{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T20:13:07Z","timestamp":1780085587641,"version":"3.54.0"},"reference-count":61,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52172380"],"award-info":[{"award-number":["52172380"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013317","name":"Key Research and Development Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2024GX-ZDCYL-01-25,2024CY-JJQ-55"],"award-info":[{"award-number":["2024GX-ZDCYL-01-25,2024CY-JJQ-55"]}],"id":[{"id":"10.13039\/501100013317","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Shanghai Municipal Science and Technology","doi-asserted-by":"publisher","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}],"id":[{"id":"10.13039\/501100003399","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\/iccv51701.2025.02495","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26879-26889","source":"Crossref","is-referenced-by-count":1,"title":["GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-Based Transformer"],"prefix":"10.1109","author":[{"given":"Xin","family":"Jin","sequence":"first","affiliation":[{"name":"Chang' an University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haisheng","family":"Su","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Ma","sequence":"additional","affiliation":[{"name":"SenseAuto Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Liu","sequence":"additional","affiliation":[{"name":"SenseAuto Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[{"name":"SenseAuto Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Hui","sequence":"additional","affiliation":[{"name":"Chang' an University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19897"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01296"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00771"},{"key":"ref9","first-page":"4","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"A generalization of transformer networks to graphs","volume-title":"AAAI Workshop on Deep Learning on Graphs: Methods and Applications","author":"Dwivedi","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0026"},{"key":"ref13","first-page":"6","article-title":"Fsd v2: Improving fully sparse 3d object detection with virtual voxels","author":"Fan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"6","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"ref17","first-page":"4","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19980"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28040"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01683"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610346"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3345880"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01685"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6837"},{"key":"ref26","article-title":"Lion: Linear group rnn for 3d object detection in point clouds","author":"Liu","year":"2024","journal-title":"arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_7"},{"key":"ref28","first-page":"6","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"ref30","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"RQi","year":"2017"},{"key":"ref31","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Ruizhongtai Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01710-9"},{"key":"ref36","first-page":"1","article-title":"Robosense: Large-scale dataset and benchmark for egocentric robot perception and navigation in crowded and unstructured environments","author":"Su","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"1","article-title":"Difsd: Ego-centric fully sparse paradigm with uncertainty denoising and iterative refinement for efficient end-to-end autonomous driving","author":"Su","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_25"},{"key":"ref40","first-page":"6","volume-title":"Openpcdet: An opensource toolbox for 3d object detection from point clouds","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967897"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01299"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0319-z"},{"key":"ref45","first-page":"5","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0305-5"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01295"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01161"},{"key":"ref52","article-title":"HEDNet: A hierarchical encoder-decoder network for 3d object detection in point clouds","volume-title":"Thirtyseventh Conference on Neural Information Processing Systems","author":"Zhang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01372"},{"key":"ref54","article-title":"Voxel mamba: Group-free state space models for point cloud based 3d object detection","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00500"},{"key":"ref57","first-page":"2","article-title":"Fastpillars: A deployment-friendly pillar-based 3d detector","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","first-page":"2","article-title":"Pillarhist: A quantization-aware pillar feature encoder based on heightaware histogram","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_29"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00897"}],"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\/11444703.pdf?arnumber=11444703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:51Z","timestamp":1777529991000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444703\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02495","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}