{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T22:06:21Z","timestamp":1782425181108,"version":"3.54.5"},"reference-count":68,"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\/iccv51701.2025.02650","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"28535-28545","source":"Crossref","is-referenced-by-count":2,"title":["SAM4D: Segment Anything in Camera and LiDAR Streams"],"prefix":"10.1109","author":[{"given":"Jianyun","family":"Xu","sequence":"first","affiliation":[{"name":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Wang","sequence":"additional","affiliation":[{"name":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqian","family":"Ni","sequence":"additional","affiliation":[{"name":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyong","family":"Hu","sequence":"additional","affiliation":[{"name":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Yang","sequence":"additional","affiliation":[{"name":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianke","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Li","sequence":"additional","affiliation":[{"name":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00024"},{"key":"ref2","article-title":"Window attention is bugged: how not to interpolate position embeddings","volume-title":"International Conference on Learning Representations","author":"Bolya","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610316"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356074"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"ref7","article-title":"Sam2-adapter: Evaluating & adapting segment anything 2 in downstream tasks: Camouflage, shadow, medical image segmentation, and more","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00551"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00105"},{"key":"ref12","article-title":"Interactive4d: Interactive 4d lidar segmentation","author":"Fradlin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802361"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_16"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1303"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02078"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00366"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02491-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25228"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1340"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0757"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28121"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1617"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01981"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3317784"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3396092"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref34","first-page":"194","volume-title":"Lift","author":"Philion","year":"2020"},{"key":"ref35","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint"},{"key":"ref36","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":"ref37","article-title":"Sam 2: Segment anything in images and videos","volume-title":"International Conference on Learning Representations","author":"Ravi","year":"2025"},{"key":"ref38","article-title":"Grounding dino 1.5: Advance the \u201cedge\u201d of open-set object detection","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","first-page":"29441","article-title":"Hiera: A hierarchical vision transformer without the bells-andwhistles","volume-title":"International Conference on Machine Learning","author":"Ryali","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01642"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref43","article-title":"Ovo: Open-vocabulary occupancy","author":"Tan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"TorchSparse: Efficient Point Cloud Inference Engine","volume-title":"Conference on Machine Learning and Systems","author":"Tang","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00025"},{"key":"ref46","article-title":"Can sam segment anything? when sam meets camouflaged object detection","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Pop-3d: Open-vocabulary 3d occupancy prediction from images","author":"Vobecky","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_6"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191040"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00502"},{"key":"ref51","article-title":"Reliocc: Towards reliable semantic occupancy prediction via uncertainty learning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01401"},{"key":"ref53","first-page":"1398","article-title":"Label-efficient semantic scene completion with scribble annotations","volume-title":"International Joint Conference on Artificial Intelligence","author":"Wang","year":"2024"},{"key":"ref54","article-title":"Pixelthink: Towards efficient chain-of-pixel reasoning","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00619"},{"key":"ref56","article-title":"Robobev: Towards robust bird\u2019s eye view perception under corruptions","author":"Xie","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref60","article-title":"Sam3d: Segment anything in 3d scenes","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01463"},{"key":"ref62","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_7"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00219"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681293"},{"key":"ref66","article-title":"Fast segment anything","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_6"},{"key":"ref68","article-title":"Point-SAM: Promptable 3d segmentation model for point clouds","volume-title":"International Conference on Learning Representations","author":"Zhou","year":"2025"}],"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\/11444552.pdf?arnumber=11444552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:12:14Z","timestamp":1777529534000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02650","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}