{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:23:40Z","timestamp":1763191420840,"version":"3.45.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227937","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["MPFormer: Multi-Prior Transformer for Vision-based Scene Understanding in Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Biao","family":"Xu","sequence":"first","affiliation":[{"name":"Northeastern University,College of Information Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuotao","family":"Ning","sequence":"additional","affiliation":[{"name":"Neusoft Reach Automotive Technology (Shenyang) Co., Ltd.,ADS Competency Center,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Cheng","sequence":"additional","affiliation":[{"name":"Neusoft Reach Automotive Technology (Shenyang) Co., Ltd.,ADS Competency Center,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Neusoft Reach Automotive Technology (Shenyang) Co., Ltd.,ADS Competency Center,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiwei","family":"Nie","sequence":"additional","affiliation":[{"name":"Northeastern University,College of Information Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guixing","family":"Xu","sequence":"additional","affiliation":[{"name":"Northeastern University,College of Information Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hualin","family":"Chen","sequence":"additional","affiliation":[{"name":"Northeastern University,College of Information Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeastern University,College of Information Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00939","article-title":"Semantickitti: A dataset for semantic scene understanding of lidar sequences","author":"Behley","year":"2019"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-20077-9_1","article-title":"Bevformer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers","author":"Li","year":"2022"},{"article-title":"Objects as points","year":"2019","author":"Zhou","key":"ref3"},{"article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","year":"2021","author":"Wang","key":"ref4"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1109\/ICCVW54120.2021.00107","article-title":"Fcos3d: Fully convolutional one-stage monocular 3d object detection","author":"Wang","year":"2021"},{"article-title":"Mask r-cnn","year":"2018","author":"He","key":"ref6"},{"article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","year":"2017","author":"Qi","key":"ref7"},{"article-title":"Semantic scene completion from a single depth image","year":"2016","author":"Song","key":"ref8"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.00396","article-title":"Monoscene: Monocular 3d semantic scene completion","author":"Cao","year":"2022"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58568-6_12","article-title":"Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d","author":"Philion","year":"2020"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46484-8_29","article-title":"Stacked hourglass networks for human pose estimation","author":"Newell","year":"2016"},{"article-title":"Rethinking atrous convolution for semantic image segmentation","year":"2017","author":"Chen","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00865","article-title":"Occformer: Dual-path transformer for vision-based 3d semantic occupancy prediction","author":"Zhang","year":"2023"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1109\/3DV50981.2020.00021","article-title":"Lmscnet: Lightweight multiscale 3d semantic completion","author":"Rold\u00e3o","year":"2020"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.00341","article-title":"Anisotropic convolutional networks for 3d semantic scene completion","author":"Li","year":"2020"},{"article-title":"Sparse single sweep lidar point cloud segmentation via learning contextual shape priors from scene completion","year":"2020","author":"Yan","key":"ref17"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.00890","article-title":"Tri-perspective view for vision-based 3d semantic occupancy prediction","author":"Huang","year":"2023"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.00877","article-title":"Voxformer: Sparse voxel transformer for camera-based 3d semantic scene completion","author":"Li","year":"2023"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227937.pdf?arnumber=11227937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:21:19Z","timestamp":1763191279000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227937\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227937","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}