{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T14:05:20Z","timestamp":1778335520928,"version":"3.51.4"},"reference-count":63,"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\/iccv51701.2025.00813","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8688-8698","source":"Crossref","is-referenced-by-count":1,"title":["OpenM3D: Open Vocabulary Multi-View Indoor 3D Object Detection without Human Annotations"],"prefix":"10.1109","author":[{"given":"Peng-Hao","family":"Hsu","sequence":"first","affiliation":[{"name":"National Tsing Hua University"}]},{"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Fu-En","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Tao","family":"Tu","sequence":"additional","affiliation":[{"name":"Cornell University"}]},{"given":"Ming-Feng","family":"Li","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Yu-Lun","family":"Liu","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University"}]},{"given":"Albert Y. C.","family":"Chen","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Min","family":"Sun","sequence":"additional","affiliation":[{"name":"National Tsing Hua University"}]},{"given":"Cheng-Hao","family":"Kuo","sequence":"additional","affiliation":[{"name":"Amazon"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00286"},{"key":"ref2","article-title":"Arkitscenes - a diverse real-world dataset for 3d indoor scene understanding using mobile rgb-d data","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Baruch","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3145"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref11","article-title":"Openvocabulary object detection via vision and language knowledge distillation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Gu","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_18"},{"key":"ref13","article-title":"Semantic abstraction: Open-world 3d scene understanding from 2d vision-language models","volume-title":"Conference on Robot Learning (CoRL)","author":"Ha","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","article-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.066"},{"key":"ref17","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Jia","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref20","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref26","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Loshchilov","year":"2019"},{"key":"ref27","article-title":"High-quality entity segmentation","volume-title":"IEEE International Conference on Computer Vision (ICCV)","author":"Lu","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00121"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_25"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref34","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Qi","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref37","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6868"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_28"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2989"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3032166"},{"key":"ref47","article-title":"Crossdtr: Cross-view and depth-guided transformers for 3d object detection","author":"Tseng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00644"},{"key":"ref49","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"Conference on Robot Learning (CoRL)","author":"Wang","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02131"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00798"},{"key":"ref54","article-title":"Imov3d: Learning open-vocabulary point clouds 3d object detection from only 2d images","volume-title":"NeurIPS 2024","author":"Yang","year":"2024"},{"key":"ref55","article-title":"Sam3d: Segment anything in 3d scenes","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00204"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00836"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_19"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"}],"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\/11445241.pdf?arnumber=11445241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:18:28Z","timestamp":1777612708000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445241\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00813","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}