{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T03:28:06Z","timestamp":1784258886532,"version":"3.55.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128729","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"3727-3733","source":"Crossref","is-referenced-by-count":2,"title":["Towards Latency-Aware 3D Streaming Perception for Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Jiaqi","family":"Peng","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangmiao","family":"Pang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Shen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3449912"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01790-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref4","article-title":"Bevdet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref6","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","volume-title":"The Eleventh International Conference on Learning Representations","author":"Park","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"ref11","article-title":"Multi-dimensional pruning: Joint channel, layer and block pruning with latency constraint","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_28"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00531"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094855"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/90"},{"issue":"2","key":"ref16","first-page":"7","article-title":"Adaptive streaming perception using deep reinforcement learning","volume":"1","author":"Ghosh","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00926"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72967-6_12"},{"key":"ref21","article-title":"Bevdet4d: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Sparse4d: Multi-view 3D object detection with sparse spatial-temporal fusion","author":"Lin","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref24","first-page":"3749","article-title":"Dort: Modeling dynamic objects in recurrent for multi-camera 3D object detection and tracking","volume-title":"Conference on Robot Learning","author":"Qing"},{"key":"ref25","article-title":"Predictive visual tracking: A new benchmark and baseline approach","author":"Li","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00918"},{"key":"ref27","article-title":"Bot-sort: Robust associations multi-pedestrian tracking","author":"Aharon","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01713"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"ref33","article-title":"Mime: Multilevel medical embedding of electronic health records for predictive healthcare","volume":"31","author":"Choi","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref34","first-page":"19 388","article-title":"Modeling irregular time series with continuous recurrent units","volume-title":"International conference on machine learning","author":"Schirmer"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3158588"},{"key":"ref36","article-title":"Deep variational bayes filters: Unsupervised learning of state space models from raw data","author":"Karl","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"A disentangled recognition and nonlinear dynamics model for unsupervised learning","volume":"30","author":"Fraccaro","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref38","volume-title":"Model predictive control: theory, computation, and design","volume":"2","author":"Rawlings","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3352811"},{"key":"ref40","first-page":"6531","article-title":"Motion transformer with global intention localization and local movement refinement","volume":"35","author":"Shaoshuai","year":"2022","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128729.pdf?arnumber=11128729","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:54:31Z","timestamp":1756882471000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128729\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128729","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}