{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T19:22:03Z","timestamp":1743016923411,"version":"3.40.3"},"publisher-location":"Cham","reference-count":69,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729423"},{"type":"electronic","value":"9783031729430"}],"license":[{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72943-0_17","type":"book-chapter","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T13:42:09Z","timestamp":1732801329000},"page":"291-309","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Viewpoint: Robust 3D Object Recognition Under Arbitrary Views Through Joint Multi-part Representation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6350-7875","authenticated-orcid":false,"given":"Linlong","family":"Fan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5668-5529","authenticated-orcid":false,"given":"Ye","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0086-4958","authenticated-orcid":false,"given":"Yanqi","family":"Ge","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5559-8594","authenticated-orcid":false,"given":"Wen","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0723-4016","authenticated-orcid":false,"given":"Lixin","family":"Duan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,29]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Afham, M., Dissanayake, I., Dissanayake, D., Dharmasiri, A., Thilakarathna, K., Rodrigo, R.: CrossPoint: self-supervised cross-modal contrastive learning for 3D point cloud understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9902\u20139912 (2022)","DOI":"10.1109\/CVPR52688.2022.00967"},{"issue":"9","key":"17_CR2","doi-asserted-by":"publisher","first-page":"2051","DOI":"10.1109\/TPAMI.2017.2747134","volume":"40","author":"U Asif","year":"2017","unstructured":"Asif, U., Bennamoun, M., Sohel, F.A.: A multi-modal, discriminative and spatially invariant CNN for RGB-D object labeling. IEEE Trans. Pattern Anal. Mach. Intell. 40(9), 2051\u20132065 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR3","unstructured":"Brock, A., Lim, T., Ritchie, J.M., Weston, N.: Generative and discriminative voxel modeling with convolutional neural networks. arXiv preprint arXiv:1608.04236 (2016)"},{"key":"17_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part I. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"17_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-3-030-58555-6_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Chen","year":"2020","unstructured":"Chen, J., Qin, J., Shen, Y., Liu, L., Zhu, F., Shao, L.: Learning attentive and hierarchical representations for 3D shape recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XV. LNCS, vol. 12360, pp. 105\u2013122. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_7"},{"key":"17_CR6","unstructured":"Chen, S., Yu, T., Li, P.: MVT: multi-view vision transformer for 3D object recognition. arXiv preprint arXiv:2110.13083 (2021)"},{"key":"17_CR7","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 17864\u201317875 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Cai, R., Zhao, X., Huang, K.: Convolutional fisher kernels for RGB-D object recognition. In: 2015 International Conference on 3D Vision, pp. 135\u2013143. IEEE (2015)","DOI":"10.1109\/3DV.2015.23"},{"key":"17_CR9","unstructured":"Delitzas, A., et al.: Multi-CLIP: contrastive vision-language pre-training for question answering tasks in 3D scenes. arXiv preprint arXiv:2306.02329 (2023)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"17_CR11","unstructured":"Dosovitskiy, A., Beyer, L., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Esteves, C., Xu, Y., Allen-Blanchette, C., Daniilidis, K.: Equivariant multi-view networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1568\u20131577 (2019)","DOI":"10.1109\/ICCV.2019.00165"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Feng, Y., Zhang, Z., Zhao, X., Ji, R., Gao, Y.: GVCNN: group-view convolutional neural networks for 3d shape recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 264\u2013272 (2018)","DOI":"10.1109\/CVPR.2018.00035"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Fu, J., Zheng, H., Mei, T.: Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4438\u20134446 (2017)","DOI":"10.1109\/CVPR.2017.476"},{"key":"17_CR15","unstructured":"Gao, K., Gao, Y., He, H., Lu, D., Xu, L., Li, J.: NeRF: neural radiance field in 3D vision, a comprehensive review. arXiv preprint arXiv:2210.00379 (2022)"},{"issue":"3","key":"17_CR16","doi-asserted-by":"publisher","first-page":"3181","DOI":"10.1109\/TPAMI.2022.3182052","volume":"45","author":"Y Gao","year":"2022","unstructured":"Gao, Y., Feng, Y., Ji, S., Ji, R.: HGNN+: general hypergraph neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3181\u20133199 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"17_CR17","doi-asserted-by":"publisher","first-page":"4338","DOI":"10.1109\/TPAMI.2020.3005434","volume":"43","author":"Y Guo","year":"2020","unstructured":"Guo, Y., Wang, H., Hu, Q., Liu, H., Liu, L., Bennamoun, M.: Deep learning for 3D point clouds: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 43(12), 4338\u20134364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"17_CR18","doi-asserted-by":"publisher","first-page":"3986","DOI":"10.1109\/TIP.2019.2904460","volume":"28","author":"Z Han","year":"2019","unstructured":"Han, Z., et al.: 3D2Seqviews: aggregating sequential views for 3d global feature learning by CNN with hierarchical attention aggregation. IEEE Trans. Image Process. 28(8), 3986\u20133999 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR20","unstructured":"Herreras, E.B.: Cognitive neuroscience; the biology of the mind. Cuadernos Neuropsicolog\u00eda\/Panamerican J. Neuropsychol. 4(1), 87\u201390 (2010)"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Hong, Y., Lin, C., Du, Y., Chen, Z., Tenenbaum, J.B., Gan, C.: 3D concept learning and reasoning from multi-view images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9202\u20139212 (2023)","DOI":"10.1109\/CVPR52729.2023.00888"},{"issue":"1","key":"17_CR22","doi-asserted-by":"publisher","first-page":"62","DOI":"10.3390\/rs13010062","volume":"13","author":"L Hu","year":"2020","unstructured":"Hu, L., Qin, M., Zhang, F., Du, Z., Liu, R.: RSCNN: a CNN-based method to enhance low-light remote-sensing images. Remote Sens. 13(1), 62 (2020)","journal-title":"Remote Sens."},{"key":"17_CR23","unstructured":"Hu, T., Qi, H., Huang, Q., Lu, Y.: See better before looking closer: weakly supervised data augmentation network for fine-grained visual classification. arXiv preprint arXiv:1901.09891 (2019)"},{"key":"17_CR24","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1109\/TMM.2020.3047762","volume":"24","author":"J Huang","year":"2022","unstructured":"Huang, J., Yan, W., Li, T., Liu, S., Li, G.: Learning the global descriptor for 3-D object recognition based on multiple views decomposition. IEEE Trans. Multimed. 24, 188\u2013201 (2022). https:\/\/doi.org\/10.1109\/TMM.2020.3047762","journal-title":"IEEE Trans. Multimed."},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Huang, S., Xu, Z., Tao, D., Zhang, Y.: Part-stacked CNN for fine-grained visual categorization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1173\u20131182 (2016)","DOI":"10.1109\/CVPR.2016.132"},{"issue":"1","key":"17_CR26","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1109\/TPAMI.2019.2922640","volume":"43","author":"A Kanezaki","year":"2019","unstructured":"Kanezaki, A., Matsushita, Y., Nishida, Y.: RotationNet for joint object categorization and unsupervised pose estimation from multi-view images. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 269\u2013283 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Klokov, R., Lempitsky, V.: Escape from cells: deep Kd-networks for the recognition of 3D point cloud models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 863\u2013872 (2017)","DOI":"10.1109\/ICCV.2017.99"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Kumawat, S., Raman, S.: LP-3DCNN: unveiling local phase in 3D convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4903\u20134912 (2019)","DOI":"10.1109\/CVPR.2019.00504"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Lai, K., Bo, L., Ren, X., Fox, D.: A large-scale hierarchical multi-view RGB-D object dataset. In: 2011 IEEE International Conference on Robotics and Automation, pp. 1817\u20131824. IEEE (2011)","DOI":"10.1109\/ICRA.2011.5980382"},{"key":"17_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20077-9_1","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Z Li","year":"2022","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1"},{"issue":"4","key":"17_CR31","first-page":"4447","volume":"45","author":"Y Lin","year":"2022","unstructured":"Lin, Y., Gou, Y., Liu, X., Bai, J., Lv, J., Peng, X.: Dual contrastive prediction for incomplete multi-view representation learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4447\u20134461 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR32","doi-asserted-by":"publisher","first-page":"984","DOI":"10.1016\/j.ins.2020.09.057","volume":"547","author":"AA Liu","year":"2021","unstructured":"Liu, A.A., et al.: Hierarchical multi-view context modelling for 3D object classification and retrieval. Inf. Sci. 547, 984\u2013995 (2021)","journal-title":"Inf. Sci."},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3D object. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Liu, S., Nguyen, V., Rehg, I., Tu, Z.: Recognizing objects from any view with object and viewer-centered representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11784\u201311793 (2020)","DOI":"10.1109\/CVPR42600.2020.01180"},{"key":"17_CR35","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1109\/TIP.2020.3048623","volume":"30","author":"X Liu","year":"2021","unstructured":"Liu, X., Han, Z., Liu, Y.S., Zwicker, M.: Fine-grained 3D shape classification with hierarchical part-view attention. IEEE Trans. Image Process. 30, 1744\u20131758 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR36","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"17_CR37","doi-asserted-by":"publisher","unstructured":"Lowe, D.: Object recognition from local scale-invariant features. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, vol.\u00a02, pp. 1150\u20131157 (1999). https:\/\/doi.org\/10.1109\/ICCV.1999.790410","DOI":"10.1109\/ICCV.1999.790410"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Maturana, D., Scherer, S.: VoxNet: a 3D convolutional neural network for real-time object recognition. In: 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922\u2013928. IEEE (2015)","DOI":"10.1109\/IROS.2015.7353481"},{"key":"17_CR39","doi-asserted-by":"publisher","first-page":"1774","DOI":"10.1109\/TIP.2022.3145238","volume":"31","author":"M Meng","year":"2022","unstructured":"Meng, M., Zhang, T., Yang, W., Zhao, J., Zhang, Y., Wu, F.: Diverse complementary part mining for weakly supervised object localization. IEEE Trans. Image Process. 31, 1774\u20131788 (2022). https:\/\/doi.org\/10.1109\/TIP.2022.3145238","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"17_CR40","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"17_CR41","doi-asserted-by":"publisher","first-page":"4371","DOI":"10.1109\/TIP.2021.3071687","volume":"30","author":"W Nie","year":"2021","unstructured":"Nie, W., Zhao, Y., Song, D., Gao, Y.: DAN: deep-attention network for 3D shape recognition. IEEE Trans. Image Process. 30, 4371\u20134383 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR42","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)"},{"key":"17_CR43","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)"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Tan, Y., Xue, J., Lu, K.: RGB-D object recognition with multimodal deep convolutional neural networks. In: 2017 IEEE International Conference on Multimedia and Expo (ICME), pp. 991\u2013996. IEEE (2017)","DOI":"10.1109\/ICME.2017.8019538"},{"key":"17_CR45","doi-asserted-by":"crossref","unstructured":"Rao, Y., Chen, G., Lu, J., Zhou, J.: Counterfactual attention learning for fine-grained visual categorization and re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1025\u20131034 (2021)","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Riegler, G., Osman\u00a0Ulusoy, A., Geiger, A.: OctNet: learning deep 3D representations at high resolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3577\u20133586 (2017)","DOI":"10.1109\/CVPR.2017.701"},{"key":"17_CR47","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 945\u2013953 (2015)","DOI":"10.1109\/ICCV.2015.114"},{"key":"17_CR49","doi-asserted-by":"crossref","unstructured":"Su, J.C., Gadelha, M., Wang, R., Maji, S.: A deeper look at 3D shape classifiers. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)","DOI":"10.1007\/978-3-030-11015-4_49"},{"key":"17_CR50","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1109\/TIP.2020.3039378","volume":"30","author":"K Sun","year":"2020","unstructured":"Sun, K., Zhang, J., Liu, J., Yu, R., Song, Z.: DRCNN: dynamic routing convolutional neural network for multi-view 3D object recognition. IEEE Trans. Image Process. 30, 868\u2013877 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"17_CR52","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: KPConv: flexible and deformable convolution for point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6411\u20136420 (2019)","DOI":"10.1109\/ICCV.2019.00651"},{"key":"17_CR53","doi-asserted-by":"crossref","unstructured":"Uy, M.A., Pham, Q.H., Hua, B.S., Nguyen, T., Yeung, S.K.: Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1588\u20131597 (2019)","DOI":"10.1109\/ICCV.2019.00167"},{"issue":"5","key":"17_CR54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. (ToG) 38(5), 1\u201312 (2019)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"17_CR55","doi-asserted-by":"crossref","unstructured":"Wei, X., Gong, Y., Wang, F., Sun, X., Sun, J.: Learning canonical view representation for 3D shape recognition with arbitrary views. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 407\u2013416 (2021)","DOI":"10.1109\/ICCV48922.2021.00046"},{"key":"17_CR56","doi-asserted-by":"crossref","unstructured":"Wei, X., Yu, R., Sun, J.: View-GCN: view-based graph convolutional network for 3D shape analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1850\u20131859 (2020)","DOI":"10.1109\/CVPR42600.2020.00192"},{"key":"17_CR57","doi-asserted-by":"crossref","unstructured":"Wei, X., Yu, R., Sun, J.: Learning view-based graph convolutional network for multi-view 3D shape analysis. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3221785"},{"key":"17_CR58","unstructured":"Wu, S., Khosla, Y., Zhang, T.: D shapeNets: a deep representation for volumetric shape modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, pp. 7\u201312 (2015)"},{"key":"17_CR59","unstructured":"Wu, Z., et al.: 3D shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912\u20131920 (2015)"},{"key":"17_CR60","doi-asserted-by":"publisher","first-page":"5299","DOI":"10.1109\/TIP.2021.3082310","volume":"30","author":"Y Xu","year":"2021","unstructured":"Xu, Y., Zheng, C., Xu, R., Quan, Y., Ling, H.: Multi-view 3D shape recognition via correspondence-aware deep learning. IEEE Trans. Image Process. 30, 5299\u20135312 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR61","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: ULIP: learning unified representation of language, image and point cloud for 3D understanding. arXiv preprint arXiv:2212.05171 (2022)","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"17_CR62","doi-asserted-by":"crossref","unstructured":"Yang, C., et\u00a0al.: BEVFormer v2: adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17830\u201317839 (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"17_CR63","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, L.: Learning relationships for multi-view 3D object recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7505\u20137514 (2019)","DOI":"10.1109\/ICCV.2019.00760"},{"key":"17_CR64","doi-asserted-by":"publisher","first-page":"2168","DOI":"10.1109\/TIP.2021.3049968","volume":"30","author":"T Yu","year":"2021","unstructured":"Yu, T., Meng, J., Yang, M., Yuan, J.: 3D object representation learning: a set-to-set matching perspective. IEEE Trans. Image Process. 30, 2168\u20132179 (2021). https:\/\/doi.org\/10.1109\/TIP.2021.3049968","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR65","doi-asserted-by":"publisher","unstructured":"Yu, T., Meng, J., Yuan, J.: Multi-view harmonized bilinear network for 3D object recognition. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 186\u2013194 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00027","DOI":"10.1109\/CVPR.2018.00027"},{"key":"17_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: SPDA-CNN: unifying semantic part detection and abstraction for fine-grained recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1143\u20131152 (2016)","DOI":"10.1109\/CVPR.2016.129"},{"key":"17_CR67","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10590-1_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"N Zhang","year":"2014","unstructured":"Zhang, N., Donahue, J., Girshick, R., Darrell, T.: Part-based R-CNNs for fine-grained category detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_54"},{"key":"17_CR68","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5209\u20135217 (2017)","DOI":"10.1109\/ICCV.2017.557"},{"key":"17_CR69","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72943-0_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T14:20:47Z","timestamp":1732803647000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72943-0_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,29]]},"ISBN":["9783031729423","9783031729430"],"references-count":69,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72943-0_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,29]]},"assertion":[{"value":"29 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}