{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:57:25Z","timestamp":1784822245336,"version":"3.55.0"},"reference-count":82,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T00:00:00Z","timestamp":1630627200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T00:00:00Z","timestamp":1630627200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61433007"],"award-info":[{"award-number":["61433007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876210"],"award-info":[{"award-number":["61876210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1007\/s11263-021-01515-2","type":"journal-article","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T21:30:27Z","timestamp":1630704627000},"page":"3051-3068","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1562,"title":["BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation"],"prefix":"10.1007","volume":"129","author":[{"given":"Changqian","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2736-3920","authenticated-orcid":false,"given":"Changxin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingbo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nong","family":"Sang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,3]]},"reference":[{"issue":"11","key":"1515_CR1","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & S\u00fcsstrunk, S. (2012). Slic superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2274\u20132282.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"12","key":"1515_CR2","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. (2017). SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12), 2481\u20132495.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1515_CR3","doi-asserted-by":"crossref","unstructured":"Bilinski, P., & Prisacariu, V. (2018). Dense decoder shortcut connections for single-pass semantic segmentation. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 6596\u20136605.","DOI":"10.1109\/CVPR.2018.00690"},{"key":"1515_CR4","unstructured":"Boykov, Y. Y., Jolly, M. P. (2001) Interactive graph cuts for optimal boundary and region segmentation of objects in nd images. In: Proc. IEEE International Conference on Computer Vision, vol\u00a01, pp. 105\u2013112."},{"key":"1515_CR5","doi-asserted-by":"crossref","unstructured":"Brostow, G. J., Shotton, J., Fauqueur, J., & Cipolla, R. (2008a). Segmentation and recognition using structure from motion point clouds. In: Proc. European Conference on Computer Vision, pp. 44\u201357.","DOI":"10.1007\/978-3-540-88682-2_5"},{"key":"1515_CR6","doi-asserted-by":"crossref","unstructured":"Brostow, G. J., Shotton, J., Fauqueur, J., & Cipolla, R. (2008b). Segmentation and recognition using structure from motion point clouds. In: Proc. European Conference on Computer Vision.","DOI":"10.1007\/978-3-540-88682-2_5"},{"key":"1515_CR7","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., & Ferrari, V. (2018). Coco-stuff: Thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 1209\u20131218.","DOI":"10.1109\/CVPR.2018.00132"},{"key":"1515_CR8","doi-asserted-by":"crossref","unstructured":"Chandra, S., Couprie, C., & Kokkinos, I. (2018). Deep spatio-temporal random fields for efficient video segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8915\u20138924.","DOI":"10.1109\/CVPR.2018.00929"},{"key":"1515_CR9","unstructured":"Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587."},{"key":"1515_CR10","unstructured":"Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2015). Semantic image segmentation with deep convolutional nets and fully connected crfs. In: Proceedings of the International Conference on Learning Representations."},{"key":"1515_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L. C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"issue":"4","key":"1515_CR12","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L Chen","year":"2018","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 834\u2013848. https:\/\/doi.org\/10.1109\/TPAMI.2017.2699184.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1515_CR13","unstructured":"Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Tran, J., Catanzaro, B., & Shelhamer, E. (2014). cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759."},{"key":"1515_CR14","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"1515_CR15","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223.","DOI":"10.1109\/CVPR.2016.350"},{"key":"1515_CR16","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., & Lu, H. (2019). Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1515_CR17","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving? The kitti vision benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 3354\u20133361.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"1515_CR18","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., & Fowlkes, C. C. (2016). LLaplacian pyramid reconstruction and refinement for semantic segmentation. In: Proceedings of the European Conference on Computer Vision, Springer, pp. 519\u2013534.","DOI":"10.1007\/978-3-319-46487-9_32"},{"key":"1515_CR19","unstructured":"Glorot, X., Bordes, A., & Bengio, Y. (2011). Glorot, X., Bordes, A., Bengio, Y. (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp. 315\u2013323."},{"key":"1515_CR20","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., & Malik, J. (2015). Hypercolumns for object segmentation and fine-grained localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 447\u2013456.","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"1515_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"1515_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1515_CR23","unstructured":"Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861."},{"key":"1515_CR24","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L. C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V., et al. (2019). Searching for mobilenetv3. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1314\u20131324.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"1515_CR25","doi-asserted-by":"crossref","unstructured":"Huang, P. Y., Hsu, W. T., Chiu, C. Y., Wu, T. F., & Sun, M. (2018). Efficient uncertainty estimation for semantic segmentation in videos. In: Proceedings of the European Conference on Computer Vision, pp. 520\u2013535.","DOI":"10.1007\/978-3-030-01246-5_32"},{"key":"1515_CR26","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"1515_CR27","unstructured":"Iandola, F. N., Moskewicz, M. W., Ashraf, K., Han, S., Dally, W. J., Keutzer, K. (2016) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and<1mb model size. arXiv preprint arXiv:1602.07360."},{"key":"1515_CR28","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the International Conference on Machine Learning, pp. 448\u2013456."},{"key":"1515_CR29","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G. E. (2012) Imagenet classification with deep convolutional neural networks. In: Proceedings of the Advances in Neural Information Processing Systems, vol.\u00a025, pp. 1097\u20131105."},{"key":"1515_CR30","doi-asserted-by":"crossref","unstructured":"Li, X., Liu, Z., Luo, P., Change Loy, C., & Tang, X. (2017). Not all pixels are equal: Difficulty-aware semantic segmentation via deep layer cascade. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3193\u20133202.","DOI":"10.1109\/CVPR.2017.684"},{"key":"1515_CR31","doi-asserted-by":"crossref","unstructured":"Li, H., Xiong, P., Fan, H., & Sun, J. (2019b). Dfanet: Deep feature aggregation for real-time semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9522\u20139531.","DOI":"10.1109\/CVPR.2019.00975"},{"key":"1515_CR32","unstructured":"Li, G., Yun, I., Kim, J., & Kim, J. (2019a). Dabnet: Depth-wise asymmetric bottleneck for real-time semantic segmentation. In: Proceedings of the British Machine Vision Conference."},{"key":"1515_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In: Proceedings of the European Conference on Computer Vision, Springer, pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1515_CR34","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., & Reid, I. (2017). Refinenet: Multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1925\u20131934.","DOI":"10.1109\/CVPR.2017.549"},{"key":"1515_CR35","unstructured":"Liu, W., Rabinovich, A., Berg, A. C. (2016) Parsenet: Looking wider to see better. arXiv preprint arXiv:1506.04579."},{"key":"1515_CR36","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1515_CR37","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H. T., & Sun, J. (2018). Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European Conference on Computer Vision, pp. 116\u2013131.","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"1515_CR38","unstructured":"Mazzini, D. (2018). Guided upsampling network for real-time semantic segmentation. In: Proceedings of the British Machine Vision Conference."},{"key":"1515_CR39","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Caspi, A., Shapiro, L., & Hajishirzi, H. (2018). Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 552\u2013568.","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"1515_CR40","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Shapiro, L. G., & Hajishirzi, H. (2019). spnetv2: A light-weight, power efficient, and general purpose convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9190\u20139200.","DOI":"10.1109\/CVPR.2019.00941"},{"key":"1515_CR41","doi-asserted-by":"publisher","first-page":"107611","DOI":"10.1016\/j.patcog.2020.107611","volume":"110","author":"M Orsic","year":"2021","unstructured":"Orsic, M., & Segvic, S. (2021). Efficient semantic segmentation with pyramidal fusion. Pattern Recognition, 110, 107611.","journal-title":"Pattern Recognition"},{"key":"1515_CR42","doi-asserted-by":"crossref","unstructured":"Orsic, M., Kreso, I., Bevandic, P., & Segvic, S. (2019). In defense of pre-trained imagenet architectures for real-time semantic segmentation of road-driving images. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12607\u201312616.","DOI":"10.1109\/CVPR.2019.01289"},{"issue":"1","key":"1515_CR43","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62\u201366.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"1515_CR44","unstructured":"Paszke A, Chaurasia A, Kim S, Culurciello E (2016) Enet: A deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147"},{"key":"1515_CR45","doi-asserted-by":"crossref","unstructured":"Peng, C., Zhang, X., Yu, G., Luo, G., & Sun, J. (2017). Large kernel matters\u2013improve semantic segmentation by global convolutional network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4353\u20134361.","DOI":"10.1109\/CVPR.2017.189"},{"key":"1515_CR46","doi-asserted-by":"crossref","unstructured":"Pohlen, T., Hermans, A., Mathias, M., & Leibe, B. (2017). 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.","DOI":"10.1109\/CVPR.2017.353"},{"key":"1515_CR47","unstructured":"Poudel, R. P., Bonde, U., Liwicki, S., & Zach, C. (2018). Contextnet: Exploring context and detail for semantic segmentation in real-time. In: Proceedings of the British Machine Vision Conference."},{"key":"1515_CR48","unstructured":"Poudel, R. P., Liwicki, S., & Cipolla, R. (2019). Fast-scnn: Fast semantic segmentation network. In: Proc. British Machine Vision Conference."},{"key":"1515_CR49","doi-asserted-by":"crossref","unstructured":"Ren, X., & Malik, J. (2003). Learning a classification model for segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, p.\u00a010\u201317.","DOI":"10.1109\/ICCV.2003.1238308"},{"issue":"1","key":"1515_CR50","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1109\/TITS.2017.2750080","volume":"19","author":"E Romera","year":"2018","unstructured":"Romera, E., Alvarez, J. M., Bergasa, L. M., & Arroyo, R. (2018). Erfnet: Efficient residual factorized convnet for real-time semantic segmentation. IEEE Transactions on Intelligent Transportation Systems, 19(1), 263\u2013272.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"1515_CR51","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, Springer, pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1515_CR52","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1145\/1015706.1015720","volume":"23","author":"C Rother","year":"2004","unstructured":"Rother, C., Kolmogorov, V., & Blake, A. (2004). Grabcut: Interactive foreground extraction using iterated graph cuts. ACM Transactions on Graphics (TOG), 23, 309\u2013314.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1515_CR53","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1515_CR54","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"issue":"4","key":"1515_CR55","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer, E., Long, J., & Darrell, T. (2017). Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4), 640\u2013651.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1515_CR56","doi-asserted-by":"crossref","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y. G., Chen, Y., & Xue, X. (2017). Dsod: Learning deeply supervised object detectors from scratch. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1919\u20131927.","DOI":"10.1109\/ICCV.2017.212"},{"key":"1515_CR57","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations."},{"key":"1515_CR58","doi-asserted-by":"crossref","unstructured":"Sturgess, P., Alahari, K., Ladicky, L., & Torr, P. H. S. (2009). Combining appearance and structure from motion features for road scene understanding. In: Proceedings of the British Machine Vision Conference.","DOI":"10.5244\/C.23.62"},{"key":"1515_CR59","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 31."},{"key":"1515_CR60","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., & Le, Q. V. (2019). Mnasnet: Platform-aware neural architecture search for mobile. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2820\u20132828.","DOI":"10.1109\/CVPR.2019.00293"},{"key":"1515_CR61","unstructured":"Treml, M., Arjona-Medina, J., Unterthiner, T., Durgesh, R., Friedmann, F., Schuberth, P., Mayr, A., Heusel, M., Hofmarcher, M., Widrich, M., et al. (2016). Speeding up semantic segmentation for autonomous driving. Proceeding of the Neural Information Processing Systems Workshops."},{"key":"1515_CR62","doi-asserted-by":"crossref","unstructured":"Van den Bergh, M., Boix, X., Roig, G., de Capitani, B., & Van Gool, L. (2012). Seeds: Superpixels extracted via energy-driven sampling. In: Proceedings of the European Conference on Computer Vision, pp. 13\u201326.","DOI":"10.1007\/978-3-642-33786-4_2"},{"issue":"6","key":"1515_CR63","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/34.87344","volume":"13","author":"L Vincent","year":"1991","unstructured":"Vincent, L., & Soille, P. (1991). Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(6), 583\u2013598.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1515_CR64","doi-asserted-by":"crossref","unstructured":"Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., & Cottrell, G. (2018a). Understanding convolution for semantic segmentation. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, IEEE, pp. 1451\u20131460.","DOI":"10.1109\/WACV.2018.00163"},{"key":"1515_CR65","unstructured":"Wang, R. J., Li, X., & Ling, C. X. (2018b). Pelee: A real-time object detection system on mobile devices. Proc (pp. 1967\u20131976). Advances in Neural Information Processing Systems: Curran Associates Inc."},{"key":"1515_CR66","doi-asserted-by":"crossref","unstructured":"Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., et al. (2020). Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2020.2983686.","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"1515_CR67","unstructured":"Wu, Z., Shen, C., Hengel Avd (2016) High-performance semantic segmentation using very deep fully convolutional networks. arXiv preprint arXiv:1604.04339"},{"key":"1515_CR68","doi-asserted-by":"crossref","unstructured":"Xie, S., & Tu, Z. (2015). Holistically-nested edge detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1395\u20131403.","DOI":"10.1109\/ICCV.2015.164"},{"key":"1515_CR69","unstructured":"Yu, F., & Koltun, V. (2016). Multi-scale context aggregation by dilated convolutions. In: Proceedings of the International Conference on Learning Representations."},{"key":"1515_CR70","doi-asserted-by":"crossref","unstructured":"Yu, C., Liu, Y., Gao, C., Shen, C., & Sang, N. (2020a). Representative graph neural network. In: Proceedings of the European Conference on Computer Vision, Springer, pp. 379\u2013396.","DOI":"10.1007\/978-3-030-58571-6_23"},{"key":"1515_CR71","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Gao, C., Yu, G., Shen, C., & Sang, N. (2020b). Context prior for scene segmentation. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 12416\u201312425.","DOI":"10.1109\/CVPR42600.2020.01243"},{"key":"1515_CR72","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., & Sang, N. (2018a). Bisenet: Bilateral segmentation network for real-time semantic segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 325\u2013341.","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"1515_CR73","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., & Sang, N. (2018b). Learning a discriminative feature network for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1857\u20131866.","DOI":"10.1109\/CVPR.2018.00199"},{"key":"1515_CR74","unstructured":"Yu, C., Xiao, B., Gao, C., Yuan, L., Zhang, L., Sang, N., & Wang, J. (2021). Lite-hrnet: A lightweight high-resolution network. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition. pp. 10440\u201310450."},{"key":"1515_CR75","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Huang, L., Guo, J., Zhang, C., Chen, X., & Wang, J. (2021). Ocnet: Object context network for scene parsing. International Journal of Computer Vision, 129, 2375\u20132398.","DOI":"10.1007\/s11263-021-01465-9"},{"key":"1515_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., & Agrawal, A. (2018a). Context encoding for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7151\u20137160.","DOI":"10.1109\/CVPR.2018.00747"},{"key":"1515_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018b). Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856.","DOI":"10.1109\/CVPR.2018.00716"},{"key":"1515_CR78","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qi, X., Shen, X., Shi, J., & Jia, J. (2018a). Icnet for real-time semantic segmentation on high-resolution images. In: Proceedings European Conference on Computer Vision, pp. 405\u2013420.","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"1515_CR79","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"key":"1515_CR80","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhang, Y., Liu, S., Shi, J., Loy, C. C., Lin, D., & Jia, J. (2018b). PSANet: Point-wise spatial attention network for scene parsing. In: Proceedings of the European Conference on Computer Vision, pp. 267\u2013283.","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"1515_CR81","doi-asserted-by":"crossref","unstructured":"Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., & Torr, P. H. (2015). Conditional random fields as recurrent neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1529\u20131537.","DOI":"10.1109\/ICCV.2015.179"},{"key":"1515_CR82","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Xiao, T., Fidler, S., Barriuso, A., et al. (2019). Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision, 127(3), 302\u2013321.","DOI":"10.1007\/s11263-018-1140-0"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01515-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01515-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01515-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T10:00:49Z","timestamp":1634464849000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01515-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,3]]},"references-count":82,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["1515"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01515-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,3]]},"assertion":[{"value":"5 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}