{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:22:21Z","timestamp":1783056141781,"version":"3.54.6"},"reference-count":93,"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\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372377"],"award-info":[{"award-number":["62372377"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502171"],"award-info":[{"award-number":["62502171"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.jvcir.2026.104841","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:02:56Z","timestamp":1779688976000},"page":"104841","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Rethinking the refinement stage of 3D object detection: A multi-task learning perspective with Mixture-of-Experts"],"prefix":"10.1016","volume":"118","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9894-8017","authenticated-orcid":false,"given":"Bingqian","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siwen","family":"Quan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chu\u2019ai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104841_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2025.104624","article-title":"A multi-modal 3D object detection framework based on enhanced Convolution, mixed Sampling, and Image-Point cloud bidirectional fusion","author":"Zhou","year":"2025","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104841_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2023.103805","article-title":"LiDAR-only 3D object detection based on spatial context","volume":"93","author":"Wang","year":"2023","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104841_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2022.103634","article-title":"ETS-3D: An efficient two-stage framework for stereo 3D object detection","volume":"88","author":"Ji","year":"2022","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104841_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2025.104555","article-title":"Fusing depth embeddings for monocular 3D object detection","author":"Ji","year":"2025","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"13","key":"10.1016\/j.jvcir.2026.104841_b5","doi-asserted-by":"crossref","first-page":"14795","DOI":"10.1109\/JSEN.2023.3279500","article-title":"3-D objects detection and tracking using solid-state LiDAR and RGB camera","volume":"23","author":"Peng","year":"2023","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.jvcir.2026.104841_b6","doi-asserted-by":"crossref","unstructured":"S. Shi, X. Wang, H. Li, Pointrcnn: 3d object proposal generation and detection from point cloud, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 770\u2013779.","DOI":"10.1109\/CVPR.2019.00086"},{"key":"10.1016\/j.jvcir.2026.104841_b7","doi-asserted-by":"crossref","unstructured":"S. Shi, C. Guo, L. Jiang, Z. Wang, J. Shi, X. Wang, H. Li, Pv-rcnn: Point-voxel feature set abstraction for 3d object detection, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10529\u201310538.","DOI":"10.1109\/CVPR42600.2020.01054"},{"issue":"2","key":"10.1016\/j.jvcir.2026.104841_b8","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1007\/s11263-022-01710-9","article-title":"PV-RCNN++: Point-voxel feature set abstraction with local vector representation for 3D object detection","volume":"131","author":"Shi","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104841_b9","doi-asserted-by":"crossref","unstructured":"J. Deng, S. Shi, P. Li, W. Zhou, Y. Zhang, H. Li, Voxel r-cnn: Towards high performance voxel-based 3d object detection, in: Proc. AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 1201\u20131209.","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"10.1016\/j.jvcir.2026.104841_b10","doi-asserted-by":"crossref","unstructured":"T. Wang, X. Zhu, J. Pang, D. Lin, Fcos3d: Fully convolutional one-stage monocular 3d object detection, in: Proc. IEEE\/CVF International Conference on Computer Vision, 2021, pp. 913\u2013922.","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"10.1016\/j.jvcir.2026.104841_b11","doi-asserted-by":"crossref","first-page":"34899","DOI":"10.52202\/068431-2529","article-title":"Fully convolutional one-stage 3d object detection on lidar range images","volume":"35","author":"Tian","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104841_b12","series-title":"Afdet: Anchor free one stage 3d object detection","author":"Ge","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104841_b13","doi-asserted-by":"crossref","unstructured":"Z. Miao, J. Chen, H. Pan, R. Zhang, K. Liu, P. Hao, J. Zhu, Y. Wang, X. Zhan, Pvgnet: A bottom-up one-stage 3d object detector with integrated multi-level features, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 3279\u20133288.","DOI":"10.1109\/CVPR46437.2021.00329"},{"key":"10.1016\/j.jvcir.2026.104841_b14","doi-asserted-by":"crossref","unstructured":"Z. Yang, Y. Sun, S. Liu, J. Jia, 3dssd: Point-based 3d single stage object detector, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11040\u201311048.","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"10.1016\/j.jvcir.2026.104841_b15","doi-asserted-by":"crossref","unstructured":"C. He, H. Zeng, J. Huang, X.-S. Hua, L. Zhang, Structure aware single-stage 3d object detection from point cloud, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11873\u201311882.","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"10.1016\/j.jvcir.2026.104841_b16","doi-asserted-by":"crossref","unstructured":"Y. Zhang, D. Huang, Y. Wang, PC-RGNN: Point cloud completion and graph neural network for 3D object detection, in: Proc. AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 3430\u20133437.","DOI":"10.1609\/aaai.v35i4.16456"},{"key":"10.1016\/j.jvcir.2026.104841_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108684","article-title":"Spatial information enhancement network for 3D object detection from point cloud","volume":"128","author":"Li","year":"2022","journal-title":"Pattern Recognit."},{"issue":"11","key":"10.1016\/j.jvcir.2026.104841_b18","doi-asserted-by":"crossref","first-page":"7217","DOI":"10.1109\/TPAMI.2024.3392303","article-title":"Fully sparse fusion for 3d object detection","volume":"46","author":"Li","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2026.104841_b19","series-title":"Part-a2 net: 3d part-aware and aggregation neural network for object detection from point cloud","author":"Shi","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104841_b20","first-page":"1","article-title":"CasA: A cascade attention network for 3-D object detection from LiDAR point clouds","volume":"60","author":"Wu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"12","key":"10.1016\/j.jvcir.2026.104841_b21","doi-asserted-by":"crossref","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","article-title":"A survey on multi-task learning","volume":"34","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.jvcir.2026.104841_b22","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.jvcir.2026.104841_b23","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1109\/JAS.2022.106004","article-title":"A survey on negative transfer","volume":"10","author":"Zhang","year":"2022","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.jvcir.2026.104841_b24","doi-asserted-by":"crossref","unstructured":"A. Kendall, Y. Gal, R. Cipolla, Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 7482\u20137491.","DOI":"10.1109\/CVPR.2018.00781"},{"key":"10.1016\/j.jvcir.2026.104841_b25","doi-asserted-by":"crossref","unstructured":"B. Li, Y. Liu, X. Wang, Gradient harmonized single-stage detector, in: Proc. AAAI Conference on Artificial Intelligence, Vol. 33, 2019, pp. 8577\u20138584.","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"10.1016\/j.jvcir.2026.104841_b26","article-title":"The evolution of moe: A survey from basics to breakthroughs","author":"Vats","year":"2024","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.jvcir.2026.104841_b27","doi-asserted-by":"crossref","unstructured":"J. Xu, L. Sun, D. Zhao, MoME: Mixture-of-masked-experts for efficient multi-task recommendation, in: Proc. International ACM SIGIR Conference on Research and Development in Information Retrieval, 2024, pp. 2527\u20132531.","DOI":"10.1145\/3626772.3657922"},{"key":"10.1016\/j.jvcir.2026.104841_b28","doi-asserted-by":"crossref","unstructured":"Z. Li, F. Wang, N. Wang, Lidar r-cnn: An efficient and universal 3d object detector, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7546\u20137555.","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"10.1016\/j.jvcir.2026.104841_b29","series-title":"3D cascade rcnn: High quality object detection in point clouds","author":"Cai","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104841_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2022.102322","article-title":"Deformable pyramid r-cnn for 3d object detection","volume":"75","author":"Hou","year":"2022","journal-title":"Displays"},{"key":"10.1016\/j.jvcir.2026.104841_b31","article-title":"ASCFormer: An adaptive structure-aware cascaded transformer for 3d object detection","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104841_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112156","article-title":"OV-GT3D: A generalizable open-vocabulary two-stage 3D detector with dual path distillation","volume":"171","author":"Sun","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.jvcir.2026.104841_b33","doi-asserted-by":"crossref","first-page":"9410","DOI":"10.1109\/TMM.2024.3391899","article-title":"General deformable RoI pooling and semi-decoupled head for object detection","volume":"26","author":"Han","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.jvcir.2026.104841_b34","article-title":"Progressive semi-decoupled detector for accurate object detection","author":"Han","year":"2025","journal-title":"IEEE Trans. Multimed."},{"issue":"3","key":"10.1016\/j.jvcir.2026.104841_b35","doi-asserted-by":"crossref","first-page":"1643","DOI":"10.1007\/s13042-024-02357-3","article-title":"YOLO-SDH: improved YOLOv5 using scaled decoupled head for object detection","volume":"16","author":"Ren","year":"2025","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"10.1016\/j.jvcir.2026.104841_b36","series-title":"Proc. Chinese Control Conference","first-page":"8386","article-title":"Decoupling classification and localization for single stage 3D vehicle detection from point clouds","author":"He","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104841_b37","series-title":"Proc. IEEE International Conference on Multimedia and Expo","first-page":"1133","article-title":"Feature decoupling and uncertainty estimation for 3d object detection","author":"Zhi","year":"2023"},{"issue":"10","key":"10.1016\/j.jvcir.2026.104841_b38","doi-asserted-by":"crossref","first-page":"10134","DOI":"10.1109\/TCSVT.2025.3563083","article-title":"Dynamic learnable label assignment for indoor 3D object detection","volume":"35","author":"Liu","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104841_b39","article-title":"AFES: Attention-based feature excitation and sorting for action recognition","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.jvcir.2026.104841_b40","doi-asserted-by":"crossref","DOI":"10.1109\/TII.2024.3431044","article-title":"Ef-detr: A lightweight transformer-based object detector with an encoder-free neck","author":"Cheng","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.jvcir.2026.104841_b41","doi-asserted-by":"crossref","unstructured":"C. Shi, C. Zhang, Y. Luo, Structure guided proposal completion for 3D object detection, in: Proc. Asian Conference on Computer Vision, 2022, pp. 4462\u20134478.","DOI":"10.1007\/978-3-031-26319-4_30"},{"key":"10.1016\/j.jvcir.2026.104841_b42","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1109\/LSP.2024.3503359","article-title":"Geometry-guided point generation for 3d object detection","volume":"32","author":"Wang","year":"2025","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.jvcir.2026.104841_b43","doi-asserted-by":"crossref","unstructured":"X. Wu, L. Peng, H. Yang, L. Xie, C. Huang, C. Deng, H. Liu, D. Cai, Sparse fuse dense: Towards high quality 3d detection with depth completion, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5418\u20135427.","DOI":"10.1109\/CVPR52688.2022.00534"},{"key":"10.1016\/j.jvcir.2026.104841_b44","series-title":"Proc. Conference on Robot Learning","first-page":"146","article-title":"Hdnet: Exploiting hd maps for 3d object detection","author":"Yang","year":"2018"},{"key":"10.1016\/j.jvcir.2026.104841_b45","doi-asserted-by":"crossref","DOI":"10.1109\/TII.2025.3588622","article-title":"GAANet: Graph aggregation alignment feature fusion for multispectral object detection","author":"Zheng","year":"2025","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.jvcir.2026.104841_b46","article-title":"COFNet: contrastive object-aware fusion using box-level masks for multispectral object detection","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Multimed."},{"issue":"4","key":"10.1016\/j.jvcir.2026.104841_b47","first-page":"1","article-title":"Robust rgb-t tracking via adaptive modality weight correlation filters and cross-modality learning","volume":"20","author":"Zhou","year":"2023","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.jvcir.2026.104841_b48","article-title":"Boundary-aware feature fusion with dual-stream attention for remote sensing small object detection","author":"Song","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104841_b49","doi-asserted-by":"crossref","unstructured":"A. Liang, L. Kong, D. Lu, Y. Liu, J. Fang, H. Zhao, W.T. Ooi, Perspective-invariant 3D object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2025, pp. 27725\u201327738.","DOI":"10.1109\/ICCV51701.2025.02574"},{"issue":"1","key":"10.1016\/j.jvcir.2026.104841_b50","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1093\/nsr\/nwx105","article-title":"An overview of multi-task learning","volume":"5","author":"Zhang","year":"2018","journal-title":"Natl. Sci. Rev."},{"key":"10.1016\/j.jvcir.2026.104841_b51","series-title":"Gradient vaccine: Investigating and improving multi-task optimization in massively multilingual models","author":"Wang","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104841_b52","series-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017"},{"issue":"120","key":"10.1016\/j.jvcir.2026.104841_b53","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.jvcir.2026.104841_b54","doi-asserted-by":"crossref","unstructured":"J. Ma, Z. Zhao, X. Yi, J. Chen, L. Hong, E.H. Chi, Modeling task relationships in multi-task learning with multi-gate mixture-of-experts, in: Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2018, pp. 1930\u20131939.","DOI":"10.1145\/3219819.3220007"},{"key":"10.1016\/j.jvcir.2026.104841_b55","series-title":"Towards accurate and efficient 3D object detection for autonomous driving: A mixture of experts computing system on edge","author":"Liu","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104841_b56","doi-asserted-by":"crossref","unstructured":"W. Shen, M. Zhou, Y. Chen, X. Wei, Y. Feng, H. Pu, W. Jia, Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inference, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 17990\u201317999.","DOI":"10.1109\/CVPR52734.2025.01676"},{"key":"10.1016\/j.jvcir.2026.104841_b57","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2025.3586106","article-title":"No-reference image quality assessment: Exploring intrinsic distortion characteristics via generative noise estimation with mamba","author":"Lan","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"10.1016\/j.jvcir.2026.104841_b58","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1109\/TBC.2022.3215249","article-title":"An end-to-end blind image quality assessment method using a recurrent network and self-attention","volume":"69","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.jvcir.2026.104841_b59","first-page":"1","article-title":"Blind image quality assessment: Exploring content fidelity perceptibility via quality adversarial learning","author":"Zhou","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104841_b60","article-title":"Image quality assessment: Exploring the similarity of deep features via covariance-constrained spectra","author":"Lang","year":"2025","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.jvcir.2026.104841_b61","doi-asserted-by":"crossref","unstructured":"P. Gong, J. Ye, C. Zhang, Robust multi-task feature learning, in: Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2012, pp. 895\u2013903.","DOI":"10.1145\/2339530.2339672"},{"key":"10.1016\/j.jvcir.2026.104841_b62","series-title":"MTLComb: multi-task learning combining regression and classification tasks for joint feature selection","author":"Cao","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104841_b63","doi-asserted-by":"crossref","unstructured":"J. Liu, P. Cui, Data Heterogeneity Modeling for Trustworthy Machine Learning, in: Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2025, pp. 6086\u20136095.","DOI":"10.1145\/3711896.3736560"},{"key":"10.1016\/j.jvcir.2026.104841_b64","doi-asserted-by":"crossref","first-page":"1182","DOI":"10.3389\/fnins.2019.01182","article-title":"Divide and conquer: stratifying training data by tumor grade improves deep learning-based brain tumor segmentation","volume":"13","author":"Rebsamen","year":"2019","journal-title":"Front. Neurosci."},{"key":"10.1016\/j.jvcir.2026.104841_b65","series-title":"Ensemble Learning techniques for object detection in high-resolution satellite images","author":"Vilhelm","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104841_b66","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.107098","article-title":"Multi-model ensemble with rich spatial information for object detection","volume":"99","author":"Xu","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.jvcir.2026.104841_b67","series-title":"Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3354","article-title":"Are we ready for autonomous driving? the kitti vision benchmark suite","author":"Geiger","year":"2012"},{"key":"10.1016\/j.jvcir.2026.104841_b68","doi-asserted-by":"crossref","unstructured":"P. Sun, H. Kretzschmar, X. Dotiwalla, A. Chouard, V. Patnaik, P. Tsui, J. Guo, Y. Zhou, Y. Chai, B. Caine, et al., Scalability in perception for autonomous driving: Waymo open dataset, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 2446\u20132454.","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"10.1016\/j.jvcir.2026.104841_b69","doi-asserted-by":"crossref","unstructured":"S. Liu, M. Cui, B. Li, Q. Liang, T. Hong, K. Huang, Y. Shan, FSHNet: Fully Sparse Hybrid Network for 3D Object Detection, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2025, pp. 8900\u20138909.","DOI":"10.1109\/CVPR52734.2025.00832"},{"issue":"10","key":"10.1016\/j.jvcir.2026.104841_b70","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.jvcir.2026.104841_b71","doi-asserted-by":"crossref","unstructured":"A.H. Lang, S. Vora, H. Caesar, L. Zhou, J. Yang, O. Beijbom, Pointpillars: Fast encoders for object detection from point clouds, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 12697\u201312705.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"10.1016\/j.jvcir.2026.104841_b72","series-title":"Proc. European Conference on Computer Vision","first-page":"35","article-title":"Epnet: Enhancing point features with image semantics for 3d object detection","author":"Huang","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104841_b73","series-title":"Proc. IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"10386","article-title":"CLOCs: Camera-LiDAR object candidates fusion for 3D object detection","author":"Pang","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104841_b74","doi-asserted-by":"crossref","unstructured":"W. Zheng, W. Tang, L. Jiang, C.-W. Fu, SE-SSD: Self-ensembling single-stage object detector from point cloud, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14494\u201314503.","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"10.1016\/j.jvcir.2026.104841_b75","doi-asserted-by":"crossref","unstructured":"Y. Chen, Y. Li, X. Zhang, J. Sun, J. Jia, Focal sparse convolutional networks for 3d object detection, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5428\u20135437.","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"10.1016\/j.jvcir.2026.104841_b76","doi-asserted-by":"crossref","unstructured":"Y. Li, X. Qi, Y. Chen, L. Wang, Z. Li, J. Sun, J. Jia, Voxel field fusion for 3d object detection, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1120\u20131129.","DOI":"10.1109\/CVPR52688.2022.00119"},{"key":"10.1016\/j.jvcir.2026.104841_b77","doi-asserted-by":"crossref","unstructured":"J.S. Hu, T. Kuai, S.L. Waslander, Point density-aware voxels for lidar 3d object detection, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8469\u20138478.","DOI":"10.1109\/CVPR52688.2022.00828"},{"key":"10.1016\/j.jvcir.2026.104841_b78","series-title":"Boosting 3D object detection with semantic-aware multi-branch framework","author":"Jing","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104841_b79","doi-asserted-by":"crossref","DOI":"10.1109\/TITS.2025.3568418","article-title":"Fade3D: Fast and deployable 3D object detection for autonomous driving","author":"Ye","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.jvcir.2026.104841_b80","series-title":"Enhancing LiDAR point features with foundation model priors for 3D object detection","author":"Mo","year":"2025"},{"issue":"5","key":"10.1016\/j.jvcir.2026.104841_b81","doi-asserted-by":"crossref","first-page":"7126","DOI":"10.1109\/JSEN.2024.3350770","article-title":"TSSTDet: Transformation-based 3-D object detection via a spatial shape transformer","volume":"24","author":"Hoang","year":"2024","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.jvcir.2026.104841_b82","doi-asserted-by":"crossref","unstructured":"Z. Yu, B. Qiu, A.W. Khong, ViKIENet: Towards efficient 3D object detection with virtual key instance enhanced network, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2025, pp. 11844\u201311853.","DOI":"10.1109\/CVPR52734.2025.01106"},{"key":"10.1016\/j.jvcir.2026.104841_b83","doi-asserted-by":"crossref","unstructured":"T. Yin, X. Zhou, P. Krahenbuhl, Center-based 3d object detection and tracking, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 11784\u201311793.","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"10.1016\/j.jvcir.2026.104841_b84","doi-asserted-by":"crossref","unstructured":"J. Li, C. Luo, X. Yang, PillarNeXt: Rethinking network designs for 3D object detection in LiDAR point clouds, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 17567\u201317576.","DOI":"10.1109\/CVPR52729.2023.01685"},{"key":"10.1016\/j.jvcir.2026.104841_b85","doi-asserted-by":"crossref","unstructured":"H. Wang, C. Shi, S. Shi, M. Lei, S. Wang, D. He, B. Schiele, L. Wang, Dsvt: Dynamic sparse voxel transformer with rotated sets, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 13520\u201313529.","DOI":"10.1109\/CVPR52729.2023.01299"},{"key":"10.1016\/j.jvcir.2026.104841_b86","series-title":"Dcdet: Dynamic cross-based 3d object detector","author":"Liu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104841_b87","doi-asserted-by":"crossref","first-page":"53076","DOI":"10.52202\/075280-2309","article-title":"Hednet: A hierarchical encoder-decoder network for 3d object detection in point clouds","volume":"36","author":"Zhang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104841_b88","series-title":"Proc. European Conference on Computer Vision","first-page":"74","article-title":"Scatterformer: Efficient voxel transformer with scattered linear attention","author":"He","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104841_b89","doi-asserted-by":"crossref","first-page":"81489","DOI":"10.52202\/079017-2590","article-title":"Voxel mamba: Group-free state space models for point cloud based 3d object detection","volume":"37","author":"Zhang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104841_b90","doi-asserted-by":"crossref","unstructured":"X. Jin, H. Su, K. Liu, C. Ma, W. Wu, F. Hui, J. Yan, UniMamba: Unified spatial-channel representation learning with group-efficient mamba for LiDAR-based 3D object detection, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2025, pp. 1407\u20131417.","DOI":"10.1109\/CVPR52734.2025.00139"},{"key":"10.1016\/j.jvcir.2026.104841_b91","series-title":"FALO: Fast and accurate LiDAR 3D object detection on resource-constrained devices","author":"Han","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104841_b92","doi-asserted-by":"crossref","unstructured":"X. Jin, H. Su, C. Ma, K. Liu, W. Wu, F. Hui, J. Yan, GeoFormer: Geometry point encoder for 3D object detection with graph-based transformer, in: Proc. IEEE\/CVF International Conference on Computer Vision, 2025, pp. 26879\u201326889.","DOI":"10.1109\/ICCV51701.2025.02495"},{"key":"10.1016\/j.jvcir.2026.104841_b93","series-title":"Yolov4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001367?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001367?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:06:48Z","timestamp":1783055208000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326001367"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":93,"alternative-id":["S1047320326001367"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104841","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Rethinking the refinement stage of 3D object detection: A multi-task learning perspective with Mixture-of-Experts","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104841","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104841"}}