{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T04:46:31Z","timestamp":1777437991703,"version":"3.51.4"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"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":[[2025,2,26]]},"DOI":"10.1109\/wacv61041.2025.00306","type":"proceedings-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T17:08:13Z","timestamp":1744132093000},"page":"3096-3106","source":"Crossref","is-referenced-by-count":3,"title":["OccLoff: Learning Optimized Feature Fusion for 3D Occupancy Prediction"],"prefix":"10.1109","author":[{"given":"Ji","family":"Zhang","sequence":"first","affiliation":[{"name":"Wuhan University,Wuhan,Hubei Province,P.R. China,430072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiran","family":"Ding","sequence":"additional","affiliation":[{"name":"Wuhan University,Wuhan,Hubei Province,P.R. China,430072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixin","family":"Liu","sequence":"additional","affiliation":[{"name":"Wuhan University,Wuhan,Hubei Province,P.R. China,430072"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9296","article-title":"Se-mantickitti: A dataset for semantic scene understanding of lidar sequences","volume-title":"2019 IEEEICVF International Confer-ence on Computer Vision, ICCV 2019","author":"Behley","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00464"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00396"},{"key":"ref5","first-page":"8748","article-title":"Ar-goverse: 3d tracking and forecasting with rich maps","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Chang","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3145159"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01635"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","article-title":"Bevdet4d: Exploit tem-poral cues in multi-camera 3d object detection","author":"Huang","year":"2022","journal-title":"CoRR, abs\/2203.17054"},{"key":"ref13","article-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"CoRR, abs\/2112.11790"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00890"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref21","first-page":"10421","article-title":"Bevfusion: A simple and robust lidar-camera fusion framework","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022","volume":"35","author":"Liang","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_8"},{"key":"ref27","article-title":"Occdepth: A depth-aware method for 3d semantic scene completion","author":"Miao","year":"2023","journal-title":"CoRR, abs\/2302.13540"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802434"},{"key":"ref29","article-title":"Occfusion: A straightforward and effective multi-sensor fusion framework for 3d occupancy prediction","author":"Ming","year":"2024","journal-title":"CoRR, abs\/2403.01644"},{"key":"ref30","first-page":"360","article-title":"No fuss distance met-ric learning using proxies","volume-title":"IEEE International Conference on Computer Vision, ICCV 2017","author":"Movshovitz-Attias","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3396092"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611537"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"ref34","article-title":"Time will tell: New outlooks and A baseline for temporal multi-view 3d object detection","volume-title":"The Eleventh International Con-ference on Learning Representations, ICLR 2023","author":"Park","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref36","first-page":"5099","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Ruizhongtai Qi","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref40","first-page":"64318","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Infor-mation Processing Systems 2023, NeurIPS 2023","volume":"36","author":"Tian","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_6"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01624"},{"key":"ref45","first-page":"5096","article-title":"Frustum-former: Adaptive instance-aware resampling for multi-view 3d detection","volume-title":"IEEEICVF Conference on Computer Vision and Pattern Recognition, CVPR 2023","author":"Wang","year":"2023"},{"key":"ref46","first-page":"180","article-title":"DETR3D: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"Conference on Robot Learning","volume":"164","author":"Wang","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01986"},{"key":"ref49","article-title":"M2bev: Multi-camera joint 3d detection and seg-mentation with unified birds-eye view representation","author":"Xie","year":"2022","journal-title":"CoRR, abs\/2204.05088"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16419"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref54","article-title":"Deformable DETR: deformable transformers for end-to-end object detection","volume-title":"9th International Con-ference on Learning Representations, ICLR 2021, Virtual Event","author":"Zhu"},{"key":"ref55","article-title":"Pointocc: Cylindrical tri-perspective view for point-based 3d semantic occupancy prediction","author":"Zuo","year":"2023","journal-title":"CoRR, abs\/2308.16896"}],"event":{"name":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2025,2,26]]},"end":{"date-parts":[[2025,3,6]]}},"container-title":["2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10943266\/10943193\/10943843.pdf?arnumber=10943843","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T05:32:06Z","timestamp":1744176726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10943843\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,26]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/wacv61041.2025.00306","relation":{},"subject":[],"published":{"date-parts":[[2025,2,26]]}}}