{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T02:04:35Z","timestamp":1778897075062,"version":"3.51.4"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T00:00:00Z","timestamp":1707264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T00:00:00Z","timestamp":1707264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s11263-023-01981-w","type":"journal-article","created":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T18:02:27Z","timestamp":1707328947000},"page":"2585-2599","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation"],"prefix":"10.1007","volume":"132","author":[{"given":"Sha","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6520-255X","authenticated-orcid":false,"given":"Yanyong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,7]]},"reference":[{"issue":"11","key":"1981_CR1","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & S\u00fcsstrunk, S. (2012). Slic superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 34(11), 2274\u20132282.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1981_CR2","doi-asserted-by":"crossref","unstructured":"Alexiou, E., Yang, N., & Ebrahimi, T. (2020). Pointxr: A toolbox for visualization and subjective evaluation of point clouds in virtual reality. In: 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX), IEEE, pp. 1\u20136.","DOI":"10.1109\/QoMEX48832.2020.9123121"},{"key":"1981_CR3","first-page":"9758","volume":"33","author":"H Alwassel","year":"2020","unstructured":"Alwassel, H., Mahajan, D., Korbar, B., Torresani, L., Ghanem, B., & Tran, D. (2020). Self-supervised learning by cross-modal audio-video clustering. Advances in Neural Information Processing Systems (NeurIPS), 33, 9758\u20139770.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"1981_CR4","doi-asserted-by":"crossref","unstructured":"Behley, J., Garbade, M., Milioto, A., Quenzel, J., Behnke, S., Stachniss, C., & Gall, J. (2019). Semantickitti: A dataset for semantic scene understanding of lidar sequences. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9297\u20139307.","DOI":"10.1109\/ICCV.2019.00939"},{"key":"1981_CR5","doi-asserted-by":"crossref","unstructured":"Berman, M., Triki, A. R., & Blaschko, M. B. (2018). The lov\u00e1sz-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 4413\u20134421.","DOI":"10.1109\/CVPR.2018.00464"},{"key":"1981_CR6","doi-asserted-by":"crossref","unstructured":"Bucilu\u01ce, C., Caruana, R., & Niculescu-Mizil, A. (2006). Model compression. In: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining (SIGKDD), pp. 535\u2013541.","DOI":"10.1145\/1150402.1150464"},{"key":"1981_CR7","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020). Nuscenes: A multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 11621\u201311631.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"1981_CR8","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp. 9650\u20139660.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"1981_CR9","unstructured":"Chen, X., Fan, H., Girshick, R., & He, K. (2020). Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297"},{"key":"1981_CR10","doi-asserted-by":"crossref","unstructured":"Chen, H., Luo, S., Gao, X., & Hu, W. (2021). Unsupervised learning of geometric sampling invariant representations for 3d point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 893\u2013903.","DOI":"10.1109\/ICCVW54120.2021.00105"},{"key":"1981_CR11","doi-asserted-by":"publisher","first-page":"3183","DOI":"10.1109\/TIP.2019.2957935","volume":"29","author":"S Chen","year":"2019","unstructured":"Chen, S., Duan, C., Yang, Y., Li, D., Feng, C., & Tian, D. (2019). Deep unsupervised learning of 3d point clouds via graph topology inference and filtering. IEEE Transactions on Image Processing (TIP), 29, 3183\u20133198.","journal-title":"IEEE Transactions on Image Processing (TIP)"},{"key":"1981_CR12","doi-asserted-by":"crossref","unstructured":"Cho, J. H., & Hariharan, B. (2019). On the efficacy of knowledge distillation. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp. 4794\u20134802.","DOI":"10.1109\/ICCV.2019.00489"},{"key":"1981_CR13","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., & Savarese, S. (2019). 4d spatio-temporal convnets: Minkowski convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3075\u20133084.","DOI":"10.1109\/CVPR.2019.00319"},{"key":"1981_CR14","doi-asserted-by":"crossref","unstructured":"Duan, Y., Peng, J., Zhang, Y., Ji, J., & Zhang, Y. (2022). Pfilter: Building persistent maps through feature filtering for fast and accurate lidar-based slam. In: 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 11087\u201311093.","DOI":"10.1109\/IROS47612.2022.9981566"},{"key":"1981_CR15","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR), IEEE, pp. 3354\u20133361.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"1981_CR16","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J. B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila Pires, B., Guo, Z., Gheshlaghi Azar, M., et al. (2020). Bootstrap your own latent-a new approach to self-supervised learning. Advances in Neural Information Processing Systems (NeurIPS), 33, 21271\u201321284.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"1981_CR17","doi-asserted-by":"crossref","unstructured":"Guo, X., Shi, S., Wang, X., & Li, H. (2021). Liga-stereo: Learning lidar geometry aware representations for stereo-based 3d detector. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 3153\u20133163.","DOI":"10.1109\/ICCV48922.2021.00314"},{"key":"1981_CR18","doi-asserted-by":"crossref","unstructured":"Gupta, S., Hoffman, J., & Malik, J. (2016). Cross modal distillation for supervision transfer. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 2827\u20132836.","DOI":"10.1109\/CVPR.2016.309"},{"key":"1981_CR19","doi-asserted-by":"crossref","unstructured":"Han, Z., Wang, X., Liu, Y. S., & Zwicker, M. (2019b). Multi-angle point cloud-vae: Unsupervised feature learning for 3d point clouds from multiple angles by joint self-reconstruction and half-to-half prediction. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE, pp. 10441\u201310450.","DOI":"10.1109\/ICCV.2019.01054"},{"key":"1981_CR20","doi-asserted-by":"crossref","unstructured":"Han, Z., Wang, X., Liu, Y. S., & Zwicker, M. (2021b). Hierarchical view predictor: Unsupervised 3d global feature learning through hierarchical prediction among unordered views. In: Proceedings of the 29th ACM International Conference on Multimedia (ACM MM), pp. 3862\u20133871.","DOI":"10.1145\/3474085.3475172"},{"key":"1981_CR21","doi-asserted-by":"publisher","first-page":"101398","DOI":"10.1016\/j.aei.2021.101398","volume":"50","author":"B Han","year":"2021","unstructured":"Han, B., Ma, J. W., & Leite, F. (2021). A framework for semi-automatically identifying fully occluded objects in 3d models: Towards comprehensive construction design review in virtual reality. Advanced Engineering Informatics, 50, 101398.","journal-title":"Advanced Engineering Informatics"},{"key":"1981_CR22","doi-asserted-by":"publisher","first-page":"8376","DOI":"10.1609\/aaai.v33i01.33018376","volume":"33","author":"Z Han","year":"2019","unstructured":"Han, Z., Shang, M., Liu, Y. S., & Zwicker, M. (2019). View inter-prediction gan: Unsupervised representation learning for 3d shapes by learning global shape memories to support local view predictions. Proceedings of the AAAI Conference On Artificial Intelligence (AAAI), 33, 8376\u20138384.","journal-title":"Proceedings of the AAAI Conference On Artificial Intelligence (AAAI)"},{"key":"1981_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1981_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1981_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1981_CR26","unstructured":"Hinton, G., Vinyals, O., Dean, J., et\u00a0al. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 2(7)."},{"key":"1981_CR27","unstructured":"Huang, J., Huang, G., Zhu, Z., & Du, D. (2021). Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790."},{"key":"1981_CR28","unstructured":"Jiang, J., Lu, X., Ouyang, W., & Wang, M. (2021). Unsupervised representation learning for 3d point cloud data. arXiv preprint arXiv:2110.06632."},{"key":"1981_CR29","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lu, T., Qiao, Y., & Dai, J. (2022b). Bevformer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part IX, Springer, pp. 1\u201318.","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"1981_CR30","unstructured":"Li, C. L., Zaheer, M., Zhang, Y., Poczos, B., & Salakhutdinov, R. (2018). Point cloud gan. arXiv preprint arXiv:1810.05795."},{"issue":"4","key":"1981_CR31","doi-asserted-by":"publisher","first-page":"11182","DOI":"10.1109\/LRA.2022.3193465","volume":"7","author":"Y Li","year":"2022","unstructured":"Li, Y., Deng, J., Zhang, Y., Ji, J., Li, H., & Zhang, Y. (2022). Ezfusion: A close look at the integration of lidar, millimeter-wave radar, and camera for accurate 3d object detection and tracking. IEEE Robotics and Automation Letters (RAL), 7(4), 11182\u201311189.","journal-title":"IEEE Robotics and Automation Letters (RAL)"},{"key":"1981_CR32","unstructured":"Liu, Y. C., Huang, Y. K., Chiang, H. Y., Su, H. T., Liu, Z. Y., Chen, C. T., Tseng, C. Y., & Hsu, W. H. (2021a). Learning from 2d: Contrastive pixel-to-point knowledge transfer for 3d pretraining. arXiv preprint arXiv:2104.04687"},{"key":"1981_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., Qi, X., & Fu, C. W. (2021b). 3d-to-2d distillation for indoor scene parsing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 4464\u20134474.","DOI":"10.1109\/CVPR46437.2021.00444"},{"key":"1981_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Tang, H., Amini, A., Yang, X., Mao, H., Rus, D., & Han, S. (2022). Bevfusion: Multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. arXiv preprint arXiv:2205.13542.","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"1981_CR35","doi-asserted-by":"publisher","first-page":"5191","DOI":"10.1609\/aaai.v34i04.5963","volume":"34","author":"SI Mirzadeh","year":"2020","unstructured":"Mirzadeh, S. I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., & Ghasemzadeh, H. (2020). Improved knowledge distillation via teacher assistant. Proceedings of the AAAI Conference On Artificial Intelligence (AAAI), 34, 5191\u20135198.","journal-title":"Proceedings of the AAAI Conference On Artificial Intelligence (AAAI)"},{"key":"1981_CR36","unstructured":"Oord, A.v.d., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748."},{"issue":"1","key":"1981_CR37","doi-asserted-by":"publisher","first-page":"172988141990006","DOI":"10.1177\/1729881419900066","volume":"17","author":"X Qi","year":"2020","unstructured":"Qi, X., Wang, W., Yuan, M., Wang, Y., Li, M., Xue, L., & Sun, Y. (2020). Building semantic grid maps for domestic robot navigation. International Journal of Advanced Robotic Systems, 17(1), 1729881419900066.","journal-title":"International Journal of Advanced Robotic Systems"},{"key":"1981_CR38","doi-asserted-by":"crossref","unstructured":"Rao, Y., Lu, J., & Zhou, J. (2020). Global-local bidirectional reasoning for unsupervised representation learning of 3d point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5376\u20135385.","DOI":"10.1109\/CVPR42600.2020.00542"},{"key":"1981_CR39","doi-asserted-by":"crossref","unstructured":"Sanghi, A. (2020). Info3d: Representation learning on 3d objects using mutual information maximization and contrastive learning. In: European Conference on Computer Vision (ECCV) (pp. 626\u2013642), Springer.","DOI":"10.1007\/978-3-030-58526-6_37"},{"key":"1981_CR40","doi-asserted-by":"crossref","unstructured":"Sautier, C., Puy, G., Gidaris, S., Boulch, A., Bursuc, A., & Marlet, R. (2022). Image-to-lidar self-supervised distillation for autonomous driving data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9891\u20139901.","DOI":"10.1109\/CVPR52688.2022.00966"},{"key":"1981_CR41","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., & Li, H. (2019). Pointrcnn: 3d object proposal generation and detection from point cloud. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 770\u2013779.","DOI":"10.1109\/CVPR.2019.00086"},{"issue":"2","key":"1981_CR42","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s11263-022-01710-9","volume":"131","author":"S Shi","year":"2023","unstructured":"Shi, S., Jiang, L., Deng, J., Wang, Z., Guo, C., Shi, J., Wang, X., & Li, H. (2023). Pv-rcnn++: Point-voxel feature set abstraction with local vector representation for 3d object detection. International Journal of Computer Vision (IJCV), 131(2), 531\u2013551.","journal-title":"International Journal of Computer Vision (IJCV)"},{"issue":"8","key":"1981_CR43","first-page":"2647","volume":"43","author":"S Shi","year":"2021","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., & Li, H. (2021). From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(8), 2647\u20132664.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1981_CR44","unstructured":"Team, O. D. (2020). Openpcdet: An open-source toolbox for 3d object detection from point clouds. https:\/\/github.com\/open-mmlab\/OpenPCDet."},{"key":"1981_CR45","unstructured":"Tian, Y., Krishnan, D., & Isola, P. (2019). Contrastive representation distillation. arXiv preprint arXiv:1910.10699."},{"key":"1981_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W. L., Garg, D., Hariharan, B., Campbell, M., & Weinberger, K. Q. (2019). Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8445\u20138453.","DOI":"10.1109\/CVPR.2019.00864"},{"key":"1981_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-023-01784-z","volume":"131","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Mao, Q., Zhu, H., Deng, J., Zhang, Y., Ji, J., Li, H., & Zhang, Y. (2023). Multi-modal 3d object detection in autonomous driving: A survey. International Journal of Computer Vision (IJCV), 131, 1\u201331.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1981_CR48","doi-asserted-by":"publisher","first-page":"2773","DOI":"10.1609\/aaai.v35i4.16382","volume":"35","author":"PS Wang","year":"2021","unstructured":"Wang, P. S., Yang, Y. Q., Zou, Q. F., Wu, Z., Liu, Y., & Tong, X. (2021). Unsupervised 3d learning for shape analysis via multiresolution instance discrimination. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 35, 2773\u20132781.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)"},{"issue":"5","key":"1981_CR49","doi-asserted-by":"publisher","first-page":"1293","DOI":"10.1007\/s11263-022-01602-y","volume":"130","author":"T Xiao","year":"2022","unstructured":"Xiao, T., Liu, S., De Mello, S., Yu, Z., Kautz, J., & Yang, M. H. (2022). Learning contrastive representation for semantic correspondence. International Journal of Computer Vision (IJCV), 130(5), 1293\u20131309.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1981_CR50","doi-asserted-by":"crossref","unstructured":"Xie, S., Gu, J., Guo, D., Qi, C. R., Guibas, L., & Litany, O. (2020). Pointcontrast: Unsupervised pre-training for 3d point cloud understanding. In: European conference on computer vision (ECCV) (pp. 574\u2013591), Springer.","DOI":"10.1007\/978-3-030-58580-8_34"},{"issue":"12","key":"1981_CR51","doi-asserted-by":"publisher","first-page":"2994","DOI":"10.1007\/s11263-022-01681-x","volume":"130","author":"J Xie","year":"2022","unstructured":"Xie, J., Zhan, X., Liu, Z., Ong, Y. S., & Loy, C. C. (2022). Delving into inter-image invariance for unsupervised visual representations. International Journal of Computer Vision (IJCV), 130(12), 2994\u20133013.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1981_CR52","unstructured":"Yang, Y., Feng, C., Shen, Y., & Tian, D. (2017). Foldingnet: Interpretable unsupervised learning on 3d point clouds. arXiv preprint arXiv:1712.07262 2(3):5."},{"key":"1981_CR53","unstructured":"Zhang, L., & Ma, K. (2020). Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors. In: International Conference on Learning Representations (ICLR)."},{"key":"1981_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., & Misra, I. (2021). Self-supervised pretraining of 3d features on any point-cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10252\u201310263.","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"1981_CR55","doi-asserted-by":"crossref","unstructured":"Zhao, B., Cui, Q., Song, R., Qiu, Y., & Liang, J. (2022a). Decoupled knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11953\u201311962.","DOI":"10.1109\/CVPR52688.2022.01165"},{"issue":"9","key":"1981_CR56","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1007\/s11263-022-01632-6","volume":"130","author":"Y Zhao","year":"2022","unstructured":"Zhao, Y., Fang, G., Guo, Y., Guibas, L., Tombari, F., & Birdal, T. (2022). 3dpointcaps++: Learning 3d representations with capsule networks. International Journal of Computer Vision (IJCV), 130(9), 2321\u20132336.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1981_CR57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189778","author":"H Zhu","year":"2022","unstructured":"Zhu, H., Deng, J., Zhang, Y., Ji, J., Mao, Q., Li, H., & Zhang, Y. (2022). Vpfnet: Improving 3d object detection with virtual point based lidar and stereo data fusion. IEEE Transactions on Multimedia (TMM). https:\/\/doi.org\/10.1109\/TMM.2022.3189778","journal-title":"IEEE Transactions on Multimedia (TMM)"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01981-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01981-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01981-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T13:17:52Z","timestamp":1718803072000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01981-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,7]]},"references-count":57,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["1981"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01981-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,7]]},"assertion":[{"value":"17 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There are no conflicts to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}