{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:17:24Z","timestamp":1787012244256,"version":"build-2736575974"},"reference-count":37,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12071478,61972404"],"award-info":[{"award-number":["12071478,61972404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004260","name":"Renmin University of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004260","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128776","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"9590-9596","source":"Crossref","is-referenced-by-count":3,"title":["Is Discretization Fusion All You Need for Collaborative Perception?"],"prefix":"10.1109","author":[{"given":"Kang","family":"Yang","sequence":"first","affiliation":[{"name":"School of Information Renmin University of China,Bei Jing,China,100872"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianci","family":"Bu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Hu Nan,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lantao","family":"Li","sequence":"additional","affiliation":[{"name":"Sony Research and Development Center China,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunxu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Renmin University of China,Bei Jing,China,100872"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongcai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Renmin University of China,Bei Jing,China,100872"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deying","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Renmin University of China,Bei Jing,China,100872"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4874","article-title":"Where2comm: Communication-efficient collaborative perception via spatial confidence maps","volume-title":"Advances in neural information processing systems","volume":"35","author":"Hu","year":"2022"},{"key":"ref2","volume-title":"Cobevt: Cooperative bird\u2019s eye view semantic segmentation with sparse transformers","author":"Xu","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_36"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01318"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00892"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref10","first-page":"180","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"Conference on Robot Learning","author":"Wang","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3028424"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00058"},{"key":"ref13","first-page":"29 541","article-title":"Learning distilled collaboration graph for multi-agent perception","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Li","year":"2021"},{"key":"ref14","article-title":"An extensible framework for open heterogeneous collaborative perception","volume-title":"arXiv preprint","author":"Lu","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00088"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00245"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref18","volume":"abs\/2112.11790","author":"Huang","year":"2021","journal-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view"},{"key":"ref19","article-title":"Orthographic feature transform for monocular 3d object detection","author":"Roddick","year":"2018","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01255"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00314"},{"issue":"2","key":"ref22","first-page":"1477","article-title":"Bevdepth: Acquisition of reliable depth for multi-view 3d object detection","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"37","author":"Li","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref26","article-title":"Sparse4d: Multi-view 3d object detection with sparse spatial-temporal fusion","author":"Lin","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3211006"},{"key":"ref30","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref36","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363300"}],"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\/11128776.pdf?arnumber=11128776","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:08:51Z","timestamp":1756879731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128776\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128776","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}