{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T22:24:04Z","timestamp":1783117444714,"version":"3.54.6"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61573057"],"award-info":[{"award-number":["61573057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0205005"],"award-info":[{"award-number":["2022ZD0205005"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.116032","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T23:03:33Z","timestamp":1776985413000},"page":"116032","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MAAFOcc: Multimodal adaptive asymmetric fusion based occupancy prediction"],"prefix":"10.1016","volume":"343","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6718-4172","authenticated-orcid":false,"given":"Jiuyu","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donglin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyan","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6375-8351","authenticated-orcid":false,"given":"Zhongli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116032_b1","series-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116032_b2","doi-asserted-by":"crossref","unstructured":"X. Bai, Z. Hu, X. Zhu, Q. Huang, Y. Chen, H. Fu, C.-L. Tai, Transfusion: Robust lidar-camera fusion for 3d object detection with transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1090\u20131099.","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"10.1016\/j.knosys.2026.116032_b3","series-title":"2023 IEEE International Conference on Robotics and Automation","first-page":"2774","article-title":"Bevfusion: Multi-task multi-sensor fusion with unified bird\u2019s-eye view representation","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116032_b4","series-title":"2024 IEEE 27th International Conference on Intelligent Transportation Systems","first-page":"2405","article-title":"QuadBEV: An efficient quadruple-task perception framework via birds\u2019-eye-view representation","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116032_b5","first-page":"64318","article-title":"Occ3D: A large-scale 3D occupancy prediction benchmark for autonomous driving","volume":"vol. 36","author":"Tian","year":"2023"},{"key":"10.1016\/j.knosys.2026.116032_b6","doi-asserted-by":"crossref","unstructured":"X. Wang, Z. Zhu, W. Xu, Y. Zhang, Y. Wei, X. Chi, Y. Ye, D. Du, J. Lu, X. Wang, OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2023, pp. 17850\u201317859.","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"10.1016\/j.knosys.2026.116032_b7","first-page":"1","article-title":"OccFusion: Multi-sensor fusion framework for 3D semantic occupancy prediction","author":"Ming","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.knosys.2026.116032_b8","doi-asserted-by":"crossref","unstructured":"J. Zhang, Y. Ding, Z. Liu, OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction, in: Proceedings of the Asian Conference on Computer Vision, ACCV, 2024, pp. 3587\u20133604.","DOI":"10.1007\/978-981-96-0972-7_14"},{"key":"10.1016\/j.knosys.2026.116032_b9","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"12404","article-title":"Renderocc: Vision-centric 3d occupancy prediction with 2d rendering supervision","author":"Pan","year":"2024"},{"key":"10.1016\/j.knosys.2026.116032_b10","doi-asserted-by":"crossref","unstructured":"Y. Zhang, Z. Zhu, D. Du, OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2023, pp. 9433\u20139443.","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"10.1016\/j.knosys.2026.116032_b11","series-title":"FlashOcc: Fast and memory-efficient occupancy prediction via channel-to-height plugin","author":"Yu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116032_b12","series-title":"EFFOcc: Learning efficient occupancy networks from minimal labels for autonomous driving","author":"Shi","year":"2025"},{"key":"10.1016\/j.knosys.2026.116032_b13","series-title":"DAOcc: 3D object detection assisted multi-sensor fusion for 3D occupancy prediction","author":"Yang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116032_b14","series-title":"FB-OCC: 3D occupancy prediction based on forward-backward view transformation","author":"Li","year":"2023"},{"key":"10.1016\/j.knosys.2026.116032_b15","doi-asserted-by":"crossref","DOI":"10.1109\/TITS.2024.3439557","article-title":"Robustness-aware 3d object detection in autonomous driving: A review and outlook","author":"Song","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.knosys.2026.116032_b16","series-title":"2021 IEEE International Intelligent Transportation Systems Conference","first-page":"3047","article-title":"Fusionpainting: Multimodal fusion with adaptive attention for 3d object detection","author":"Xu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116032_b17","doi-asserted-by":"crossref","unstructured":"R. Nabati, H. Qi, Centerfusion: Center-based radar and camera fusion for 3d object detection, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 1527\u20131536.","DOI":"10.1109\/WACV48630.2021.00157"},{"key":"10.1016\/j.knosys.2026.116032_b18","doi-asserted-by":"crossref","unstructured":"Y. Qin, C. Wang, Z. Kang, N. Ma, Z. Li, R. Zhang, SupFusion: Supervised LiDAR-camera fusion for 3D object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 22014\u201322024.","DOI":"10.1109\/ICCV51070.2023.02012"},{"key":"10.1016\/j.knosys.2026.116032_b19","series-title":"European Conference on Computer Vision","first-page":"347","article-title":"Graphbev: Towards robust bev feature alignment for multi-modal 3d object detection","author":"Song","year":"2024"},{"key":"10.1016\/j.knosys.2026.116032_b20","series-title":"European Conference on Computer Vision","first-page":"691","article-title":"Homogeneous multi-modal feature fusion and interaction for 3D object detection","author":"Li","year":"2022"},{"key":"10.1016\/j.knosys.2026.116032_b21","doi-asserted-by":"crossref","first-page":"51710","DOI":"10.1109\/ACCESS.2021.3070379","article-title":"RoIFusion: 3D object detection from LiDAR and vision","volume":"9","author":"Chen","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.knosys.2026.116032_b22","series-title":"Bevfusion4d: Learning lidar-camera fusion under bird\u2019s-eye-view via cross-modality guidance and temporal aggregation","author":"Cai","year":"2023"},{"key":"10.1016\/j.knosys.2026.116032_b23","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16","first-page":"194","article-title":"Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d","author":"Philion","year":"2020"},{"key":"10.1016\/j.knosys.2026.116032_b24","article-title":"Bevformer: learning bird\u2019s-eye-view representation from lidar-camera via spatiotemporal transformers","author":"Li","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116032_b25","doi-asserted-by":"crossref","unstructured":"Y. Wei, L. Zhao, W. Zheng, Z. Zhu, J. Zhou, J. Lu, SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2023, pp. 21729\u201321740.","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"10.1016\/j.knosys.2026.116032_b26","series-title":"Fully sparse 3D panoptic occupancy prediction","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116032_b27","doi-asserted-by":"crossref","unstructured":"Z. Li, Z. Yu, W. Wang, A. Anandkumar, T. Lu, J.M. Alvarez, FB-BEV: BEV Representation from Forward-Backward View Transformations, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2023, pp. 6919\u20136928.","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"10.1016\/j.knosys.2026.116032_b28","series-title":"Unleashing HyDRa: Hybrid fusion, depth consistency and radar for unified 3D perception","author":"Wolters","year":"2025"},{"key":"10.1016\/j.knosys.2026.116032_b29","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"10","key":"10.1016\/j.knosys.2026.116032_b30","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/s18103337","article-title":"Second: Sparsely embedded convolutional detection","volume":"18","author":"Yan","year":"2018","journal-title":"Sensors"},{"key":"10.1016\/j.knosys.2026.116032_b31","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"439","article-title":"Detecting as labeling: Rethinking lidar-camera fusion in 3D object detection","author":"Huang","year":"2025"},{"issue":"2","key":"10.1016\/j.knosys.2026.116032_b32","doi-asserted-by":"crossref","first-page":"1787","DOI":"10.1109\/TCSVT.2024.3483191","article-title":"A semantic-aware detail adaptive network for image enhancement","volume":"35","author":"Fan","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"10.1016\/j.knosys.2026.116032_b33","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1109\/TBC.2022.3231101","article-title":"Perception-oriented U-shaped transformer network for 360-degree no-reference image quality assessment","volume":"69","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Broadcast."},{"issue":"11","key":"10.1016\/j.knosys.2026.116032_b34","doi-asserted-by":"crossref","first-page":"8282","DOI":"10.1109\/TII.2025.3588622","article-title":"GAANet: Graph aggregation alignment feature fusion for multispectral object detection","volume":"21","author":"Zheng","year":"2025","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.knosys.2026.116032_b35","doi-asserted-by":"crossref","first-page":"7444","DOI":"10.1109\/TMM.2025.3599097","article-title":"COFNet: Contrastive object-aware fusion using box-level masks for multispectral object detection","volume":"27","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116032_b36","series-title":"Squeeze-and-excitation networks","author":"Hu","year":"2019"},{"key":"10.1016\/j.knosys.2026.116032_b37","doi-asserted-by":"crossref","unstructured":"Y. Wang, Y. Chen, X. Liao, L. Fan, Z. Zhang, PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 17158\u201317168.","DOI":"10.1109\/CVPR52733.2024.01624"},{"key":"10.1016\/j.knosys.2026.116032_b38","doi-asserted-by":"crossref","unstructured":"Q. Ma, X. Tan, Y. Qu, L. Ma, Z. Zhang, Y. Xie, COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 19936\u201319945.","DOI":"10.1109\/CVPR52733.2024.01884"},{"key":"10.1016\/j.knosys.2026.116032_b39","series-title":"RadOcc: Learning cross-modality occupancy knowledge through rendering assisted distillation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116032_b40","doi-asserted-by":"crossref","unstructured":"T. Yin, X. Zhou, P. Krahenbuhl, Center-Based 3D Object Detection and Tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 11784\u201311793.","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"10.1016\/j.knosys.2026.116032_b41","series-title":"Focal loss for dense object detection","author":"Lin","year":"2018"},{"key":"10.1016\/j.knosys.2026.116032_b42","doi-asserted-by":"crossref","unstructured":"X. Bai, Z. Hu, X. Zhu, Q. Huang, Y. Chen, H. Fu, C.-L. Tai, TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection With Transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 1090\u20131099.","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"10.1016\/j.knosys.2026.116032_b43","series-title":"2020 International Conference on 3D Vision","first-page":"111","article-title":"LMSCNet: Lightweight multiscale 3D semantic completion","author":"Rold\u00e3o","year":"2020"},{"issue":"6","key":"10.1016\/j.knosys.2026.116032_b44","doi-asserted-by":"crossref","first-page":"5687","DOI":"10.1109\/LRA.2024.3396092","article-title":"Co-occ: Coupling explicit feature fusion with volume rendering regularization for multi-modal 3D semantic occupancy prediction","volume":"9","author":"Pan","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.knosys.2026.116032_b45","doi-asserted-by":"crossref","unstructured":"H. Caesar, V. Bankiti, A.H. Lang, S. Vora, V.E. Liong, Q. Xu, A. Krishnan, Y. Pan, G. Baldan, O. Beijbom, nuScenes: A Multimodal Dataset for Autonomous Driving, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 11621\u201311631.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"10.1016\/j.knosys.2026.116032_b46","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"10.1016\/j.knosys.2026.116032_b47","first-page":"369","article-title":"Super-convergence: Very fast training of neural networks using large learning rates","volume":"vol. 11006","author":"Smith","year":"2019"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126007586?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126007586?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T22:13:17Z","timestamp":1783116797000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126007586"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":47,"alternative-id":["S0950705126007586"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116032","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MAAFOcc: Multimodal adaptive asymmetric fusion based occupancy prediction","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116032","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116032"}}