{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T19:22:16Z","timestamp":1771960936130,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tiv.2024.3386576","type":"journal-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T14:52:47Z","timestamp":1712674367000},"page":"2905-2914","source":"Crossref","is-referenced-by-count":12,"title":["PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-Based 3D Object Detection"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0444-1079","authenticated-orcid":false,"given":"Weixin","family":"Mao","sequence":"first","affiliation":[{"name":"Graduate School of Information, Production and Systems, Waseda University, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0481-4813","authenticated-orcid":false,"given":"Tiancai","family":"Wang","sequence":"additional","affiliation":[{"name":"Megvii Technology Limited, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2004-0897","authenticated-orcid":false,"given":"Diankun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2259-7487","authenticated-orcid":false,"given":"Junjie","family":"Yan","sequence":"additional","affiliation":[{"name":"Computer Institute, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4192-554X","authenticated-orcid":false,"given":"Osamu","family":"Yoshie","sequence":"additional","affiliation":[{"name":"Graduate School of Information, Production and Systems, Waseda University, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref2","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3223131"},{"key":"ref5","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref6","first-page":"21224","article-title":"Every view counts: Cross-view consistency in 3D object detection with hybrid-cylindrical-spherical voxelization","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Chen","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01296"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"ref11","article-title":"MMDetection3D: OpenMMLab next-generation platform for general 3D object detection","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00826"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01166"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"ref19","first-page":"351","article-title":"Fully sparse 3D object detection","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Fan","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01668"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19980"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01685"},{"key":"ref26","article-title":"PointCNN: Convolution on x-transformed points","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2018"},{"key":"ref27","first-page":"18442","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Li","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28141"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00113"},{"key":"ref32","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo","year":"2016"},{"key":"ref33","article-title":"Voxel-mae: Masked autoencoders for pre-training large-scale point clouds","author":"Min","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3329437"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01437"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref38","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qi","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_3"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref41","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref42","first-page":"34899","article-title":"Fully convolutional one-stage 3D object detection on LiDAR range images","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Tian","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3213796"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3264658"},{"key":"ref46","first-page":"14388","article-title":"P2P: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2022"},{"key":"ref47","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Wilson","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref49","article-title":"DBQ-SSD: Dynamic ball query for efficient 3D object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00170"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01151"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16470"},{"key":"ref55","article-title":"Cylinder3D: An effective 3D framework for driving-scene lidar semantic segmentation","author":"Zhou","year":"2020"},{"key":"ref56","article-title":"Fastpillars: A deployment-friendly pillar-based 3D detector","author":"Zhou","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref58","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274857\/11142486\/10495196.pdf?arnumber=10495196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T05:16:57Z","timestamp":1756271817000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10495196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":58,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2024.3386576","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}