{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:56:20Z","timestamp":1783439780810,"version":"3.54.6"},"reference-count":75,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T00:00:00Z","timestamp":1621814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T00:00:00Z","timestamp":1621814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s11263-021-01465-9","type":"journal-article","created":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T09:03:12Z","timestamp":1621846992000},"page":"2375-2398","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":234,"title":["OCNet: Object Context for Semantic Segmentation"],"prefix":"10.1007","volume":"129","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8345-4205","authenticated-orcid":false,"given":"Yuhui","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyuan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,5,24]]},"reference":[{"key":"1465_CR1","doi-asserted-by":"crossref","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.","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"1465_CR2","doi-asserted-by":"crossref","unstructured":"Bul\u00f2, S.R., Porzi, L., & Kontschieder, P. (2018). In-place activated batchnorm for memory-optimized training of dnns. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp 5639\u20135647.","DOI":"10.1109\/CVPR.2018.00591"},{"key":"1465_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J.R.R., & Ferrari, V. (2018). Coco-stuff: Thing and stuff classes in context. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp 1209\u20131218.","DOI":"10.1109\/CVPR.2018.00132"},{"key":"1465_CR4","unstructured":"Chen, L., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. CoRR. arXiv:1706.05587."},{"issue":"4","key":"1465_CR5","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.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1465_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, B., Chen, L., Wei, Y., Zhu, Y., Huang, Z., Xiong, J., Huang, T.S., Hwu, W., & Shi, H. (2019). Spgnet: Semantic prediction guidance for scene parsing. In: 2019 IEEE\/CVF international conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp 5217\u20135227.","DOI":"10.1109\/ICCV.2019.00532"},{"key":"1465_CR7","unstructured":"Child, R., Gray, S., Radford, A., & Sutskever, I. (2019). Generating long sequences with sparse transformers. CoRR. arXiv:1904.10509."},{"key":"1465_CR8","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: 2016 IEEE conference on computer vision and pattern recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pp 3213\u20133223.","DOI":"10.1109\/CVPR.2016.350"},{"key":"1465_CR9","doi-asserted-by":"crossref","unstructured":"Ding, H., Jiang, X., Shuai, B., Liu, A.Q., & Wang, G. (2018). Context contrasted feature and gated multi-scale aggregation for scene segmentation. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp 2393\u20132402.","DOI":"10.1109\/CVPR.2018.00254"},{"key":"1465_CR10","doi-asserted-by":"crossref","unstructured":"Ding, H., Jiang, X., Liu, A.Q., Magnenat-Thalmann, N., & Wang, G. (2019a). Boundary-aware feature propagation for scene segmentation. In: 2019 IEEE\/CVF international conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp 6818\u20136828.","DOI":"10.1109\/ICCV.2019.00692"},{"key":"1465_CR11","doi-asserted-by":"crossref","unstructured":"Ding, H., Jiang, X., Shuai, B., Liu, A.Q., & Wang, G. (2019b). Semantic correlation promoted shape-variant context for segmentation. In: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp 8885\u20138894.","DOI":"10.1109\/CVPR.2019.00909"},{"key":"1465_CR12","doi-asserted-by":"crossref","unstructured":"Divvala, S. K., Hoiem, D., Hays, J., Efros, A. A., & Hebert, M. (2009). An empirical study of context in object detection. 2009 IEEE computer society conference on computer vision and pattern recognition (CVPR 2009), 20\u201325 June 2009 (pp. 1271\u20131278). Miami: Florida, USA.","DOI":"10.1109\/CVPRW.2009.5206532"},{"key":"1465_CR13","doi-asserted-by":"crossref","unstructured":"Ferrari, V., Hebert, M., Sminchisescu, C., & Weiss, Y. (eds) (2018). Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part I, Lecture Notes in Computer Science, vol 11205, Springer.","DOI":"10.1007\/978-3-030-01228-1"},{"key":"1465_CR14","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., & Lu, H. (2019a). Dual attention network for scene segmentation. In: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp 3146\u20133154.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1465_CR15","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Wang, Y., Li, Y., Bao, Y., Tang, J., & Lu, H. (2019b). Adaptive context network for scene parsing. In: 2019 IEEE\/CVF international conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp 6747\u20136756.","DOI":"10.1109\/ICCV.2019.00685"},{"key":"1465_CR16","doi-asserted-by":"crossref","unstructured":"Gong, K., Liang, X., Zhang, D., Shen, X., & Lin, L. (2017). Look into person: Self-supervised structure-sensitive learning and a new benchmark for human parsing. In: 2017 IEEE conference on computer vision and pattern recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp 6757\u20136765.","DOI":"10.1109\/CVPR.2017.715"},{"key":"1465_CR17","doi-asserted-by":"crossref","unstructured":"Gonzalez-Garcia, A., Modolo, D., & Ferrari, V. (2018). Objects as context for detecting their semantic parts. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp 6907\u20136916.","DOI":"10.1109\/CVPR.2018.00722"},{"key":"1465_CR18","unstructured":"Greenspun, P. (1999). Philip and Alex\u2019s guide to Web publishing. Morgan Kaufmann."},{"key":"1465_CR19","doi-asserted-by":"crossref","unstructured":"He, J., Deng, Z., Zhou, L., Wang, Y., & Qiao, Y. (2019). Adaptive pyramid context network for semantic segmentation. In: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp 7519\u20137528.","DOI":"10.1109\/CVPR.2019.00770"},{"key":"1465_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pp 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1465_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R.B. (2017). Mask R-CNN. In: IEEE international conference on computer vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pp 2980\u20132988.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1465_CR22","unstructured":"Hoyer, L., Munoz, M., Katiyar, P., Khoreva, A., Fischer, V., & (2019) Grid saliency for context explanations of semantic segmentation. In: Advances in neural information processing systems 32: Annual conference on neural information processing systems 2019, NeurIPS 2019(December), pp. 8\u201314, . (2019). Vancouver (pp. 6459\u20136470). Canada: BC."},{"key":"1465_CR23","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., & Liu, W. (2019). Ccnet: Criss-cross attention for semantic segmentation. In: 2019 IEEE\/CVF international conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp 603\u2013612.","DOI":"10.1109\/ICCV.2019.00069"},{"key":"1465_CR24","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd international conference on machine learning, ICML 2015, Lille, France, 6-11 July 2015, pp 448\u2013456."},{"key":"1465_CR25","doi-asserted-by":"crossref","unstructured":"Kong, S., & Fowlkes, C.C. (2018). Recurrent scene parsing with perspective understanding in the loop. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp 956\u2013965.","DOI":"10.1109\/CVPR.2018.00106"},{"issue":"1","key":"1465_CR26","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., et al. (2017). Visual genome: Connecting language and vision using crowdsourced dense image annotations. International Journal of Computer Vision, 123(1), 32\u201373.","journal-title":"International Journal of Computer Vision"},{"key":"1465_CR27","doi-asserted-by":"crossref","unstructured":"Kuo, W., Angelova, A., Malik, J., & Lin, T. (2019). Shapemask: Learning to segment novel objects by refining shape priors. In: 2019 IEEE\/CVF international conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp 9206\u20139215.","DOI":"10.1109\/ICCV.2019.00930"},{"key":"1465_CR28","doi-asserted-by":"crossref","unstructured":"Li, X., Zhong, Z., Wu, J., Yang, Y., Lin, Z., & Liu, H. (2019). Expectation-maximization attention networks for semantic segmentation. In: 2019 IEEE\/CVF international conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp 9166\u20139175.","DOI":"10.1109\/ICCV.2019.00926"},{"key":"1465_CR29","unstructured":"Li, Y., & Gupta, A. (2018). Beyond grids: Learning graph representations for visual recognition. In: Advances in neural information processing systems 31: Annual conference on neural information processing systems 2018, NeurIPS 2018, December 3-8, 2018, Montr\u00e9al, Canada, pp 9245\u20139255."},{"key":"1465_CR30","unstructured":"Liang, X., Hu, Z., Zhang, H., Lin, L., & Xing, E.P. (2018a). Symbolic graph reasoning meets convolutions. In: Advances in neural information processing systems 31: Annual conference on neural information processing systems 2018, NeurIPS 2018, December 3-8, 2018, Montr\u00e9al, Canada, pp 1858\u20131868."},{"key":"1465_CR31","doi-asserted-by":"crossref","unstructured":"Liang, X., Zhou, H., & Xing, E.P. (2018b). Dynamic-structured semantic propagation network. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp 752\u2013761.","DOI":"10.1109\/CVPR.2018.00085"},{"issue":"4","key":"1465_CR32","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1109\/TPAMI.2018.2820063","volume":"41","author":"X Liang","year":"2019","unstructured":"Liang, X., Gong, K., Shen, X., & Lin, L. (2019). Look into person: Joint body parsing & pose estimation network and a new benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(4), 871\u2013885.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1465_CR33","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., & Reid, I.D. (2017a). Refinenet: Multi-path refinement networks for high-resolution semantic segmentation. In: 2017 IEEE conference on computer vision and pattern recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp 5168\u20135177.","DOI":"10.1109\/CVPR.2017.549"},{"key":"1465_CR34","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S.J., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.L. (2014). Microsoft COCO: common objects in context. In: Computer Vision - ECCV 2014 - 13th European conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V, pp 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1465_CR35","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., & Belongie, S.J. (2017b). Feature pyramid networks for object detection. In: 2017 IEEE conference on computer vision and pattern recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp 936\u2013944.","DOI":"10.1109\/CVPR.2017.106"},{"key":"1465_CR36","unstructured":"Liu, W., Rabinovich, A., & Berg, A. C. (2015). ParseNet: Looking wider to see better. CoRR. arXiv:1506.04579."},{"key":"1465_CR37","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zheng, Z., Zheng, L., Guan, T., Yu, J., & Yang, Y. (2018). Macro-micro adversarial network for human parsing. In: Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IX, pp 424\u2013440.","DOI":"10.1007\/978-3-030-01240-3_26"},{"key":"1465_CR38","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H., & Sun, J. (2018). Shufflenet V2: practical guidelines for efficient CNN architecture design. In: Computer Vision - ECCV 2018 - 15th European conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIV, pp 122\u2013138.","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"1465_CR39","unstructured":"Massa, F., & Girshick, R. (2018). Maskrcnn-benchmark: Fast, modular reference implementation of instance segmentation and object detection algorithms in PyTorch. https:\/\/github.com\/facebookresearch\/maskrcnn-benchmark."},{"key":"1465_CR40","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Chen, X., Liu, X., Cho, N., Lee, S., Fidler, S., Urtasun, R., & Yuille, A.L. (2014). The role of context for object detection and semantic segmentation in the wild. In: 2014 IEEE conference on computer vision and pattern recognition, CVPR 2014, Columbus, OH, USA, June 23-28, 2014, pp 891\u2013898.","DOI":"10.1109\/CVPR.2014.119"},{"key":"1465_CR41","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., & Yan, S. (2018). Mutual learning to adapt for joint human parsing and pose estimation. In: Computer Vision - ECCV 2018 - 15th European conference, Munich, Germany, September 8-14, 2018, Proceedings, Part V, pp 519\u2013534.","DOI":"10.1007\/978-3-030-01228-1_31"},{"key":"1465_CR42","doi-asserted-by":"crossref","unstructured":"Pang, Y., Li, Y., Shen, J., & Shao, L. (2019). Towards bridging semantic gap to improve semantic segmentation. In: 2019 IEEE\/CVF International conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp 4229\u20134238.","DOI":"10.1109\/ICCV.2019.00433"},{"key":"1465_CR43","unstructured":"Roelofs, G., & Koman, R. (1999) PNG: the definitive guide. O\u2019Reilly & Associates, Inc."},{"key":"1465_CR44","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015 - 18th International conference Munich, Germany, October 5 - 9, 2015, Proceedings, Part III, pp 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1465_CR45","doi-asserted-by":"crossref","unstructured":"Ruan, T., Liu, T., Huang, Z., Wei, Y., Wei, S., & Zhao, Y. (2019). Devil in the details: Towards accurate single and multiple human parsing. In: The Thirty-Third AAAI conference on artificial intelligence, AAAI 2019, The Thirty-first innovative applications of artificial intelligence conference, IAAI 2019, The Ninth AAAI symposium on educational advances in artificial intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019, pp 4814\u20134821.","DOI":"10.1609\/aaai.v33i01.33014814"},{"issue":"4","key":"1465_CR46","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":"1465_CR47","unstructured":"Shen, Z., Zhang, M., Zhao, H., Yi, S., & Li, H. (2018). Efficient attention: Attention with linear complexities. arXiv:1812.01243."},{"key":"1465_CR48","doi-asserted-by":"crossref","unstructured":"Shetty, R., Schiele, B., & Fritz, M. (2019). Not using the car to see the sidewalk - quantifying and controlling the effects of context in classification and segmentation. In: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp 8218\u20138226.","DOI":"10.1109\/CVPR.2019.00841"},{"issue":"6","key":"1465_CR49","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2017.2712691","volume":"40","author":"B Shuai","year":"2018","unstructured":"Shuai, B., Zuo, Z., Wang, B., & Wang, G. (2018). Scene segmentation with dag-recurrent neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1480\u20131493.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1465_CR50","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., & Wang, J. (2019a). Deep high-resolution representation learning for human pose estimation. In: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp 5693\u20135703.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"1465_CR51","unstructured":"Sun, K., Zhao, Y., Jiang, B., Cheng, T., Xiao, B., & Liu, D., et al. (2019b). High-resolution representations for labeling pixels and regions. CoRR. arXiv:1904.04514."},{"key":"1465_CR52","doi-asserted-by":"crossref","unstructured":"Tian, Z., He, T., Shen, C., Yan, Y. (2019). Decoders matter for semantic segmentation: Data-dependent decoding enables flexible feature aggregation. In: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp 3126\u20133135.","DOI":"10.1109\/CVPR.2019.00324"},{"key":"1465_CR53","first-page":"5998","volume-title":"Long Beach","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., et al. (2017). Long Beach (pp. 5998\u20136008). USA: CA."},{"key":"1465_CR54","doi-asserted-by":"crossref","unstructured":"Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., & Cottrell, G.W. (2018a). Understanding convolution for semantic segmentation. In: 2018 IEEE winter conference on applications of computer vision, WACV 2018, Lake Tahoe, NV, USA, March 12-15, 2018, pp 1451\u20131460.","DOI":"10.1109\/WACV.2018.00163"},{"key":"1465_CR55","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhang, Z., Qi, S., Shen, J., Pang, Y., & Shao, L. (2019). Learning compositional neural information fusion for human parsing. In: 2019 IEEE\/CVF international conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp 5702\u20135712.","DOI":"10.1109\/ICCV.2019.00580"},{"key":"1465_CR56","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R.B., Gupta, A., & He, K. (2018b). Non-local neural networks. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp 7794\u20137803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1465_CR57","doi-asserted-by":"crossref","unstructured":"Wu, T., Tang, S., Zhang, R., Cao, J., & Li, J. (2019). Tree-structured kronecker convolutional network for semantic segmentation. In: IEEE international conference on multimedia and expo, ICME 2019, Shanghai, China, July 8-12, 2019, pp 940\u2013945.","DOI":"10.1109\/ICME.2019.00166"},{"key":"1465_CR58","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., & Sun, J. (2018). Unified perceptual parsing for scene understanding. In: Computer Vision - ECCV 2018 - 15th European conference, Munich, Germany, September 8-14, 2018, Proceedings, Part V, pp 432\u2013448.","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"1465_CR59","doi-asserted-by":"crossref","unstructured":"Xie, G., Wang, J., Zhang, T., Lai, J., Hong, R., & Qi, G. (2018). Interleaved structured sparse convolutional neural networks. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp 8847\u20138856.","DOI":"10.1109\/CVPR.2018.00922"},{"key":"1465_CR60","doi-asserted-by":"crossref","unstructured":"Yang, M., Yu, K., Zhang, C., Li, Z., & Yang, K. (2018). Denseaspp for semantic segmentation in street scenes. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp 3684\u20133692.","DOI":"10.1109\/CVPR.2018.00388"},{"key":"1465_CR61","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: Computer Vision - ECCV 2018 - 15th European conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIII, pp 334\u2013349.","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"1465_CR62","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: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp 1857\u20131866.","DOI":"10.1109\/CVPR.2018.00199"},{"key":"1465_CR63","unstructured":"Yu, F., & Koltun, V. (2016). Multi-scale context aggregation by dilated convolutions. In: 4th international conference on learning representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings."},{"key":"1465_CR64","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, X., & Wang, J. (2020). Object-contextual representations for semantic segmentation. In: Computer Vision - ECCV 2020 - 16th European conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part VI, pp 173\u2013190.","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"1465_CR65","unstructured":"Yue, K., Sun, M., Yuan, Y., Zhou, F., Ding, E., & Xu, F. (2018). Compact generalized non-local network. In: Advances in neural information processing systems 31: Annual conference on neural information processing systems 2018, NeurIPS 2018, December 3-8, 2018, Montr\u00e9al, Canada, pp 6511\u20136520."},{"key":"1465_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, F., Chen, Y., Li, Z., Hong, Z., Liu, J., Ma, F., Han, J., & Ding, E. (2019a). Acfnet: Attentional class feature network for semantic segmentation. In: 2019 IEEE\/CVF international conference on computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp 6797\u20136806.","DOI":"10.1109\/ICCV.2019.00690"},{"key":"1465_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, H., Dana, K.J., Shi, J., Zhang, Z., Wang, X., Tyagi, A., & Agrawal, A. (2018). Context encoding for semantic segmentation. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp 7151\u20137160.","DOI":"10.1109\/CVPR.2018.00747"},{"key":"1465_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, H., Wang, C., & Xie, J. (2019b). Co-occurrent features in semantic segmentation. In: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp 548\u2013557.","DOI":"10.1109\/CVPR.2019.00064"},{"key":"1465_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, R., Tang, S., Zhang, Y., Li, J., & Yan, S. (2017a). Scale-adaptive convolutions for scene parsing. In: IEEE international conference on computer vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pp 2050\u20132058.","DOI":"10.1109\/ICCV.2017.224"},{"key":"1465_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, T., Qi, G., Xiao, B., Wang, J. (2017b). Interleaved group convolutions. In: IEEE international conference on computer vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pp 4383\u20134392.","DOI":"10.1109\/ICCV.2017.469"},{"key":"1465_CR71","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. In: 2017 IEEE conference on computer vision and pattern recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp 6230\u20136239.","DOI":"10.1109\/CVPR.2017.660"},{"key":"1465_CR72","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhang, Y., Liu, S., Shi, J., Loy, C.C., Lin, D., & Jia, J. (2018). Psanet: Point-wise spatial attention network for scene parsing. In: Computer Vision - ECCV 2018 - 15th European conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IX, pp 270\u2013286.","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"1465_CR73","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017). Scene parsing through ADE20K dataset. In: 2017 IEEE conference on computer vision and pattern recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp 5122\u20135130.","DOI":"10.1109\/CVPR.2017.544"},{"key":"1465_CR74","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., & Liang, J. (2018). Unet++: A nested u-net architecture for medical image segmentation. In: Deep learning in medical image analysis - and - multimodal learning for clinical decision support - 4th international workshop, DLMIA 2018, and 8th international workshop, ML-CDS 2018, held in conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, proceedings, pp 3\u201311.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"1465_CR75","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xu, M., Bai, S., Huang, T., & Bai, X. (2019). Asymmetric non-local neural networks for semantic segmentation. In: 2019 IEEE\/CVF international conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp 593\u2013602.","DOI":"10.1109\/ICCV.2019.00068"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01465-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01465-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01465-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,24]],"date-time":"2021-07-24T06:18:21Z","timestamp":1627107501000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01465-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,24]]},"references-count":75,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["1465"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01465-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,24]]},"assertion":[{"value":"20 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}