{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T09:25:35Z","timestamp":1787217935489,"version":"build-2736575974"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114340","type":"journal-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:40:17Z","timestamp":1782574817000},"page":"114340","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["SHTOcc: Effective 3D occupancy prediction with sparse head and tail voxels"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7150-371X","authenticated-orcid":false,"given":"Qiucheng","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9346-1196","authenticated-orcid":false,"given":"Xin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114340_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108722","article-title":"Paying attention for adjacent areas: Learning discriminative features for large-scale 3D scene segmentation","volume":"129","author":"Li","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114340_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111030","article-title":"Geometry-semantic aware for monocular 3D semantic scene completion","volume":"158","author":"Lu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114340_b3","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, 2024, pp. 19936\u201319945.","DOI":"10.1109\/CVPR52733.2024.01884"},{"key":"10.1016\/j.patcog.2026.114340_b4","article-title":"FSF-Net: Enhance 4D occupancy forecasting with coarse BEV scene flow for autonomous driving","author":"Guo","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114340_b5","doi-asserted-by":"crossref","unstructured":"Y. Huang, W. Zheng, Y. Zhang, J. Zhou, J. Lu, Tri-perspective view for vision-based 3D semantic occupancy prediction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9223\u20139232.","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"10.1016\/j.patcog.2026.114340_b6","series-title":"European Conference on Computer Vision","first-page":"376","article-title":"Gaussianformer: Scene as gaussians for vision-based 3D semantic occupancy prediction","author":"Huang","year":"2024"},{"key":"10.1016\/j.patcog.2026.114340_b7","series-title":"European Conference on Computer Vision","first-page":"54","article-title":"Fully sparse 3D occupancy prediction","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.114340_b8","article-title":"E2IGB: Enhanced effective-information-guided class-balanced loss for long-tailed object recognition","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114340_b9","article-title":"DBL: Dual-level balanced learning for long-tailed classification","author":"Wu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114340_b10","doi-asserted-by":"crossref","unstructured":"P. Tang, Z. Wang, G. Wang, J. Zheng, X. Ren, B. Feng, C. Ma, Sparseocc: Rethinking sparse latent representation for vision-based semantic occupancy prediction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 15035\u201315044.","DOI":"10.1109\/CVPR52733.2024.01424"},{"key":"10.1016\/j.patcog.2026.114340_b11","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9297","article-title":"Semantickitti: A dataset for semantic scene understanding of lidar sequences","author":"Behley","year":"2019"},{"key":"10.1016\/j.patcog.2026.114340_b12","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11621","article-title":"nuscenes: A multimodal dataset for autonomous driving","author":"Caesar","year":"2020"},{"key":"10.1016\/j.patcog.2026.114340_b13","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, 2023, pp. 17850\u201317859.","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"10.1016\/j.patcog.2026.114340_b14","doi-asserted-by":"crossref","first-page":"64318","DOI":"10.52202\/075280-2809","article-title":"Occ3d: A large-scale 3D occupancy prediction benchmark for autonomous driving","volume":"36","author":"Tian","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114340_b15","first-page":"7374","article-title":"Drivingforward: Feed-forward 3D gaussian splatting for driving scene reconstruction from flexible surround-view input","volume":"vol. 39","author":"Tian","year":"2025"},{"key":"10.1016\/j.patcog.2026.114340_b16","series-title":"S2GS: Streaming semantic Gaussian splatting for online scene understanding and reconstruction","author":"Zhang","year":"2026"},{"key":"10.1016\/j.patcog.2026.114340_b17","first-page":"4248","article-title":"Human motion synthesis in 3D scenes via unified scene semantic occupancy","volume":"vol. 40","author":"Gong","year":"2026"},{"key":"10.1016\/j.patcog.2026.114340_b18","first-page":"18683","article-title":"Zero-shot robotic manipulation via 3D Gaussian splatting-enhanced multimodal retrieval-augmented generation","volume":"vol. 40","author":"Xie","year":"2026"},{"issue":"3","key":"10.1016\/j.patcog.2026.114340_b19","article-title":"Confusing object detection: A survey","volume":"80","author":"Tong","year":"2024","journal-title":"Comput. Mater. Contin."},{"issue":"1","key":"10.1016\/j.patcog.2026.114340_b20","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s44267-025-00099-6","article-title":"Efficient multimodal large language models: A survey","volume":"3","author":"Jin","year":"2025","journal-title":"Vis. Intell."},{"key":"10.1016\/j.patcog.2026.114340_b21","article-title":"Efficient vision-based occupancy prediction with knowledge distillation","author":"Ke","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114340_b22","doi-asserted-by":"crossref","unstructured":"A.-Q. Cao, R. De Charette, Monoscene: Monocular 3D semantic scene completion, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 3991\u20134001.","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"10.1016\/j.patcog.2026.114340_b23","doi-asserted-by":"crossref","unstructured":"Y. Li, Z. Yu, C. Choy, C. Xiao, J.M. Alvarez, S. Fidler, C. Feng, A. Anandkumar, Voxformer: Sparse voxel transformer for camera-based 3D semantic scene completion, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9087\u20139098.","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"10.1016\/j.patcog.2026.114340_b24","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, 2023, pp. 9433\u20139443.","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"10.1016\/j.patcog.2026.114340_b25","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"9565","article-title":"Inversematrixvt3d: An efficient projection matrix-based approach for 3D occupancy prediction","author":"Ming","year":"2024"},{"key":"10.1016\/j.patcog.2026.114340_b26","series-title":"3D occupancy prediction with low-resolution queries via prototype-aware view transformation","author":"Oh","year":"2025"},{"key":"10.1016\/j.patcog.2026.114340_b27","article-title":"Decoupling 3-D point cloud attributes for semantic segmentation via real-world prior exploitation","author":"Zhang","year":"2026","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patcog.2026.114340_b28","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.patcog.2018.03.003","article-title":"Deep super-class learning for long-tail distributed image classification","volume":"80","author":"Zhou","year":"2018","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114340_b29","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16","first-page":"728","article-title":"The devil is in classification: A simple framework for long-tail instance segmentation","author":"Wang","year":"2020"},{"key":"10.1016\/j.patcog.2026.114340_b30","doi-asserted-by":"crossref","unstructured":"S. Alshammari, Y.-X. Wang, D. Ramanan, S. Kong, Long-tailed recognition via weight balancing, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 6897\u20136907.","DOI":"10.1109\/CVPR52688.2022.00677"},{"key":"10.1016\/j.patcog.2026.114340_b31","series-title":"Decoupling representation and classifier for long-tailed recognition","author":"Kang","year":"2019"},{"key":"10.1016\/j.patcog.2026.114340_b32","unstructured":"S. Sun, H. Lu, J. Li, Y. Xie, T. Li, X. Yang, L. Zhang, J. Yan, Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can Balance, in: The Thirteenth International Conference on Learning Representations."},{"key":"10.1016\/j.patcog.2026.114340_b33","doi-asserted-by":"crossref","unstructured":"S. Wang, J. Yu, W. Li, W. Liu, X. Liu, J. Chen, J. Zhu, Not all voxels are equal: Hardness-aware semantic scene completion with self-distillation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 14792\u201314801.","DOI":"10.1109\/CVPR52733.2024.01401"},{"key":"10.1016\/j.patcog.2026.114340_b34","doi-asserted-by":"crossref","unstructured":"Z. Zhong, J. Cui, S. Liu, J. Jia, Improving calibration for long-tailed recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 16489\u201316498.","DOI":"10.1109\/CVPR46437.2021.01622"},{"key":"10.1016\/j.patcog.2026.114340_b35","series-title":"2020 International Conference on 3D Vision (3DV)","first-page":"111","article-title":"Lmscnet: Lightweight multiscale 3D semantic completion","author":"Roldao","year":"2020"},{"key":"10.1016\/j.patcog.2026.114340_b36","doi-asserted-by":"crossref","unstructured":"J. Li, K. Han, P. Wang, Y. Liu, X. Yuan, Anisotropic convolutional networks for 3D semantic scene completion, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3351\u20133359.","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"10.1016\/j.patcog.2026.114340_b37","first-page":"3101","article-title":"Sparse single sweep lidar point cloud segmentation via learning contextual shape priors from scene completion","volume":"vol. 35","author":"Yan","year":"2021"},{"key":"10.1016\/j.patcog.2026.114340_b38","doi-asserted-by":"crossref","unstructured":"H. Jiang, T. Cheng, N. Gao, H. Zhang, T. Lin, W. Liu, X. Wang, Symphonize 3D semantic scene completion with contextual instance queries, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 20258\u201320267.","DOI":"10.1109\/CVPR52733.2024.01915"},{"key":"10.1016\/j.patcog.2026.114340_b39","doi-asserted-by":"crossref","unstructured":"Y. Cui, M. Jia, T.-Y. Lin, Y. Song, S. Belongie, Class-balanced loss based on effective number of samples, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 9268\u20139277.","DOI":"10.1109\/CVPR.2019.00949"},{"key":"10.1016\/j.patcog.2026.114340_b40","doi-asserted-by":"crossref","unstructured":"Z. Liu, Z. Miao, X. Zhan, J. Wang, B. Gong, S.X. Yu, Large-scale long-tailed recognition in an open world, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 2537\u20132546.","DOI":"10.1109\/CVPR.2019.00264"},{"key":"10.1016\/j.patcog.2026.114340_b41","series-title":"BEVFormer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers","author":"Li","year":"2022"},{"key":"10.1016\/j.patcog.2026.114340_b42","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, 2023, pp. 21729\u201321740.","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"10.1016\/j.patcog.2026.114340_b43","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, 2023, pp. 6919\u20136928.","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"10.1016\/j.patcog.2026.114340_b44","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, 2024, pp. 17158\u201317168.","DOI":"10.1109\/CVPR52733.2024.01624"},{"key":"10.1016\/j.patcog.2026.114340_b45","article-title":"Occnerf: Advancing 3D occupancy prediction in lidar-free environments","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114340_b46","first-page":"4284","article-title":"ProtoOcc: Accurate, efficient 3D occupancy prediction using dual branch encoder-prototype query decoder","volume":"vol. 39","author":"Kim","year":"2025"},{"key":"10.1016\/j.patcog.2026.114340_b47","series-title":"STCOcc: Sparse spatial-temporal cascade renovation for 3D occupancy and scene flow prediction","author":"Liao","year":"2025"},{"key":"10.1016\/j.patcog.2026.114340_b48","series-title":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4213","article-title":"Rangenet++: Fast and accurate lidar semantic segmentation","author":"Milioto","year":"2019"},{"key":"10.1016\/j.patcog.2026.114340_b49","doi-asserted-by":"crossref","unstructured":"Y. Zhang, Z. Zhou, P. David, X. Yue, Z. Xi, B. Gong, H. Foroosh, Polarnet: An improved grid representation for online lidar point clouds semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9601\u20139610.","DOI":"10.1109\/CVPR42600.2020.00962"},{"key":"10.1016\/j.patcog.2026.114340_b50","series-title":"Advances in Visual Computing: 15th International Symposium, ISVC 2020, San Diego, CA, USA, October 5\u20137, 2020, Proceedings, Part II 15","first-page":"207","article-title":"Salsanext: Fast, uncertainty-aware semantic segmentation of lidar point clouds","author":"Cortinhal","year":"2020"},{"key":"10.1016\/j.patcog.2026.114340_b51","doi-asserted-by":"crossref","unstructured":"X. Zhu, H. Zhou, T. Wang, F. Hong, Y. Ma, W. Li, H. Li, D. Lin, Cylindrical and asymmetrical 3D convolution networks for lidar segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 9939\u20139948.","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"10.1016\/j.patcog.2026.114340_b52","doi-asserted-by":"crossref","unstructured":"J. Xu, R. Zhang, J. Dou, Y. Zhu, J. Sun, S. Pu, Rpvnet: A deep and efficient range-point-voxel fusion network for lidar point cloud segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 16024\u201316033.","DOI":"10.1109\/ICCV48922.2021.01572"},{"key":"10.1016\/j.patcog.2026.114340_b53","doi-asserted-by":"crossref","unstructured":"Y. Wang, J. Fei, H. Wang, W. Li, T. Bao, L. Wu, R. Zhao, Y. Shen, Balancing logit variation for long-tailed semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19561\u201319573.","DOI":"10.1109\/CVPR52729.2023.01874"},{"key":"10.1016\/j.patcog.2026.114340_b54","doi-asserted-by":"crossref","unstructured":"B. Li, Y. Yao, J. Tan, G. Zhang, F. Yu, J. Lu, Y. Luo, Equalized focal loss for dense long-tailed object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 6990\u20136999.","DOI":"10.1109\/CVPR52688.2022.00686"},{"key":"10.1016\/j.patcog.2026.114340_b55","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Doll\u00e1r, Focal loss for dense object detection, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013051?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013051?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T08:48:15Z","timestamp":1787215695000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326013051"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":55,"alternative-id":["S0031320326013051"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114340","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SHTOcc: Effective 3D occupancy prediction with sparse head and tail voxels","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114340","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114340"}}