{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T19:25:12Z","timestamp":1783970712954,"version":"3.55.0"},"reference-count":38,"publisher":"Tsinghua University Press","issue":"1","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T00:00:00Z","timestamp":1635292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s41095-021-0235-7","type":"journal-article","created":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T12:03:16Z","timestamp":1635336196000},"page":"165-175","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Erroneous pixel prediction for semantic image segmentation"],"prefix":"10.26599","volume":"8","author":[{"given":"Lixue","family":"Gong","sequence":"first","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou 310058, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqun","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou 310058, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunke","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou 310058, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yin","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computing Clemson University, South Carolina, 29634, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou 310058, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"issue":"1","key":"235_CR1","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M.; Eslami, S. M. A.; van Gool, L.; Williams, C. K. I.; Winn, J.; Zisserman, A. The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision Vol. 111, No. 1, 98\u2013136, 2015.","journal-title":"International Journal of Computer Vision"},{"key":"235_CR2","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R.; Franke, U.; Roth, S.; Schiele, B. The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3213\u20133223, 2016.","DOI":"10.1109\/CVPR.2016.350"},{"key":"235_CR3","doi-asserted-by":"crossref","unstructured":"Zhou, B. L.; Zhao, H.; Puig, X.; Fidler, S.; Barriuso, A.; Torralba, A. Scene parsing through ADE20K dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 633\u2013641, 2017.","DOI":"10.1109\/CVPR.2017.544"},{"key":"235_CR4","doi-asserted-by":"crossref","unstructured":"Long, J.; Shelhamer, E.; Darrell, T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3431\u20133440, 2015.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"235_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O.; Fischer, P.; Brox, T. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention. Lecture Notes in Computer Science, Vol. 9351. Navab, N.; Hornegger, J.; Wells, W.; Frangi, A. Eds. Springer Cham, 234\u2013241, 2015."},{"key":"235_CR6","unstructured":"Chen, L.-C.; Papandreou, G.; Schrofi, F.; Adam, H. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587, 2017."},{"key":"235_CR7","doi-asserted-by":"crossref","unstructured":"Zhao, H.; Shi, J.; Qi, X.; Wang, X.; Jia, J. Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 6230\u20136239, 2017.","DOI":"10.1109\/CVPR.2017.660"},{"key":"235_CR8","unstructured":"Li, H.; Xiong, P.; An, J.; Wang, L. Pyramid attention network for semantic segmentation. arXiv preprint arXiv:1805.10180, 2018."},{"key":"235_CR9","doi-asserted-by":"crossref","unstructured":"Lin, G. S.; Milan, A.; Shen, C. H.; Reid, I. RefineNet: Multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5168\u20135177, 2017.","DOI":"10.1109\/CVPR.2017.549"},{"key":"235_CR10","doi-asserted-by":"crossref","unstructured":"Li, X.; Liu, Z.; Luo, P.; Loy, C. C.; Tang, X. Not all pixels are equal: Dificulty-aware semantic segmentation via deep layer cascade. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 6459\u20136468, 2017.","DOI":"10.1109\/CVPR.2017.684"},{"key":"235_CR11","unstructured":"Kendall, A.; Gal, Y. What uncertainties do we need in Bayesian deep learning for computer vision? In: Proceedings of the 31st Conference on Neural Information Processing Systems, 2017."},{"key":"235_CR12","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-ECCV 2018","author":"L C Chen","year":"2018","unstructured":"Chen, L. C.; Zhu, Y. K.; Papandreou, G.; Schroff, F.; Adam, H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Computer Vision-ECCV 2018. Lecture Notes in Computer Science, Vol. 11211. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 833\u2013851, 2018."},{"issue":"2","key":"235_CR13","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s13735-017-0141-z","volume":"7","author":"Y M Guo","year":"2018","unstructured":"Guo, Y. M.; Liu, Y.; Georgiou, T.; Lew, M. S. A review of semantic segmentation using deep neural networks. International Journal of Multimedia Information Retrieval Vol. 7, No. 2, 87\u201393, 2018.","journal-title":"International Journal of Multimedia Information Retrieval"},{"issue":"12","key":"235_CR14","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V.; Kendall, A.; Cipolla, R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 39, No. 12, 2481\u20132495, 2017.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"235_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-3-319-46487-9_32","volume-title":"Computer Vision-ECCV 2016","author":"G Ghiasi","year":"2016","unstructured":"Ghiasi, G.; Fowlkes, C. C. Laplacian pyramid reconstruction and refinement for semantic segmentation. In: Computer Vision-ECCV 2016. Lecture Notes in Computer Science, Vol. 9907. Leibe, B.; Matas, J.; Sebe, N.; Welling, M. Eds. Springer Cham, 519\u2013534, 2016."},{"key":"235_CR16","doi-asserted-by":"crossref","unstructured":"Peng, C.; Zhang, X. Y.; Yu, G.; Luo, G. M.; Sun, J. Large kernel matters\u2014improve semantic segmentation by global convolutional network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1743\u20131751, 2017.","DOI":"10.1109\/CVPR.2017.189"},{"key":"235_CR17","doi-asserted-by":"crossref","unstructured":"Ding, H. H.; Jiang, X. D.; Shuai, B.; Liu, A. Q.; Wang, G. Context contrasted feature and gated multi-scale aggregation for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2393\u20132402, 2018.","DOI":"10.1109\/CVPR.2018.00254"},{"key":"235_CR18","unstructured":"Liu, W.; Rabinovich, A.; Berg, A. C. ParseNet: Looking wider to see better. arXiv preprint arXiv:1506.04579, 2015."},{"key":"235_CR19","doi-asserted-by":"crossref","unstructured":"Hu, J.; Shen, L.; Sun, G. Squeeze-and-excitation networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 7132\u20137141, 2018.","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"4","key":"235_CR20","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L C Chen","year":"2018","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. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 40, No. 4, 834\u2013848, 2018.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"235_CR21","unstructured":"Chen, L.-C.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A. L. Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv preprint arXiv:1412.7062, 2014."},{"key":"235_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, H.; Dana, K., Shi, J. P.; Zhang, Z. Y.; Wang, X. G.; Tyagi, A.; Agrawal, A. Context encoding for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 7151\u20137160, 2018.","DOI":"10.1109\/CVPR.2018.00747"},{"key":"235_CR23","doi-asserted-by":"crossref","unstructured":"Sun, K.; Xiao, B.; Liu, D.; Wang, J. D. Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5686\u20135696, 2019.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"235_CR24","unstructured":"Chen, L.-C.; Collins, M.; Zhu, Y.; Papandreou, G.; Zoph, B.; Schrofi, F.; Adam, H.; Shlens, J. Searching for efficient multi-scale architectures for dense image prediction. In: Proceedings of the 32nd Conference on Neural Information Processing Systems, 8713\u20138724, 2018."},{"key":"235_CR25","doi-asserted-by":"crossref","unstructured":"Nekrasov, V.; Chen, H.; Shen, C. H.; Reid, I. Fast neural architecture search of compact semantic segmentation models via auxiliary cells. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 9118\u20139127, 2019.","DOI":"10.1109\/CVPR.2019.00934"},{"key":"235_CR26","doi-asserted-by":"crossref","unstructured":"Liu, C. X.; Chen, L. C.; Schroff, F.; Adam, H.; Hua, W.; Yuille, A. L.; Fei-Fei, L. Auto-DeepLab: Hierarchical neural architecture search for semantic image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 82\u201392, 2019.","DOI":"10.1109\/CVPR.2019.00017"},{"key":"235_CR27","doi-asserted-by":"crossref","unstructured":"Viola, P.; Jones, M. Rapid object detection using a boosted cascade of simple features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 511\u2013518, 2001.","DOI":"10.1109\/CVPR.2001.990517"},{"key":"235_CR28","unstructured":"Lienhart, R.; Maydt, J. An extended set of Haar-like features for rapid object detection. In: Proceedings of the International Conference on Image Processing, 2002."},{"key":"235_CR29","doi-asserted-by":"crossref","unstructured":"Pang, J. H.; Sun, W. X.; Ren, J. S.; Yang, C. X.; Yan, Q. Cascade residual learning: A two-stage convolutional neural network for stereo matching. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, 878\u2013886, 2017.","DOI":"10.1109\/ICCVW.2017.108"},{"key":"235_CR30","doi-asserted-by":"crossref","unstructured":"Li, H. X.; Lin, Z.; Shen, X. H.; Brandt, J.; Hua, G. A convolutional neural network cascade for face detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5325\u20135334, 2015.","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"235_CR31","unstructured":"Iofie, S.; Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167, 2015."},{"key":"235_CR32","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research Vol. 15, 1929\u20131958, 2014.","journal-title":"Journal of Machine Learning Research"},{"key":"235_CR33","unstructured":"Kingma, D.; Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014."},{"key":"235_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01261-8_1","volume-title":"Computer Vision-ECCV 2018","author":"Y Wu","year":"2018","unstructured":"Wu, Y.; He, K. Group normalization. In: Computer Vision-ECCV 2018. Lecture Notes in Computer Science, Vol. 11217. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 3\u201319, 2018."},{"key":"235_CR35","doi-asserted-by":"crossref","unstructured":"Tian, Z.; He, T.; Shen, C. H.; Yan, Y. L. Decoders matter for semantic segmentation: Data-dependent decoding enables flexible feature aggregation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3121\u20133130, 2019.","DOI":"10.1109\/CVPR.2019.00324"},{"key":"235_CR36","doi-asserted-by":"crossref","unstructured":"Yu, H.; Zhang, Z. N.; Qin, Z.; Wu, H.; Li, D. S.; Zhao, J.; Lu, X. Loss rank mining: A general hard example mining method for real-time detectors. In: Proceedings of the International Joint Conference on Neural Networks, 2018.","DOI":"10.1109\/IJCNN.2018.8489071"},{"key":"235_CR37","unstructured":"Yu, F.; Koltun, V. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122, 2015."},{"issue":"3","key":"235_CR38","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B.; Zhao, H.; Puig, X.; Xiao, T.; Fidler, S.; Barriuso, A.; Torralba, A. Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision Vol. 127, No. 3, 302\u2013321, 2019.","journal-title":"International Journal of Computer Vision"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-021-0235-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41095-021-0235-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-021-0235-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10897562\/10897574.pdf?arnumber=10897574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:38:40Z","timestamp":1762367920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10897574\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":38,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1007\/s41095-021-0235-7","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2022,3]]},"assertion":[{"value":"13 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}