{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:17:27Z","timestamp":1777889847036,"version":"3.51.4"},"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"}],"funder":[{"DOI":"10.13039\/501100021847","name":"Swiss National Supercomputing Centre","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100021847","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\/iccv51701.2025.00697","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7429-7439","source":"Crossref","is-referenced-by-count":0,"title":["3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection"],"prefix":"10.1109","author":[{"given":"Yung-Hsu","family":"Yang","sequence":"first","affiliation":[{"name":"ETH Zürich"}]},{"given":"Luigi","family":"Piccinelli","sequence":"additional","affiliation":[{"name":"ETH Zürich"}]},{"given":"Mattia","family":"Segu","sequence":"additional","affiliation":[{"name":"ETH Zürich"}]},{"given":"Siyuan","family":"Li","sequence":"additional","affiliation":[{"name":"ETH Zürich"}]},{"given":"Rui","family":"Huang","sequence":"additional","affiliation":[{"name":"ETH Zürich"}]},{"given":"Yuqian","family":"Fu","sequence":"additional","affiliation":[{"name":"INSAIT"}]},{"given":"Marc","family":"Pollefeys","sequence":"additional","affiliation":[{"name":"ETH Zürich"}]},{"given":"Hermann","family":"Blum","sequence":"additional","affiliation":[{"name":"ETH Zürich"}]},{"given":"Zuria","family":"Bauer","sequence":"additional","affiliation":[{"name":"ETH Zürich"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00773"},{"key":"ref2","article-title":"ARKitscenes - a diverse real-world dataset for 3d indoor scene understanding using mobile RGB-d data","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)","author":"Baruch","year":"2021"},{"key":"ref3","article-title":"Depth pro: Sharp monocular metric depth in less than a second","author":"Bochkovskii","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref9","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3160741"},{"key":"ref11","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume":"27","author":"Eigen","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref12","article-title":"Cc-3dt: Panoramic 3d object tracking via cross-camera fusion","volume-title":"6th Annual Conference on Robot Learning","author":"Fischer","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_15"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246620"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3168781"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2303"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00375"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01567"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref25","article-title":"Sparse4d: Multi-view 3d object detection with sparse spatial-temporal fusion","author":"Lin","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Sparse4d v3: Advancing end-to-end 3d detection and tracking","author":"Lin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803397"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32672"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref36","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Paszke","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00104"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3628473"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00644"},{"key":"ref48","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref50","first-page":"1475","article-title":"Probabilistic and geometric depth: Detecting objects in perspective","volume-title":"Conference on Robot Learning","author":"Wang","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00864"},{"key":"ref52","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks 2021)","author":"Wilson","year":"2021"},{"key":"ref53","article-title":"Bevformer v2: Adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision","author":"Yang","year":"2022","journal-title":"ArXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01161"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref56","volume-title":"Vis4d","author":"Yang","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref59","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref60","article-title":"Monodetr: Depthguided transformer for monocular 3d object detection","author":"Zhang","year":"2022","journal-title":"ICCV 2023"},{"key":"ref61","article-title":"An open and comprehensive pipeline for unified object grounding and detection","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw6661"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref64","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint arXiv"}],"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\/11446210.pdf?arnumber=11446210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:21:45Z","timestamp":1777612905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00697","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}