{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:25:38Z","timestamp":1780053938932,"version":"3.54.0"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031189128","type":"print"},{"value":"9783031189135","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-18913-5_7","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"82-95","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Unsupervised Pre-training for\u00a03D Object Detection with\u00a0Transformer"],"prefix":"10.1007","author":[{"given":"Maosheng","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoshui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeren","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yazhou","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"7_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. arXiv preprint arXiv:2203.00680 (2022)","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"7_CR2","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. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"7_CR3","doi-asserted-by":"publisher","first-page":"1042","DOI":"10.1109\/TMM.2021.3106095","volume":"24","author":"T Chen","year":"2022","unstructured":"Chen, T., Wang, S.H., Wang, Q., Zhang, Z., Xie, G.S., Tang, Z.: Enhanced feature alignment for unsupervised domain adaptation of semantic segmentation. IEEE Trans. Multimedia (TMM) 24, 1042\u20131054 (2022)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"7_CR4","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1109\/TMM.2021.3061816","volume":"24","author":"T Chen","year":"2022","unstructured":"Chen, T., et al.: Semantically meaningful class prototype learning for one-shot image segmentation. IEEE Trans. Multimedia (TMM) 24, 968\u2013980 (2022)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"7_CR5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3157481","author":"T Chen","year":"2022","unstructured":"Chen, T., Yao, Y., Zhang, L., Wang, Q., Xie, G., Shen, F.: Saliency guided inter-and intra-class relation constraints for weakly supervised semantic segmentation. IEEE Trans. Multimedia (TMM) (2022). https:\/\/doi.org\/10.1109\/TMM.2022.3157481","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"7_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"7_CR7","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR.2017.691"},{"key":"7_CR8","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y., Nie\u00dfner, M., Dai, A.: 4Dcontrast: Contrastive learning with dynamic correspondences for 3d scene understanding. arXiv preprint arXiv:2112.02990 (2021)","DOI":"10.1007\/978-3-031-19824-3_32"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Choy, C., Park, J., Koltun, V.: Fully convolutional geometric features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8958\u20138966 (2019)","DOI":"10.1109\/ICCV.2019.00905"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: Richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., Chen, J.: UP-DETR: Unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1601\u20131610 (2021)","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: M3DETR: Multi-representation, multi-scale, mutual-relation 3d object detection with transformers. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 772\u2013782 (2022)","DOI":"10.1109\/WACV51458.2022.00235"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Hassani, K., Haley, M.: Unsupervised multi-task feature learning on point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8160\u20138171 (2019)","DOI":"10.1109\/ICCV.2019.00825"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Hou, J., Graham, B., Nie\u00dfner, M., Xie, S.: Exploring data-efficient 3d scene understanding with contrastive scene contexts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15587\u201315597 (2021)","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Huang, S., Xie, Y., Zhu, S.C., Zhu, Y.: Spatio-temporal self-supervised representation learning for 3d point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6535\u20136545 (2021)","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Huang, X., Fan, L., Wu, Q., Zhang, J., Yuan, C.: Fast registration for cross-source point clouds by using weak regional affinity and pixel-wise refinement. In: 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 1552\u20131557. IEEE (2019)","DOI":"10.1109\/ICME.2019.00268"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Huang, X., Fan, L., Zhang, J., Wu, Q., Yuan, C.: Real time complete dense depth reconstruction for a monocular camera. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 32\u201337 (2016)","DOI":"10.1109\/CVPRW.2016.89"},{"key":"7_CR20","doi-asserted-by":"crossref","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), pp. 1\u20138. IEEE (2018)","DOI":"10.1109\/IROS.2018.8594049"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., Wang, S., Urtasun, R.: Deep continuous fusion for multi-sensor 3d object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 641\u2013656 (2018)","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"7_CR22","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1109\/TMM.2021.3055024","volume":"24","author":"H Liu","year":"2022","unstructured":"Liu, H., et al.: Exploiting web images for fine-grained visual recognition by eliminating open-set noise and utilizing hard examples. IEEE Trans. Multimedia (TMM) 24, 546\u2013557 (2022)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"7_CR23","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1109\/TMM.2021.3118216","volume":"24","author":"H Liu","year":"2022","unstructured":"Liu, H., Zhang, H., Lu, J., Tang, Z.: Exploiting web images for fine-grained visual recognition via dynamic loss correction and global sample selection. IEEE Trans. Multimedia (TMM) 24, 1105\u20131115 (2022)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, Z., Cao, Y., Hu, H., Tong, X.: Group-free 3D object detection via transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2949\u20132958 (2021)","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Mao, J., et al.: 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":"7_CR26","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2906\u20132917 (2021)","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"7_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: Feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Pei, G., Shen, F., Yao, Y., Xie, G.S., Tang, Z., Tang, J.: Hierarchical feature alignment network for unsupervised video object segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19830-4_34"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep hough voting for 3d object detection in point clouds. In: proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"7_CR31","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":"7_CR32","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: Deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"7_CR33","unstructured":"Sauder, J., Sievers, B.: Self-supervised deep learning on point clouds by reconstructing space. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Sheng, H., et al.: Improving 3D object detection with channel-wise transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2743\u20132752 (2021)","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"7_CR35","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: SUN RGB-D: A RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Sun, Z., Hua, X.S., Yao, Y., Wei, X.S., Hu, G., Zhang, J.: CRSSC: salvage reusable samples from noisy data for robust learning. In: Proceedings of the ACM International Conference on Multimedia (ACMMM), pp. 92\u2013101 (2020)","DOI":"10.1145\/3394171.3413978"},{"key":"7_CR38","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1109\/TMM.2021.3116430","volume":"24","author":"Z Sun","year":"2022","unstructured":"Sun, Z., Liu, H., Wang, Q., Zhou, T., Wu, Q., Tang, Z.: Co-LDL: a co-training-based label distribution learning method for tackling label noise. IEEE Trans. Multimedia (TMM) 24, 1093\u20131104 (2022)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: PNP: Robust learning from noisy labels by probabilistic noise prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5311\u20135320 (2022)","DOI":"10.1109\/CVPR52688.2022.00524"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: Webly supervised fine-grained recognition: Benchmark datasets and an approach. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 10602\u201310611 (2021)","DOI":"10.1109\/ICCV48922.2021.01043"},{"key":"7_CR41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3158001","author":"Z Sun","year":"2022","unstructured":"Sun, Z., Yao, Y., Wei, X., Shen, F., Liu, H., Hua, X.S.: Boosting robust learning via leveraging reusable samples in noisy web data. IEEE Trans. Multimedia (TMM) (2022). https:\/\/doi.org\/10.1109\/TMM.2022.3158001","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"7_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107620","volume":"110","author":"Z Sun","year":"2021","unstructured":"Sun, Z., Yao, Y., Xiao, J., Zhang, L., Zhang, J., Tang, Z.: Exploiting textual queries for dynamically visual disambiguation. Pattern Recogn. 110, 107620 (2021)","journal-title":"Pattern Recogn."},{"key":"7_CR43","first-page":"7537","volume":"33","author":"M Tancik","year":"2020","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. Adv. Neural. Inf. Process. Syst. 33, 7537\u20137547 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR44","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"7_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/978-3-030-58580-8_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Xie","year":"2020","unstructured":"Xie, S., Gu, J., Guo, D., Qi, C.R., Guibas, L., Litany, O.: PointContrast: unsupervised pre-training for 3D point cloud understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 574\u2013591. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_34"},{"key":"7_CR46","doi-asserted-by":"crossref","unstructured":"Xu, B., Chen, Z.: Multi-level fusion based 3D object detection from monocular images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2345\u20132353 (2018)","DOI":"10.1109\/CVPR.2018.00249"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Yang, B., Luo, W., Urtasun, R.: Pixor: Real-time 3D object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7652\u20137660 (2018)","DOI":"10.1109\/CVPR.2018.00798"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: Non-salient region object mining for weakly supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2623\u20132632 (2021)","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Yao, Y., Hua, X.S., Shen, F., Zhang, J., Tang, Z.: A domain robust approach for image dataset construction. In: Proceedings of the ACM International Conference on Multimedia (ACMMM), pp. 212\u2013216 (2016)","DOI":"10.1145\/2964284.2967213"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Yao, Y., Hua, X., Gao, G., Sun, Z., Li, Z., Zhang, J.: Bridging the web data and fine-grained visual recognition via alleviating label noise and domain mismatch. In: Proceedings of the ACM International Conference on Multimedia (ACMMM), pp. 1735\u20131744 (2020)","DOI":"10.1145\/3394171.3413851"},{"issue":"7","key":"7_CR51","first-page":"2348","volume":"31","author":"Y Yao","year":"2020","unstructured":"Yao, Y., et al.: Exploiting web images for multi-output classification: from category to subcategories. IEEE Trans. Neural Netw. Learn. Syst. (TNNLS) 31(7), 2348\u20132360 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst. (TNNLS)"},{"issue":"1","key":"7_CR52","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1109\/TMM.2018.2847248","volume":"21","author":"Y Yao","year":"2019","unstructured":"Yao, Y., Shen, F., Zhang, J., Liu, L., Tang, Z., Shao, L.: Extracting multiple visual senses for web learning. IEEE Trans. Multimedia (TMM) 21(1), 184\u2013196 (2019)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"issue":"1","key":"7_CR53","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1109\/TIP.2018.2869721","volume":"28","author":"Y Yao","year":"2019","unstructured":"Yao, Y., Shen, F., Zhang, J., Liu, L., Tang, Z., Shao, L.: Extracting privileged information for enhancing classifier learning. IEEE Trans. Image Process. (TIP) 28(1), 436\u2013450 (2019)","journal-title":"IEEE Trans. Image Process. (TIP)"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Yao, Y., Sun, Z., Zhang, C., Shen, F., Wu, Q., Zhang, J., Tang, Z.: Jo-SRC: A contrastive approach for combating noisy labels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5192\u20135201 (2021)","DOI":"10.1109\/CVPR46437.2021.00515"},{"issue":"8","key":"7_CR55","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1109\/TMM.2017.2684626","volume":"19","author":"Y Yao","year":"2017","unstructured":"Yao, Y., Zhang, J., Shen, F., Hua, X., Xu, J., Tang, Z.: Exploiting web images for dataset construction: a domain robust approach. IEEE Trans. Multimedia (TMM) 19(8), 1771\u20131784 (2017)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"issue":"6","key":"7_CR56","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1109\/TKDE.2019.2903036","volume":"32","author":"Y Yao","year":"2020","unstructured":"Yao, Y., et al.: Towards automatic construction of diverse, high-quality image datasets. IEEE Trans. Knowl. Data Eng. (TKDE) 32(6), 1199\u20131211 (2020)","journal-title":"IEEE Trans. Knowl. Data Eng. (TKDE)"},{"key":"7_CR57","doi-asserted-by":"crossref","unstructured":"Yao, Y., Zhang, J., Shen, F., Yang, W., Huang, P., Tang, Z.: Discovering and distinguishing multiple visual senses for polysemous words. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 523\u2013530 (2018)","DOI":"10.1609\/aaai.v32i1.11255"},{"key":"7_CR58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3181439","author":"C Zhang","year":"2022","unstructured":"Zhang, C., Lin, G., Wang, Q., Shen, F., Yao, Y., Tang, Z.: Guided by meta-set: a data-driven method for fine-grained visual recognition. IEEE Trans. Multimedia (TMM) (2022). https:\/\/doi.org\/10.1109\/TMM.2022.3181439","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"7_CR59","doi-asserted-by":"publisher","first-page":"1198","DOI":"10.1109\/TMM.2021.3134156","volume":"24","author":"C Zhang","year":"2022","unstructured":"Zhang, C., Wang, Q., Xie, G., Wu, Q., Shen, F., Tang, Z.: Robust learning from noisy web images via data purification for fine-grained recognition. IEEE Trans. Multimedia (TMM) 24, 1198\u20131209 (2022)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"7_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, C.,et al.: Web-supervised network with softly update-drop training for fine-grained visual classification. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 12781\u201312788 (2020)","DOI":"10.1609\/aaai.v34i07.6973"},{"key":"7_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, C., Yao, Y., Shu, X., Li, Z., Tang, Z., Wu, Q.: Data-driven meta-set based fine-grained visual recognition. In: Proceedings of the ACM International Conference on Multimedia (ACMMM), pp. 2372\u20132381 (2020)","DOI":"10.1145\/3394171.3414044"},{"key":"7_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Extracting useful knowledge from noisy web images via data purification for fine-grained recognition. In: Proceedings of the ACM International Conference on Multimedia (ACMMM), pp. 4063\u20134072 (2021)","DOI":"10.1145\/3474085.3475536"},{"key":"7_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3d features on any point-cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10252\u201310263 (2021)","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"7_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3D features on any point-cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10252\u201310263 (2021)","DOI":"10.1109\/ICCV48922.2021.01009"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18913-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T04:15:15Z","timestamp":1678421715000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18913-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189128","9783031189135"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18913-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"233","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.03","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.35","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}