{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:39:56Z","timestamp":1766061596405,"version":"3.48.0"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007569","name":"Carl-Zeiss-Stiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007569","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11245809","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"2400-2407","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers"],"prefix":"10.1109","author":[{"given":"S\u00f6hnke Benedikt","family":"Fischedick","sequence":"first","affiliation":[{"name":"Technische Universität Ilmenau,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98693"}]},{"given":"Daniel","family":"Seichter","sequence":"additional","affiliation":[{"name":"Technische Universität Ilmenau,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98693"}]},{"given":"Benedict","family":"Stephan","sequence":"additional","affiliation":[{"name":"Technische Universität Ilmenau,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98693"}]},{"given":"Robin","family":"Schmidt","sequence":"additional","affiliation":[{"name":"Technische Universität Ilmenau,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98693"}]},{"given":"Horst-Michael","family":"Gross","sequence":"additional","affiliation":[{"name":"Technische Universität Ilmenau,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98693"}]}],"member":"263","reference":[{"article-title":"Bridging Distance with a Collaborative Telepresence Robot for Older Adults \u2013 Report on Progress in the CO-HUMANICS Project","volume-title":"Proc. of ISR","author":"Fischedick","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN60168.2024.10731330"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-024-01143-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342137"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892852"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191977"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"article-title":"DFormer: Rethinking RGBD representation learning for semantic segmentation","volume-title":"Proc. of ICLR","author":"Yin","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812205"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967890"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811877"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965390"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01979"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00135"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref28","article-title":"Zero-shot semantic segmentation","volume-title":"Proc. of NeurIPS","volume":"32","author":"Bucher"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00111"},{"key":"ref31","first-page":"35631","article-title":"Learning mask-aware clip representations for zero-shot segmentation","volume-title":"Proc. of NeurIPS","volume":"36","author":"Jiao"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00335"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8555-5_13"},{"article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. of NeurIPS (Workshop)","author":"Hinton","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","first-page":"13019","article-title":"Alpha-clixp: A clip model focusing on wherever you want","volume-title":"Proc. of CVPR","author":"Sun"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"article-title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","volume-title":"Proc. of NeurIPS","author":"Xie","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2013.6698849"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. of NeurIPS","author":"Cheng","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"article-title":"RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation","year":"2018","author":"Jiang","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01188-y"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_9"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_33"},{"article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","volume-title":"Proc. of ICLR","author":"Dosovitskiy","key":"ref51"},{"key":"ref52","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. of ICML","author":"Radford"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02252"},{"article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","volume-title":"Proc. of NeurIPS (Workshop)","author":"Sanh","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"issue":"86","key":"ref57","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der Maaten","year":"2008","journal-title":"JMLR"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref60","first-page":"21875","article-title":"Depth anything v2","volume-title":"Proc. of NeurIPS","volume":"37","author":"Yang"},{"article-title":"Decoupled weight decay regularization","volume-title":"Proc. of ICLR","author":"Loshchilov","key":"ref61"},{"article-title":"Kosmos-2: Grounding multimodal large language models to the world","year":"2023","author":"Peng","key":"ref62"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11245809.pdf?arnumber=11245809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:35:08Z","timestamp":1766061308000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245809\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11245809","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}