{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:20:23Z","timestamp":1785334823297,"version":"3.55.0"},"reference-count":64,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00924","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9913-9923","source":"Crossref","is-referenced-by-count":3,"title":["LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models"],"prefix":"10.1109","author":[{"given":"Haiwen","family":"Huang","sequence":"first","affiliation":[{"name":"University of T&#x00FC;bingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anpei","family":"Chen","sequence":"additional","affiliation":[{"name":"University of T&#x00FC;bingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Volodymyr","family":"Havrylov","sequence":"additional","affiliation":[{"name":"University of T&#x00FC;bingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Geiger","sequence":"additional","affiliation":[{"name":"University of T&#x00FC;bingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bosch Center for Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00852"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00677"},{"key":"ref6","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0450(1979)018<1016:lfioat>2.0.co;2"},{"key":"ref8","article-title":"A guide to convolution arithmetic for deep learning","author":"Dumoulin","year":"2016","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"Eigen","year":"2014","journal-title":"NeurIPS, 27"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02059"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.126"},{"key":"ref12","article-title":"Featup: A model-agnostic framework for features at any resolution","author":"Fu","year":"2024","journal-title":"ICLR"},{"key":"ref13","article-title":"Unsupervised semantic segmentation by distilling feature correspondences","author":"Hamilton","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2012.213"},{"key":"ref16","article-title":"Renovating names in open-vocabulary segmentation benchmarks","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Huang","year":"2024"},{"key":"ref17","first-page":"19545","article-title":"Space-time correspondence as a contrastive random walk","volume":"33","author":"Jabri","year":"2020","journal-title":"NeurIPS"},{"key":"ref18","article-title":"NAVI: Categoryagnostic image collections with high-quality 3d shape and pose annotations","author":"Jampani","year":"2023","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276497"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00087"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02037"},{"key":"ref28","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004474"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_14"},{"key":"ref31","first-page":"20889","article-title":"Sapa: Similarity-aware point affiliation for feature upsampling","volume":"35","author":"Lu","year":"2022","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"issue":"1","key":"ref33","first-page":"1049","article-title":"Cubic spline interpolation","volume":"45","author":"McKinley","year":"1998","journal-title":"College of the Redwoods"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00003"},{"key":"ref37","article-title":"Featured Certification","author":"Oquab","journal-title":"DINOv2: Learning robust visual features without supervision"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref39","author":"Pont-Tuset","year":"2017","journal-title":"The 2017 davis challenge on video object segmentation"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02033"},{"key":"ref41","first-page":"8748","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01187"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref45","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","author":"Ren","year":"2024","journal-title":"Grounded sam: Assembling open-world models for diverse visual tasks"},{"key":"ref47","article-title":"Unet: Convolutional networks for biomedical image segmentation","volume-title":"Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany","author":"Ronneberger","year":"2015"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015720"},{"key":"ref49","article-title":"Is the deconvolution layer the same as a convolutional layer?","author":"Shi","year":"2016","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00745"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897365"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_7"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"ref54","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_21"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00310"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00823"},{"key":"ref61","article-title":"pixelnerf: Neural radiance fields from one or few images. 2021 ieee","author":"Yu","year":"2020","journal-title":"CVPR"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1399"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444710.pdf?arnumber=11444710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:58Z","timestamp":1777611538000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00924","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}