{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:13:38Z","timestamp":1782317618866,"version":"3.54.5"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["2020YFB0204500"],"award-info":[{"award-number":["2020YFB0204500"]}],"id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2021JZ-21"],"award-info":[{"award-number":["2021JZ-21"]}],"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":["62271297"],"award-info":[{"award-number":["62271297"]}],"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":["12271324"],"award-info":[{"award-number":["12271324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s00371-023-02860-8","type":"journal-article","created":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T08:01:27Z","timestamp":1682928087000},"page":"1453-1466","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["MVTr: multi-feature voxel transformer for 3D object detection"],"prefix":"10.1007","volume":"40","author":[{"given":"Lingmei","family":"Ai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoyu","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruoxia","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,5,1]]},"reference":[{"key":"2860_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2021.103193","volume":"119","author":"C Benedek","year":"2021","unstructured":"Benedek, C., Majdik, A., Nagy, B., Rozsa, Z., Sziranyi, T.: Positioning and perception in LIDAR point clouds. Digital Signal Process. 119, 103193 (2021). https:\/\/doi.org\/10.1016\/j.dsp.2021.103193","journal-title":"Digital Signal Process."},{"key":"2860_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2021.103138","volume":"117","author":"Y Cui","year":"2021","unstructured":"Cui, Y., Yu, M., Jiang, Z., Peng, Z., Chen, F.: Blind light field image quality assessment by analyzing angular-spatial characteristics. Digital Signal Process. 117, 103138 (2021). https:\/\/doi.org\/10.1016\/j.dsp.2021.103138","journal-title":"Digital Signal Process."},{"key":"2860_CR3","doi-asserted-by":"publisher","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: Std: Sparse-to-dense 3d object detector for point cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1951\u20131960 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00204","DOI":"10.1109\/ICCV.2019.00204"},{"key":"2860_CR4","doi-asserted-by":"publisher","unstructured":"Shi, S., Wang, X., Li, H.: Pointrcnn: 3d object proposal generation and detection from point cloud. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 770\u2013779 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00086","DOI":"10.1109\/CVPR.2019.00086"},{"key":"2860_CR5","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.neucom.2019.09.086","volume":"379","author":"Y Ye","year":"2020","unstructured":"Ye, Y., Chen, H., Zhang, C., Hao, X., Zhang, Z.: Sarpnet: shape attention regional proposal network for lidar-based 3d object detection. Neurocomputing 379, 53\u201363 (2020). https:\/\/doi.org\/10.1016\/j.neucom.2019.09.086","journal-title":"Neurocomputing"},{"key":"2860_CR6","doi-asserted-by":"publisher","unstructured":"Wang, L., Wang, C., Zhang, X., Lan, T., Li, J.: S-AT GCN: Spatial-Attention Graph Convolution Network based Feature Enhancement for 3D Object Detection. arXiv preprint arXiv:2103.08439 (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.08439","DOI":"10.48550\/arXiv.2103.08439"},{"key":"2860_CR7","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: End-to-end learning for point cloud based 3d object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4490\u20134499 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00472","DOI":"10.1109\/CVPR.2018.00472"},{"key":"2860_CR8","doi-asserted-by":"publisher","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: Fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12697-12705 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01298","DOI":"10.1109\/CVPR.2019.01298"},{"issue":"10","key":"2860_CR9","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018). https:\/\/doi.org\/10.3390\/s18103337","journal-title":"Sensors"},{"issue":"8","key":"2860_CR10","doi-asserted-by":"publisher","first-page":"2647","DOI":"10.1109\/TPAMI.2020.2977026","volume":"43","author":"S Shi","year":"2020","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network. IEEE Trans. Pattern Anal. Mach. Intell. 43(8), 2647\u20132664 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2020.2977026","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2860_CR11","doi-asserted-by":"publisher","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3d object detection network for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907\u20131915 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.691","DOI":"10.1109\/CVPR.2017.691"},{"key":"2860_CR12","doi-asserted-by":"publisher","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3d proposal generation and object detection from view aggregation. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 1\u20138 (2018). https:\/\/doi.org\/10.1109\/IROS.2018.8594049","DOI":"10.1109\/IROS.2018.8594049"},{"key":"2860_CR13","doi-asserted-by":"publisher","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3d object detection from rgb-d data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00102","DOI":"10.1109\/CVPR.2018.00102"},{"key":"2860_CR14","doi-asserted-by":"publisher","unstructured":"Beltr\u00e1n, J., Guindel, C., Moreno, F.M., Cruzado, D., Garcia, F., De La Escalera, A.: Birdnet: a 3d object detection framework from lidar information. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), IEEE, pp. 3517\u20133523 (2018). https:\/\/doi.org\/10.1109\/ITSC.2018.8569311","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"2860_CR15","doi-asserted-by":"publisher","unstructured":"Chen, L., Wan, L.: CTUNet: automatic pancreas segmentation using a channel-wise transformer and 3D U-Net, The Visual Computer, pp. 1\u201315 (2022). https:\/\/doi.org\/10.1007\/s00371-022-02656-2","DOI":"10.1007\/s00371-022-02656-2"},{"key":"2860_CR16","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End Object Detection with Transformers. In: European Conference on Computer Vision, Springer, pp. 213\u2013229 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2860_CR17","doi-asserted-by":"publisher","unstructured":"Zhang, Q., Ge, Y., Zhang, C., Bi, H.: TPRNet: camouflaged object detection via transformer-induced progressive refinement network. Vis. Comput., pp. 1\u201315 (2022). https:\/\/doi.org\/10.1007\/s00371-022-02611-1","DOI":"10.1007\/s00371-022-02611-1"},{"key":"2860_CR18","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"issue":"3","key":"2860_CR19","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/s00371-018-1471-4","volume":"35","author":"X Zhou","year":"2019","unstructured":"Zhou, X., Wang, Y., Zhu, Q., Xiao, C., Lu, X.: Ssg: superpixel segmentation and grabcut-based salient object segmentation. Vis. Comput. 35(3), 385\u2013398 (2019). https:\/\/doi.org\/10.1007\/s00371-018-1471-4","journal-title":"Vis. Comput."},{"key":"2860_CR20","doi-asserted-by":"publisher","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9404\u20139413 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00963","DOI":"10.1109\/CVPR.2019.00963"},{"key":"2860_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2021.103283","volume":"120","author":"X Li","year":"2022","unstructured":"Li, X., Chen, D.: A survey on deep learning-based panoptic segmentation. Digital Signal Process. 120, 103283 (2022). https:\/\/doi.org\/10.1016\/j.dsp.2021.103283","journal-title":"Digital Signal Process."},{"key":"2860_CR22","doi-asserted-by":"publisher","unstructured":"Gu, W., Bai, S., Kong, L.: A review on 2D instance segmentation based on deep neural networks. Image Vis. Comput., p. 104401 (2022). https:\/\/doi.org\/10.1016\/j.imavis.2022.104401","DOI":"10.1016\/j.imavis.2022.104401"},{"key":"2860_CR23","doi-asserted-by":"publisher","unstructured":"Geiger, A., Lenz, P., Urtasun, R., Are we ready for autonomous driving? The kitti vision benchmark suite. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp. 3354\u20133361 (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2860_CR24","doi-asserted-by":"publisher","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.16","DOI":"10.1109\/CVPR.2017.16"},{"key":"2860_CR25","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inf Process. syst., 30 (2017). paper\/2017\/file\/d8bf84b"},{"key":"2860_CR26","doi-asserted-by":"publisher","unstructured":"Liu, Z., Zhao, X., Huang, T., Hu, R., Zhou, Y., Bai, X.: Tanet: Robust 3d object detection from point clouds with triple attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11677\u201311684 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6837","DOI":"10.1609\/aaai.v34i07.6837"},{"key":"2860_CR27","doi-asserted-by":"publisher","unstructured":"He, C., Zeng, H., Huang, J., Hua, X.-S., Zhang, L.: Structure aware single-stage 3d object detection from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11873\u201311882 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01189","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"2860_CR28","doi-asserted-by":"publisher","unstructured":"Wang, G., Tian, B., Zhang, Y., Chen, L., Cao, D., Wu, J.: Multi-view adaptive fusion network for 3d object detection. arXiv preprint arXiv:2011.00652 (2020). https:\/\/doi.org\/10.48550\/arXiv.2011.00652","DOI":"10.48550\/arXiv.2011.00652"},{"key":"2860_CR29","doi-asserted-by":"publisher","unstructured":"Liang, Z., Zhang, Z., Zhang, M., Zhao, X., Pu, S.: RangeIoUDet: Range image based real-time 3D object detector optimized by intersection over union. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7140\u20137149 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00706","DOI":"10.1109\/CVPR46437.2021.00706"},{"key":"2860_CR30","doi-asserted-by":"publisher","unstructured":"Ji, C., Liu, G., Zhao, D.: Stereo 3D object detection via instance depth prior guidance and adaptive spatial feature aggregation. Vis. Comput., pp. 1\u201312 (2022). https:\/\/doi.org\/10.1007\/s00371-022-02607-x","DOI":"10.1007\/s00371-022-02607-x"},{"key":"2860_CR31","doi-asserted-by":"publisher","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P.H.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00681","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"2860_CR32","doi-asserted-by":"publisher","unstructured":"Wang, H., Zhu, Y., Adam, H., Yuille, A., Chen, L.-C.: Max-deeplab: End-to-end panoptic segmentation with mask transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5463\u20135474 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00542","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"2860_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16259\u201316268 (2021). ICCV2021\/papers\/Zhao_Point_Transformer_ICCV_2021_paper","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"2860_CR34","doi-asserted-by":"publisher","unstructured":"Pan, X., Xia, Z., Song, S., Li, L.E., Huang, G.: 3d object detection with pointformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7463\u20137472 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00738","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"2860_CR35","unstructured":"Zaheer, M., Guruganesh, G., Dubey, K.A., Ainslie, J., Alberti, C., Ontanon, S., Pham, P., Ravula, A., Wang, Q., Yang, L.: Big bird: transformers for longer sequences. Adv. Neural Inf. Process. Syst. 33, 17283\u201317297 (2020). https:\/\/proceedings.neurips.cc\/paper\/2020"},{"key":"2860_CR36","doi-asserted-by":"publisher","unstructured":"Shi, S., Guo, C., Jiang, L., et al.: Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10529\u201310538 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01054","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"2860_CR37","doi-asserted-by":"publisher","unstructured":"Hasan, S.K., Linte, C.A., U-NetPlus: A modified encoder-decoder U-Net architecture for semantic and instance segmentation of surgical instruments from laparoscopic images. In: 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE 2019, 7205\u20137211 (2019). https:\/\/doi.org\/10.1109\/EMBC.2019.8856791","DOI":"10.1109\/EMBC.2019.8856791"},{"key":"2860_CR38","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2117\u20132125 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"2860_CR39","doi-asserted-by":"publisher","unstructured":"W. Liu, A. Yue, W. Shi, J. Ji, R. Deng, An automatic extraction architecture of urban green space based on DeepLabv3plus semantic segmentation model. In: 2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC), IEEE, pp. 311\u2013315 (2019). https:\/\/doi.org\/10.1109\/ICIVC47709.2019.8981007","DOI":"10.1109\/ICIVC47709.2019.8981007"},{"key":"2860_CR40","doi-asserted-by":"publisher","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1492\u20131500 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.634","DOI":"10.1109\/CVPR.2017.634"},{"key":"2860_CR41","doi-asserted-by":"publisher","unstructured":"Zhang, H., Wu, C., Zhang, Z., Zhu, Y., Lin, H., Zhang, Z., Sun, Y., He, T., Mueller, J., Manmatha,R.: Resnest: split-attention networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2736\u20132746 (2022). https:\/\/doi.org\/10.48550\/arXiv.2004.08955","DOI":"10.48550\/arXiv.2004.08955"},{"key":"2860_CR42","doi-asserted-by":"publisher","unstructured":"Qamar, S., Jin, H., Zheng, R., Faizan, M., Hybrid loss guided densely connected convolutional neural network for Ischemic Stroke Lesion segmentation. In: IEEE 5th International Conference for Convergence in Technology (I2CT). IEEE 2019, 1\u20135 (2019). https:\/\/doi.org\/10.1109\/I2CT45611.2019.9033802","DOI":"10.1109\/I2CT45611.2019.9033802"},{"key":"2860_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.algal.2020.101932","volume":"48","author":"G Pant","year":"2020","unstructured":"Pant, G., Yadav, D., Gaur, A.: ResNeXt convolution neural network topology-based deep learning model for identification and classification of Pediastrum. Algal Res. 48, 101932 (2020). https:\/\/doi.org\/10.1016\/j.algal.2020.101932","journal-title":"Algal Res."},{"key":"2860_CR44","doi-asserted-by":"publisher","unstructured":"Zhao, X., Liu, Z., Hu, R., Huang, K.: 3d object detection using scale invariant and feature reweighting networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 9267\u20139274 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33019267","DOI":"10.1609\/aaai.v33i01.33019267"},{"key":"2860_CR45","doi-asserted-by":"publisher","unstructured":"Liang, M., Yang, B., Chen, Y., Hu, R., Urtasun,R.: Multi-task multi-sensor fusion for 3d object detection, Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (2019), pp. 7345-7353, https:\/\/doi.org\/10.1109\/CVPR.2019.00752","DOI":"10.1109\/CVPR.2019.00752"},{"key":"2860_CR46","doi-asserted-by":"publisher","unstructured":"Ye, M., Xu, S., Cao, T.: Hvnet: Hybrid voxel network for lidar based 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 1631\u20131640 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00170","DOI":"10.1109\/CVPR42600.2020.00170"},{"key":"2860_CR47","doi-asserted-by":"publisher","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3dssd: Point-based 3d single stage object detector In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11040\u201311048 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01105","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"2860_CR48","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.neucom.2021.06.046","volume":"459","author":"Y He","year":"2021","unstructured":"He, Y., Xia, G., Luo, Y., Su, L., Zhang, Z., Li, W., Wang, P.: DVFENet: dual-branch voxel feature extraction network for 3D object detection. Neurocomputing 459, 201\u2013211 (2021). https:\/\/doi.org\/10.1016\/j.neucom.2021.06.046","journal-title":"Neurocomputing"},{"key":"2860_CR49","doi-asserted-by":"crossref","unstructured":"Mao, J., Xue, Y., Niu, M., Bai, H., Feng, J., Liang, X., Xu, H., Xu, C.: Voxel transformer for 3d object detection In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3164\u20133173 (2021)","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"2860_CR50","doi-asserted-by":"crossref","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel r-cnn: Towards high performance voxel-based 3d object detection In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"2860_CR51","doi-asserted-by":"publisher","unstructured":"Lan, M., Zhang, J., Wang, Z.: Coherence-aware context aggregator for fast video object segmentation. Pattern Recogn. 136, 109214 (2023). https:\/\/doi.org\/10.1016\/j.patcog.2022.109214","DOI":"10.1016\/j.patcog.2022.109214"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02860-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-02860-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02860-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,18]],"date-time":"2024-02-18T23:27:39Z","timestamp":1708298859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-02860-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,1]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["2860"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-02860-8","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,1]]},"assertion":[{"value":"29 March 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 May 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}