{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:50:57Z","timestamp":1778604657418,"version":"3.51.4"},"publisher-location":"Cham","reference-count":96,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585440","type":"print"},{"value":"9783030585457","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\/978-3-030-58545-7_40","type":"book-chapter","created":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T10:04:51Z","timestamp":1604484291000},"page":"695-714","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":110,"title":["Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation"],"prefix":"10.1007","author":[{"given":"Liang-Chieh","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raphael Gontijo","family":"Lopes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maxwell D.","family":"Collins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ekin D.","family":"Cubuk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barret","family":"Zoph","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hartwig","family":"Adam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathon","family":"Shlens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,5]]},"reference":[{"key":"40_CR1","unstructured":"Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (2016)"},{"key":"40_CR2","unstructured":"Abu-El-Haija, S., et al.: YouTube-8M: a large-scale video classification benchmark. arXiv:1609.08675 (2016)"},{"key":"40_CR3","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:1908.02983 (2019)","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Badrinarayanan, V., Galasso, F., Cipolla, R.: Label propagation in video sequences. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540054"},{"key":"40_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2461912.2462002","volume":"32","author":"S Bell","year":"2013","unstructured":"Bell, S., Upchurch, P., Snavely, N., Bala, K.: OpenSurfaces: a richly annotated catalog of surface appearance. ACM Trans. Graph. 32, 1\u201317 (2013)","journal-title":"ACM Trans. Graph."},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Budvytis, I., Sauer, P., Roddick, T., Breen, K., Cipolla, R.: Large scale labelled video data augmentation for semantic segmentation in driving scenarios. In: ICCV Workshop (2017)","DOI":"10.1109\/ICCVW.2017.36"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Castrejon, L., Kundu, K., Urtasun, R., Fidler, S.: Annotating object instances with a polygon-RNN. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.477"},{"key":"40_CR9","unstructured":"Chen, L.C., et al.: Searching for efficient multi-scale architectures for dense image prediction. In: NeurIPS (2018)"},{"key":"40_CR10","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: ICLR (2015)"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. In: IEEE TPAMI (2017)","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"40_CR12","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587 (2017)"},{"key":"40_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"40_CR14","unstructured":"Cheng, B., et al.: Panoptic-DeepLab. In: ICCV COCO + Mapillary Joint Recognition Challenge Workshop (2019)"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Cheng, B., et al.: Panoptic-DeepLab: a simple, strong, and fast baseline for bottom-up panoptic segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"40_CR18","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical data augmentation with no separate search. arXiv:1909.13719 (2019)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Boxsup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.191"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.167"},{"issue":"2","key":"40_CR21","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. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"40_CR22","unstructured":"Forsyth, D.A., Ponce, J.: Computer Vision: A Modern Approach. Prentice Hall Professional Technical Reference (2002)"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Gadde, R., Jampani, V., Gehler, P.V.: Semantic video CNNs through representation warping. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.477"},{"key":"40_CR24","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32, 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"40_CR25","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: CVPR (2018)"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"40_CR27","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbelaez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"40_CR29","unstructured":"H\u00e9naff, O.J., Razavi, A., Doersch, C., Eslami, S., Oord, A.v.d.: Data-efficient image recognition with contrastive predictive coding. arXiv:1905.09272 (2019)"},{"key":"40_CR30","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"40_CR31","unstructured":"Hong, S., Noh, H., Han, B.: Decoupled deep neural network for semi-supervised semantic segmentation. In: NeurIPS (2015)"},{"key":"40_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"40_CR33","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"40_CR34","doi-asserted-by":"crossref","unstructured":"Iscen, A., Tolias, G., Avrithis, Y., Chum, O.: Label propagation for deep semi-supervised learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00521"},{"key":"40_CR35","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Benenson, R., Hosang, J., Hein, M., Schiele, B.: Simple does it: weakly supervised instance and semantic segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.181"},{"key":"40_CR36","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"40_CR37","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"40_CR38","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"40_CR39","doi-asserted-by":"crossref","unstructured":"Kornblith, S., Shlens, J., Le, Q.V.: Do better imagenet models transfer better? In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00277"},{"key":"40_CR40","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NeurIPS (2012)"},{"key":"40_CR41","doi-asserted-by":"crossref","unstructured":"Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. (2017)","DOI":"10.1017\/S0140525X16001837"},{"key":"40_CR42","unstructured":"Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: ICML Workshop (2013)"},{"key":"40_CR43","unstructured":"Li, J., Raventos, A., Bhargava, A., Tagawa, T., Gaidon, A.: Learning to fuse things and stuff. arXiv:1812.01192 (2018)"},{"key":"40_CR44","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s11263-009-0265-6","volume":"88","author":"LJ Li","year":"2010","unstructured":"Li, L.J., Fei-Fei, L.: Optimol: automatic online picture collection via incremental model learning. IJCV 88, 147\u2013168 (2010). https:\/\/doi.org\/10.1007\/s11263-009-0265-6","journal-title":"IJCV"},{"key":"40_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-030-01267-0_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Q Li","year":"2018","unstructured":"Li, Q., Arnab, A., Torr, P.H.S.: Weakly- and semi-supervised panoptic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 106\u2013124. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_7"},{"key":"40_CR46","doi-asserted-by":"crossref","unstructured":"Li, Q., Qi, X., Torr, P.H.: Unifying training and inference for panoptic segmentation. arXiv:2001.04982 (2020)","DOI":"10.1109\/CVPR42600.2020.01333"},{"key":"40_CR47","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.472"},{"key":"40_CR48","doi-asserted-by":"crossref","unstructured":"Liang, J., Homayounfar, N., Ma, W.C., Xiong, Y., Hu, R., Urtasun, R.: Polytransform: deep polygon transformer for instance segmentation. arXiv:1912.02801 (2019)","DOI":"10.1109\/CVPR42600.2020.00915"},{"key":"40_CR49","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":"40_CR50","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Auto-DeepLab: hierarchical neural architecture search for semantic image segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00017"},{"key":"40_CR51","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"40_CR52","unstructured":"Liu, W., Rabinovich, A., Berg, A.C.: Parsenet: looking wider to see better. arXiv:1506.04579 (2015)"},{"key":"40_CR53","doi-asserted-by":"crossref","unstructured":"Luc, P., Neverova, N., Couprie, C., Verbeek, J., LeCun, Y.: Predicting deeper into the future of semantic segmentation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.77"},{"key":"40_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1007\/978-3-319-49409-8_66","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"SK Mustikovela","year":"2016","unstructured":"Mustikovela, S.K., Yang, M.Y., Rother, C.: Can ground truth label propagation from video help semantic segmentation? In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 804\u2013820. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_66"},{"key":"40_CR55","doi-asserted-by":"crossref","unstructured":"Neuhold, G., Ollmann, T., Bul\u00f2, S.R., Kontschieder, P.: The mapillary vistas dataset for semantic understanding of street scenes. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.534"},{"key":"40_CR56","doi-asserted-by":"crossref","unstructured":"Nilsson, D., Sminchisescu, C.: Semantic video segmentation by gated recurrent flow propagation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00713"},{"key":"40_CR57","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Chen, L.C., Murphy, K.P., Yuille, A.L.: Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.203"},{"key":"40_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-030-01264-9_17","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Papandreou","year":"2018","unstructured":"Papandreou, G., Zhu, T., Chen, L.-C., Gidaris, S., Tompson, J., Murphy, K.: PersonLab: person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 282\u2013299. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_17"},{"key":"40_CR59","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Darrell, T.: Constrained convolutional neural networks for weakly supervised segmentation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.209"},{"key":"40_CR60","unstructured":"Pinheiro, P.O., Collobert, R., Doll\u00e1r, P.: Learning to segment object candidates. In: NeurIPS (2015)"},{"key":"40_CR61","doi-asserted-by":"crossref","unstructured":"Porzi, L., Bul\u00f2, S.R., Colovic, A., Kontschieder, P.: Seamless scene segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00847"},{"key":"40_CR62","doi-asserted-by":"crossref","unstructured":"Porzi, L., Hofinger, M., Ruiz, I., Serrat, J., Bulo, S.R., Kontschieder, P.: Learning multi-object tracking and segmentation from automatic annotations. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00688"},{"key":"40_CR63","unstructured":"Qi, H., et al.: Deformable convolutional networks - COCO detection and segmentation challenge 2017 entry. In: ICCV COCO Challenge Workshop (2017)"},{"key":"40_CR64","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Doll\u00e1r, P., Girshick, R., Gkioxari, G., He, K.: Data distillation: towards omni-supervised learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00433"},{"key":"40_CR65","doi-asserted-by":"crossref","unstructured":"Real, E., Shlens, J., Mazzocchi, S., Pan, X., Vanhoucke, V.: YouTube-BoundingBoxes: a large high-precision human-annotated data set for object detection in video. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.789"},{"key":"40_CR66","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"40_CR67","doi-asserted-by":"crossref","unstructured":"Riloff, E., Wiebe, J.: Learning extraction patterns for subjective expressions. In: EMNLP (2003)","DOI":"10.3115\/1119355.1119369"},{"key":"40_CR68","doi-asserted-by":"crossref","unstructured":"Rosenberg, C., Hebert, M., Schneiderman, H.: Semi-supervised self-training of object detection models. WACV\/MOTION (2005)","DOI":"10.1109\/ACVMOT.2005.107"},{"key":"40_CR69","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115, 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"IJCV"},{"key":"40_CR70","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","volume":"77","author":"BC Russell","year":"2008","unstructured":"Russell, B.C., Torralba, A., Murphy, K.P., Freeman, W.T.: LabelMe: a database and web-based tool for image annotation. IJCV 77, 157\u2013173 (2008). https:\/\/doi.org\/10.1007\/s11263-007-0090-8","journal-title":"IJCV"},{"key":"40_CR71","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. Theor. 11, 363\u2013371 (1965)","journal-title":"IEEE Trans. Inf. Theor."},{"key":"40_CR72","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":"40_CR73","doi-asserted-by":"crossref","unstructured":"Souly, N., Spampinato, C., Shah, M.: Semi supervised semantic segmentation using generative adversarial network. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.606"},{"key":"40_CR74","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"40_CR75","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: Waymo open dataset. arXiv:1912.04838 (2019)"},{"key":"40_CR76","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: CVPR (2016)","DOI":"10.1109\/CVPR.2016.233"},{"key":"40_CR77","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., et al.: Mots: multi-object tracking and segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00813"},{"key":"40_CR78","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., Chen, L.C.: Axial-DeepLab: stand-alone axial-attention for panoptic segmentation. arXiv:2003.07853 (2020)","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"40_CR79","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: Understanding convolution for semantic segmentation. arXiv:1702.08502 (2017)","DOI":"10.1109\/WACV.2018.00163"},{"key":"40_CR80","unstructured":"Wei, Y., et al.: STC: a simple to complex framework for weakly-supervised semantic segmentation. In: IEEE TPAMI (2016)"},{"key":"40_CR81","doi-asserted-by":"crossref","unstructured":"Wei, Y., Xiao, H., Shi, H., Jie, Z., Feng, J., Huang, T.S.: Revisiting dilated convolution: a simple approach for weakly-and semi-supervised semantic segmentation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00759"},{"key":"40_CR82","unstructured":"Wu, J., Yildirim, I., Lim, J.J., Freeman, B., Tenenbaum, J.: Galileo: perceiving physical object properties by integrating a physics engine with deep learning. In: NeurIPS (2015)"},{"key":"40_CR83","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.patcog.2019.01.006","volume":"90","author":"Z Wu","year":"2019","unstructured":"Wu, Z., Shen, C., Van Den Hengel, A.: Wider or deeper: revisiting the ResNet model for visual recognition. Pattern Recogn. 90, 119\u2013133 (2019)","journal-title":"Pattern Recogn."},{"key":"40_CR84","doi-asserted-by":"crossref","unstructured":"Xie, Q., Hovy, E., Luong, M.T., Le, Q.V.: Self-training with noisy student improves imagenet classification. arXiv:1911.04252 (2019)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"40_CR85","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Liao, R., Zhao, H., Hu, R., Bai, M., Yumer, E., Urtasun, R.: UPSNet: a unified panoptic segmentation network. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00902"},{"key":"40_CR86","unstructured":"Yalniz, I.Z., J\u2019egou, H., Chen, K., Paluri, M., Mahajan, D.: Billion-scale semi-supervised learning for image classification. arXiv:1905.00546 (2019)"},{"key":"40_CR87","unstructured":"Yang, T.J., et al.: DeeperLab: single-shot image parser. arXiv:1902.05093 (2019)"},{"key":"40_CR88","doi-asserted-by":"crossref","unstructured":"Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In: ACL (1995)","DOI":"10.3115\/981658.981684"},{"key":"40_CR89","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. arXiv:1909.11065 (2019)","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"40_CR90","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. In: BMVC (2016)","DOI":"10.5244\/C.30.87"},{"key":"40_CR91","doi-asserted-by":"crossref","unstructured":"Zhai, X., Oliver, A., Kolesnikov, A., Beyer, L.: S4l: self-supervised semi-supervised learning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00156"},{"key":"40_CR92","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"40_CR93","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.405"},{"key":"40_CR94","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., Yuan, L., Wei, Y.: Deep feature flow for video recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.441"},{"key":"40_CR95","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Improving semantic segmentation via video propagation and label relaxation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00906"},{"key":"40_CR96","unstructured":"Zhu, Y., et al.: Improving semantic segmentation via self-training. arXiv:2004.14960 (2020)"}],"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\/978-3-030-58545-7_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T01:17:14Z","timestamp":1730683034000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58545-7_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585440","9783030585457"],"references-count":96,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58545-7_40","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":"5 November 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)"}}]}}