{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:38Z","timestamp":1778048318097,"version":"3.51.4"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00313","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3203-3212","source":"Crossref","is-referenced-by-count":0,"title":["PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications"],"prefix":"10.1109","author":[{"given":"Yunze","family":"Liu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiran","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Bristol"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayang","family":"Ao","sequence":"additional","affiliation":[{"name":"The University of Melbourne"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01642"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00062"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_2"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"ref6","article-title":"Dpmix: Mixture of depth and point cloud video experts for 4d action segmentation","author":"Zhang","year":"2023"},{"key":"ref7","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"First conference on language modeling","author":"Gu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02575"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812302"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00832"},{"key":"ref14","article-title":"Nsm4d: Neural scene model based online 4d point cloud sequence understanding","author":"Dong","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"ref16","article-title":"Maskmamba: A hybrid mamba-transformer model for masked image generation","author":"Chen","year":"2024"},{"key":"ref17","article-title":"Hmt-unet: A hybird mamba-transformer vision unet for medical image segmentation","author":"Zhang","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761394"},{"key":"ref19","article-title":"Pointramba: A hybrid transformer-mamba framework for point cloud analysis","author":"Wang","year":"2024"},{"key":"ref20","article-title":"Hmt-grasp: A hybrid mamba-transformer approach for robot grasping in cluttered environments","author":"Xiong","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247625"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.1168"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00904"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01520"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref26","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017","journal-title":"NeurIPS"},{"key":"ref27","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":"Qi"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01548"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01694"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref34","article-title":"SHREC\u201917 Track: 3D hand gesture recognition using a depth and skeletal dataset","author":"De Smedt","year":"2017","journal-title":"3DOR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.033"},{"key":"ref39","first-page":"70","article-title":"Goal-auxiliary actor-critic for 6d robotic grasping with point clouds","volume-title":"Conference on Robot Learning","author":"Wang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00931"},{"key":"ref41","author":"Ke","year":"2024","journal-title":"3d diffuser actor: Policy diffusion with 3d scene representations"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492418.pdf?arnumber=11492418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:27Z","timestamp":1778046987000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492418\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00313","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}