{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:06:33Z","timestamp":1777889193501,"version":"3.51.4"},"reference-count":65,"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":["62433003,62476017"],"award-info":[{"award-number":["62433003,62476017"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.02588","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27885-27895","source":"Crossref","is-referenced-by-count":0,"title":["SP\n                    <sup>2<\/sup>\n                    T: Sparse Proxy Attention for Dual-Stream Point Transformer"],"prefix":"10.1109","author":[{"given":"Jiaxu","family":"Wan","sequence":"first","affiliation":[{"name":"School of Aerospace, BUAA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Aerospace, BUAA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqi","family":"He","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, BUAA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangyan","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, BUAA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qishu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, BUAA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ding","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Aerospace, BUAA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Aerospace, BUAA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref10","article-title":"Vision transformers need registers","author":"Darcet","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_10"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_5"},{"key":"ref16","first-page":"22690","article-title":"Vision transformer with super token sampling","volume-title":"In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Huang"},{"key":"ref17","article-title":"Perceiver io: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"In International conference on machine learning","author":"Jaegle"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01683"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref24","first-page":"3744","article-title":"Set transformer: A frame-work for attention-based permutation-invariant neural networks","volume-title":"In International conference on machine learning","author":"Lee"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588612"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01696"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3295095"},{"key":"ref31","first-page":"25346","article-title":"Dualstream network for visual recognition","volume":"34","author":"Mao","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01644"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02089"},{"key":"ref36","article-title":"How do vision transformers work?","author":"Park","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"In Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi"},{"key":"ref38","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1685"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCS45141.2019.9065747"},{"key":"ref46","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01299"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3592131"},{"key":"ref49","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","journal-title":"arXiv preprint"},{"key":"ref50","first-page":"180","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"In Conference on Robot Learning","author":"Wang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2415"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_39"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.26599\/cvm.2025.9450383"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01161"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01372"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102455"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3700443"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113381"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105363"},{"key":"ref62","article-title":"Dspoint: Dual-scale point cloud recognition with high-frequency fusion","author":"Zhang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00571"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref65","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\/11445096.pdf?arnumber=11445096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:43Z","timestamp":1777612063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445096\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02588","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}