{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T11:36:21Z","timestamp":1762083381294,"version":"build-2065373602"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T00:00:00Z","timestamp":1674086400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T00:00:00Z","timestamp":1674086400000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s00138-023-01373-7","type":"journal-article","created":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T19:25:27Z","timestamp":1674156327000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Dual Context Network for real-time semantic segmentation"],"prefix":"10.1007","volume":"34","author":[{"given":"Hong","family":"Yin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanfa","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yajun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,19]]},"reference":[{"issue":"12","key":"1373_CR1","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 Trans Pattern Anal Mach Intell 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1373_CR2","unstructured":"Paszke, A., Chaurasia, A., Kim,S., Culurciello, E.: Enet: a deep neural network architecture for real-time semantic segmentation (2016)"},{"key":"1373_CR3","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Caspi, A., Shapiro, L., Hajishirzi, H.: Espnet: efficient spatial pyramid of dilated convolutions for semantic segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 552\u2013568 (2018)","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"1373_CR4","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C. Gao, C., Yu, G., Sang, N.: Bisenet: bilateral segmentation network for real-time semantic segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 325\u2013341 (2018)","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"1373_CR5","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: Icnet for real-time semantic segmentation on high-resolution images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 405\u2013420 (2018)","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"1373_CR6","doi-asserted-by":"crossref","unstructured":"Li, H., Xiong, P., Fan, H., Sun, J.: Dfanet: deep feature aggregation for real-time semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9522\u20139531 (2019).","DOI":"10.1109\/CVPR.2019.00975"},{"key":"1373_CR7","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":"1373_CR8","doi-asserted-by":"crossref","unstructured":"Cordts, M. et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"issue":"2","key":"1373_CR9","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"GJ Brostow","year":"2009","unstructured":"Brostow, G.J., Fauqueur, J., Cipolla, R.J.: Semantic object classes in video: a high-definition ground truth database. Pattern Recognit. Lett. 30(2), 88\u201397 (2009)","journal-title":"Pattern Recognit. Lett."},{"key":"1373_CR10","unstructured":"Wu, Z., Shen, C., Hengel, A.: Real-time semantic image segmentation via spatial sparsity (2017)"},{"key":"1373_CR11","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1373_CR12","unstructured":"Liu, W., Rabinovich, A., Berg, A. C.: Parsenet: Looking wider to see better (2015)"},{"key":"1373_CR13","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1373_CR14","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1373_CR15","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation (2017)"},{"key":"1373_CR16","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, pp. 2881\u20132890 (2017).","DOI":"10.1109\/CVPR.2017.660"},{"key":"1373_CR17","doi-asserted-by":"crossref","unstructured":"Yang, M., Yu, K., Zhang, C., Li, Z.,. Yang, K: Denseaspp for semantic segmentation in street scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3684\u20133692 (2018)","DOI":"10.1109\/CVPR.2018.00388"},{"key":"1373_CR18","unstructured":"Yuan, Y., Wang, J.: Ocnet: Object context network for scene parsing (2018)"},{"key":"1373_CR19","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Learning a discriminative feature network for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1857\u20131866 (2018)","DOI":"10.1109\/CVPR.2018.00199"},{"key":"1373_CR20","doi-asserted-by":"crossref","unstructured":"Orsic, M., Kreso, I., Bevandic, P., Segvic, S.: In defense of pre-trained imagenet architectures for real-time semantic segmentation of road-driving images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12607\u201312616 (2019)","DOI":"10.1109\/CVPR.2019.01289"},{"key":"1373_CR21","unstructured":"Lin, Z. et al.: A structured self-attentive sentence embedding (2017)"},{"issue":"1","key":"1373_CR22","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1109\/TITS.2017.2750080","volume":"19","author":"E Romera","year":"2017","unstructured":"Romera, E., Alvarez, J.M., Bergasa, L.M., Arroyo, R.: \"Erfnet: efficient residual factorized convnet for real-time semantic segmentation. IEEE Trans. Intell. Transp. Syst. 19(1), 263\u2013272 (2017)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1373_CR23","unstructured":"Howard A. et al.: Searching for mobilenetv3. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1314\u20131324"},{"key":"1373_CR24","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"1373_CR25","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision (ECCV), pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"1373_CR26","doi-asserted-by":"crossref","unstructured":"Fu, J. et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1373_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H. et al.: Context encoding for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7151\u20137160 (2018)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"1373_CR28","doi-asserted-by":"crossref","unstructured":"Sturgess, P., Alahari, K., Ladicky, L., Torr, P. H.: Combining appearance and structure from motion features for road scene understanding (2009)","DOI":"10.5244\/C.23.62"},{"key":"1373_CR29","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: Thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"1373_CR30","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y. et al.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1373_CR31","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, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"4","key":"1373_CR32","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","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 Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1373_CR33","doi-asserted-by":"crossref","unstructured":"Wang, P. et al.: Understanding convolution for semantic segmentation. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1451\u20131460, IEEE (2018)","DOI":"10.1109\/WACV.2018.00163"},{"key":"1373_CR34","doi-asserted-by":"crossref","unstructured":"Ding, H., Jiang, X., Shuai, B., Qun Liu, A., Wang, G.: Context contrasted feature and gated multi-scale aggregation for scene segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2393\u20132402 (2018)","DOI":"10.1109\/CVPR.2018.00254"},{"key":"1373_CR35","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: Shufflenet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"1373_CR36","doi-asserted-by":"crossref","unstructured":"Pohlen, T., Hermans, A., Mathias, M., Leibe, B.: Full-resolution residual networks for semantic segmentation in street scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4151\u20134160 (2017)","DOI":"10.1109\/CVPR.2017.353"},{"key":"1373_CR37","doi-asserted-by":"crossref","unstructured":"Pan, X., Shi, J., Luo, P., Wang, X., Tang, X.: Spatial as deep: Spatial CNN for traffic scene understanding. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12301"},{"key":"1373_CR38","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: Ccnet: Criss-cross attention for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"1373_CR39","unstructured":"Li, H., Xiong, P. An, J., Wang, L.: Pyramid attention network for semantic segmentation. arXiv 2018"},{"key":"1373_CR40","doi-asserted-by":"crossref","unstructured":"Zheng, S. et al.: Conditional random fields as recurrent neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1529\u20131537 (2015)","DOI":"10.1109\/ICCV.2015.179"},{"key":"1373_CR41","unstructured":"Liu, Y., Cao, S., Lasang, P., Shen, S.: Modular lightweight network for road object detection using a feature fusion approach. IEEE Trans. Syst. Man Cybern. Syst. pp 1\u201313 (2019)"},{"issue":"9","key":"1373_CR42","first-page":"2489","volume":"47","author":"L Khelifi","year":"2017","unstructured":"Khelifi, L., Mignotte, M.: A novel fusion approach based on the global consistency criterion to fusing multiple segmentations. IEEE Trans. Syst. Man Cybern. Syst. 47(9), 2489\u20132502 (2017)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"7","key":"1373_CR43","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1109\/TSMC.2016.2587483","volume":"47","author":"X Yuan","year":"2017","unstructured":"Yuan, X., Cao, X., Hao, X., Chen, H., Wei, X.: Vehicle detection by a context-aware multichannel feature pyramid. IEEE Trans. Syst. Man Cybern. Syst. 47(7), 1348\u20131357 (2017)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"4","key":"1373_CR44","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1109\/TSMC.2016.2623683","volume":"47","author":"Y Li","year":"2017","unstructured":"Li, Y., Guo, Y., Kao, Y., He, R.: Image piece learning for weakly supervised semantic segmentation. IEEE Trans. Syst. Man Cybern. Syst. 47(4), 648\u2013659 (2017)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"7","key":"1373_CR45","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1109\/TSMC.2016.2645660","volume":"48","author":"J Si","year":"2018","unstructured":"Si, J., Zhang, H., Li, C., Guo, J.: Spatial pyramid-based statistical features for person re-identification: a comprehensive evaluation. IEEE Trans. Syst. Man Cybern. Syst. 48(7), 1140\u20131154 (2018)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"1373_CR46","doi-asserted-by":"crossref","unstructured":"Chen, B., Collins, M., Zhu, Y., Liu, T., Huang, T., Adam, H., Chen, L.: Panoptic-deeplab: a simple, strong, and fast baseline for bottom-up panoptic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01249"},{"issue":"9","key":"1373_CR47","doi-asserted-by":"publisher","first-page":"2990","DOI":"10.1109\/TPAMI.2020.3044416","volume":"43","author":"J Fang","year":"2021","unstructured":"Fang, J., Sun, Y., Zhang, Q., Peng, K., Li, Y., Liu, W., Wang, X.: FNA++: fast network adaptation via parameter remapping and architecture search. IEEE Trans. Pattern Anal. Mach. Intell. 43(9), 2990\u20133004 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1373_CR48","doi-asserted-by":"crossref","unstructured":"Li, X., You, A., Zhu, Z., Zhao, H., Yang, M., Yang, K., Tan, S., Tong, Y.: Semantic flow for fast and accurate scene parsing. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"1373_CR49","doi-asserted-by":"crossref","unstructured":"Fang, C., Tian., H., Zhang, D, Zhang, Q., Han, J., Han, J.: Densely nested top-down flows for salient object detection. Sci. China Inf. Sci. (2022)","DOI":"10.1007\/s11432-021-3384-y"},{"key":"1373_CR50","doi-asserted-by":"crossref","unstructured":"Liu, N., Han, J.: DHSNet: deep hierarchical saliency network for salient object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.80"},{"key":"1373_CR51","doi-asserted-by":"crossref","unstructured":"Liu, N., Han, J., Yang, M.: PiCANet: learning pixel-wise contextual attention for saliency detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00326"},{"key":"1373_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, J., Liu, J.-J., Fan, D.-P., Cao, Y., Yang, J., Cheng, M.-M.: EGNet: Edge guidance network for salient object detection. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8779\u20138788 (2019)","DOI":"10.1109\/ICCV.2019.00887"},{"key":"1373_CR53","doi-asserted-by":"publisher","first-page":"5862","DOI":"10.1109\/TIP.2021.3088282","volume":"30","author":"N Liu","year":"2021","unstructured":"Liu, N., Zhao, W., Shao, L., Han, J.: SCG: saliency and contour guided salient instance segmentation. IEEE Trans. Image Process. 30, 5862\u20135874 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"1373_CR54","unstructured":"Zhang, D., Zeng, W., Guo, G., Fang, C., Cheng, L., Han. J.: Weakly supervised semantic segmentation via alternative self-dual teaching. arXiv preprint arXiv:2112.09459 (2021)"},{"issue":"6","key":"1373_CR55","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.3046647","volume":"44","author":"D Zhang","year":"2022","unstructured":"Zhang, D., Zeng, W., Yao, J., Han, J.: Weakly supervised object detection using proposal-and semantic-level relationships. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3349\u20133363 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"1373_CR56","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1109\/TPAMI.2018.2881114","volume":"42","author":"D Zhang","year":"2020","unstructured":"Zhang, D., Han, J., Yang, L., Xu, D.: SPFTN: a joint learning framework for localizing and segmenting objects in weakly labeled videos. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 475\u2013489 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01373-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-023-01373-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01373-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T03:06:27Z","timestamp":1679454387000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-023-01373-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,19]]},"references-count":56,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["1373"],"URL":"https:\/\/doi.org\/10.1007\/s00138-023-01373-7","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"type":"print","value":"0932-8092"},{"type":"electronic","value":"1432-1769"}],"subject":[],"published":{"date-parts":[[2023,1,19]]},"assertion":[{"value":"20 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"22"}}