{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:50:16Z","timestamp":1771959016382,"version":"3.50.1"},"publisher-location":"Cham","reference-count":75,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585259","type":"print"},{"value":"9783030585266","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58526-6_35","type":"book-chapter","created":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T21:03:07Z","timestamp":1602018187000},"page":"589-607","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["Improving Object Detection with Selective Self-supervised Self-training"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2448-1294","authenticated-orcid":false,"given":"Yandong","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6021-5175","authenticated-orcid":false,"given":"Di","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7756-2074","authenticated-orcid":false,"given":"Danfeng","family":"Qin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1265-4656","authenticated-orcid":false,"given":"Liqiang","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3915-5977","authenticated-orcid":false,"given":"Boqing","family":"Gong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,7]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Arazo, E., Ortego, D., Albert, P., O\u2019Connor, N.E., McGuinness, K.: Pseudo-labeling and confirmation bias in deep semi-supervised learning. arXiv preprint arXiv:1908.02983 (2019)","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Arun, A., Jawahar, C., Kumar, M.P.: Dissimilarity coefficient based weakly supervised object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9432\u20139441 (2019)","DOI":"10.1109\/CVPR.2019.00966"},{"key":"35_CR3","unstructured":"Bachman, P., Alsharif, O., Precup, D.: Learning with pseudo-ensembles. In: Advances in Neural Information Processing Systems, pp. 3365\u20133373 (2014)"},{"key":"35_CR4","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: Mixmatch: a holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems, pp. 5050\u20135060 (2019)"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Bilen, H., Vedaldi, A.: Weakly supervised deep detection networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2846\u20132854 (2016)","DOI":"10.1109\/CVPR.2016.311"},{"key":"35_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709 (2020)"},{"key":"35_CR7","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, pp. 379\u2013387 (2016)"},{"key":"35_CR8","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":"35_CR9","doi-asserted-by":"crossref","unstructured":"Ding, Y., Wang, L., Fan, D., Gong, B.: A semi-supervised two-stage approach to learning from noisy labels. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1215\u20131224. IEEE (2018)","DOI":"10.1109\/WACV.2018.00138"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1422\u20131430 (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"35_CR11","unstructured":"Donahue, J., Simonyan, K.: Large scale adversarial representation learning. In: Advances in Neural Information Processing Systems, pp. 10541\u201310551 (2019)"},{"issue":"2","key":"35_CR12","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010). https:\/\/doi.org\/10.1007\/s11263-009-0275-4","journal-title":"Int. J. Comput. Vis."},{"key":"35_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1007\/978-3-319-46487-9_52","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Gan","year":"2016","unstructured":"Gan, C., Sun, C., Duan, L., Gong, B.: Webly-supervised video recognition by mutually voting for relevant web images and web video frames. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 849\u2013866. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_52"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Gan, C., Yao, T., Yang, K., Yang, Y., Mei, T.: You lead, we exceed: labor-free video concept learning by jointly exploiting web videos and images. In: CVPR, pp. 923\u2013932 (2016)","DOI":"10.1109\/CVPR.2016.106"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Gan, C., Zhao, H., Chen, P., Cox, D., Torralba, A.: Self-supervised moving vehicle tracking with stereo sound. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7053\u20137062 (2019)","DOI":"10.1109\/ICCV.2019.00715"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Gao, J., Wang, J., Dai, S., Li, L.J., Nevatia, R.: Note-RCNN: noise tolerant ensemble RCNN for semi-supervised object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9508\u20139517 (2019)","DOI":"10.1109\/ICCV.2019.00960"},{"key":"35_CR17","unstructured":"Gao, Y., et al.: C-MIDN: coupled multiple instance detection network with segmentation guidance for weakly supervised object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9834\u20139843 (2019)"},{"key":"35_CR18","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728 (2018)"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Grabner, H., Gall, J., Van Gool, L.: What makes a chair a chair? In: CVPR 2011, pp. 1529\u20131536. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995327"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. arXiv preprint arXiv:1911.05722 (2019)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"35_CR22","doi-asserted-by":"crossref","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)","DOI":"10.1109\/ICCV.2017.322"},{"key":"35_CR23","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":"35_CR24","doi-asserted-by":"crossref","unstructured":"Iscen, A., Tolias, G., Avrithis, Y., Chum, O.: Label propagation for deep semi-supervised learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5070\u20135079 (2019)","DOI":"10.1109\/CVPR.2019.00521"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Jenni, S., Favaro, P.: Self-supervised feature learning by learning to spot artifacts. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2733\u20132742 (2018)","DOI":"10.1109\/CVPR.2018.00289"},{"key":"35_CR26","unstructured":"Jeong, J., Lee, S., Kim, J., Kwak, N.: Consistency-based semi-supervised learning for object detection. In: Advances in Neural Information Processing Systems, pp. 10758\u201310767 (2019)"},{"key":"35_CR27","doi-asserted-by":"crossref","unstructured":"Kumar Singh, K., Xiao, F., Jae Lee, Y.: Track and transfer: watching videos to simulate strong human supervision for weakly-supervised object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3548\u20133556 (2016)","DOI":"10.1109\/CVPR.2016.386"},{"key":"35_CR28","unstructured":"Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242 (2016)"},{"key":"35_CR29","unstructured":"Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol. 3, p. 2 (2013)"},{"key":"35_CR30","doi-asserted-by":"crossref","unstructured":"Lee, W., Na, J., Kim, G.: Multi-task self-supervised object detection via recycling of bounding box annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4984\u20134993 (2019)","DOI":"10.1109\/CVPR.2019.00512"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Li, X., Kan, M., Shan, S., Chen, X.: Weakly supervised object detection with segmentation collaboration. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9735\u20139744 (2019)","DOI":"10.1109\/ICCV.2019.00983"},{"key":"35_CR32","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR.2017.106"},{"key":"35_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"35_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"35_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"35_CR36","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhu, J., Li, M., Ren, Y., Zhang, B.: Smooth neighbors on teacher graphs for semi-supervised learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8896\u20138905 (2018)","DOI":"10.1109\/CVPR.2018.00927"},{"key":"35_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/978-3-030-01216-8_12","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Mahajan","year":"2018","unstructured":"Mahajan, D., et al.: Exploring the limits of weakly supervised pretraining. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 185\u2013201. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_12"},{"key":"35_CR38","volume-title":"Society of Mind","author":"M Minsky","year":"1988","unstructured":"Minsky, M.: Society of Mind. Simon and Schuster, New York (1988)"},{"issue":"8","key":"35_CR39","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1109\/TPAMI.2018.2858821","volume":"41","author":"T Miyato","year":"2018","unstructured":"Miyato, T., Maeda, S.I., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1979\u20131993 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR40","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":"35_CR41","unstructured":"Oliver, A., Odena, A., Raffel, C.A., Cubuk, E.D., Goodfellow, I.: Realistic evaluation of deep semi-supervised learning algorithms. In: Advances in Neural Information Processing Systems, pp. 3235\u20133246 (2018)"},{"key":"35_CR42","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"35_CR43","doi-asserted-by":"crossref","unstructured":"Pathak, D., Girshick, R., Doll\u00e1r, P., Darrell, T., Hariharan, B.: Learning features by watching objects move. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2701\u20132710 (2017)","DOI":"10.1109\/CVPR.2017.638"},{"key":"35_CR44","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":"35_CR45","doi-asserted-by":"crossref","unstructured":"Prest, A., Leistner, C., Civera, J., Schmid, C., Ferrari, V.: Learning object class detectors from weakly annotated video. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3282\u20133289. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"35_CR46","unstructured":"Rasmus, A., Berglund, M., Honkala, M., Valpola, H., Raiko, T.: Semi-supervised learning with ladder networks. In: Advances in Neural Information Processing Systems, pp. 3546\u20133554 (2015)"},{"key":"35_CR47","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"35_CR48","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"35_CR49","doi-asserted-by":"crossref","unstructured":"Riloff, E., Wiebe, J.: Learning extraction patterns for subjective expressions. In: Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing, pp. 105\u2013112 (2003)","DOI":"10.3115\/1119355.1119369"},{"issue":"3","key":"35_CR50","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1109\/TIT.1965.1053799","volume":"11","author":"H Scudder","year":"1965","unstructured":"Scudder, H.: Probability of error of some adaptive pattern-recognition machines. IEEE Trans. Inf. Theory 11(3), 363\u2013371 (1965)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"35_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-01228-1_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"W Shi","year":"2018","unstructured":"Shi, W., Gong, Y., Ding, C., Ma, Z., Tao, X., Zheng, N.: Transductive semi-supervised deep learning using min-max features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 311\u2013327. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_19"},{"key":"35_CR52","doi-asserted-by":"crossref","unstructured":"Singh, K.K., Lee, Y.J.: You reap what you sow: using videos to generate high precision object proposals for weakly-supervised object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9414\u20139422 (2019)","DOI":"10.1109\/CVPR.2019.00964"},{"key":"35_CR53","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"35_CR54","doi-asserted-by":"crossref","unstructured":"Tang, P., Wang, X., Bai, X., Liu, W.: Multiple instance detection network with online instance classifier refinement. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2843\u20132851 (2017)","DOI":"10.1109\/CVPR.2017.326"},{"key":"35_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1007\/978-3-030-01252-6_22","volume-title":"Computer Vision \u2013 ECCV 2018","author":"P Tang","year":"2018","unstructured":"Tang, P., et al.: Weakly supervised region proposal network and object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 370\u2013386. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_22"},{"key":"35_CR56","doi-asserted-by":"crossref","unstructured":"Tang, Y., Wang, J., Gao, B., Dellandr\u00e9a, E., Gaizauskas, R., Chen, L.: Large scale semi-supervised object detection using visual and semantic knowledge transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2119\u20132128 (2016)","DOI":"10.1109\/CVPR.2016.233"},{"key":"35_CR57","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-030-01252-6_23","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Q Tao","year":"2018","unstructured":"Tao, Q., Yang, H., Cai, J.: Zero-annotation object detection with web knowledge transfer. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 387\u2013403. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_23"},{"key":"35_CR58","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems, pp. 1195\u20131204 (2017)"},{"key":"35_CR59","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096\u20131103 (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"35_CR60","doi-asserted-by":"crossref","unstructured":"Wang, K., Yan, X., Zhang, D., Zhang, L., Lin, L.: Towards human-machine cooperation: self-supervised sample mining for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1605\u20131613 (2018)","DOI":"10.1109\/CVPR.2018.00173"},{"key":"35_CR61","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Unsupervised learning of visual representations using videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2794\u20132802 (2015)","DOI":"10.1109\/ICCV.2015.320"},{"key":"35_CR62","unstructured":"Wei, X., Gong, B., Liu, Z., Lu, W., Wang, L.: Improving the improved training of Wasserstein GANs: a consistency term and its dual effect. arXiv preprint arXiv:1803.01541 (2018)"},{"key":"35_CR63","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"35_CR64","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S., Lin, D.: Unsupervised feature learning via non-parametric instance-level discrimination. arXiv preprint arXiv:1805.01978 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"35_CR65","unstructured":"Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised data augmentation. arXiv preprint arXiv:1904.12848 (2019)"},{"key":"35_CR66","doi-asserted-by":"crossref","unstructured":"Xie, Q., Hovy, E., Luong, M.T., Le, Q.V.: Self-training with noisy student improves ImageNet classification. arXiv preprint arXiv:1911.04252 (2019)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"35_CR67","unstructured":"Yalniz, I.Z., J\u00e9gou, H., Chen, K., Paluri, M., Mahajan, D.: Billion-scale semi-supervised learning for image classification. arXiv preprint arXiv:1905.00546 (2019)"},{"key":"35_CR68","unstructured":"Yan, Z., Liang, J., Pan, W., Li, J., Zhang, C.: Weakly-and semi-supervised object detection with expectation-maximization algorithm. arXiv preprint arXiv:1702.08740 (2017)"},{"key":"35_CR69","doi-asserted-by":"crossref","unstructured":"Yang, H., Wu, H., Chen, H.: Detecting 11K classes: large scale object detection without fine-grained bounding boxes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9805\u20139813 (2019)","DOI":"10.1109\/ICCV.2019.00990"},{"key":"35_CR70","doi-asserted-by":"crossref","unstructured":"Yang, K., Li, D., Dou, Y.: Towards precise end-to-end weakly supervised object detection network. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8372\u20138381 (2019)","DOI":"10.1109\/ICCV.2019.00846"},{"key":"35_CR71","doi-asserted-by":"crossref","unstructured":"Yang, Z., Mahajan, D., Ghadiyaram, D., Nevatia, R., Ramanathan, V.: Activity driven weakly supervised object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2917\u20132926 (2019)","DOI":"10.1109\/CVPR.2019.00303"},{"key":"35_CR72","doi-asserted-by":"crossref","unstructured":"Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In: 33rd Annual Meeting of the Association for Computational Linguistics, pp. 189\u2013196 (1995)","DOI":"10.3115\/981658.981684"},{"key":"35_CR73","doi-asserted-by":"crossref","unstructured":"Zeng, Z., Liu, B., Fu, J., Chao, H., Zhang, L.: WSOD2: learning bottom-up and top-down objectness distillation for weakly-supervised object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8292\u20138300 (2019)","DOI":"10.1109\/ICCV.2019.00838"},{"key":"35_CR74","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1007\/978-3-030-01246-5_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Zhao","year":"2018","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 587\u2013604. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_35"},{"key":"35_CR75","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58526-6_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:21:27Z","timestamp":1728174087000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58526-6_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585259","9783030585266"],"references-count":75,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58526-6_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"7 October 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}