{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:20:27Z","timestamp":1787322027126,"version":"build-2736575974"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tpami.2024.3479222","type":"journal-article","created":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T13:23:59Z","timestamp":1728912239000},"page":"650-662","source":"Crossref","is-referenced-by-count":37,"title":["V2X-ViTv2: Improved Vision Transformers for Vehicle-to-Everything Cooperative Perception"],"prefix":"10.1109","volume":"47","author":[{"given":"Runsheng","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Civil and Environmental Engineering, University of California, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chia-Ju","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, University of California, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7594-2292","authenticated-orcid":false,"given":"Zhengzhong","family":"Tu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-2304","authenticated-orcid":false,"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Google, University of California Merced, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917447"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.066"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_36"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00058"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363300"},{"key":"ref9","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"78","author":"Dosovitskiy","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"ref11","first-page":"4874","article-title":"Where2comm: Communication-efficient collaborative perception via spatial confidence maps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Hu","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2012.6232130"},{"key":"ref13","first-page":"1319","article-title":"Maxout networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goodfellow","year":"2013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10488-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref19","first-page":"989","article-title":"Cobevt: Cooperative bird\u2019s eye view semantic segmentation with sparse transformers","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"205","author":"Xu","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"ref21","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jaderberg","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref30","first-page":"29541","article-title":"Learning distilled collaboration graph for multi-agent perception","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564825"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3086095"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3019199"},{"key":"ref34","article-title":"Rt3000","year":"2021"},{"key":"ref35","first-page":"25151","article-title":"How2comm: Communication-efficient and collaboration-pragmatic multi-agent perception","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01669"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Fall49728.2020.9348525"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/fi11020027"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940479"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10777928\/10715696.pdf?arnumber=10715696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T01:30:41Z","timestamp":1733362241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10715696\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":39,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3479222","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}