000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11338696\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icar65334.2025.11338696","relation":{},"subject":[],"published":{"date-parts":[[2025,12,2]]}}}