{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T04:13:07Z","timestamp":1789099987543,"version":"build-2803163510"},"reference-count":86,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T00:00:00Z","timestamp":1675900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T00:00:00Z","timestamp":1675900800000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s11432-021-3590-1","type":"journal-article","created":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T10:04:16Z","timestamp":1676282656000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Augmented FCN: rethinking context modeling for semantic segmentation"],"prefix":"10.1007","volume":"66","author":[{"given":"Dong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,9]]},"reference":[{"key":"3590_CR1","doi-asserted-by":"publisher","first-page":"2663","DOI":"10.1109\/TMI.2018.2845918","volume":"37","author":"X Li","year":"2018","unstructured":"Li X, Chen H, Qi X, et al. H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes. IEEE Trans Med Imag, 2018, 37: 2663\u20132674","journal-title":"IEEE Trans Med Imag"},{"key":"3590_CR2","doi-asserted-by":"crossref","unstructured":"Li P, Chen X, Shen S. Stereo R-CNN based 3D object detection for autonomous driving. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019","DOI":"10.1109\/CVPR.2019.00783"},{"key":"3590_CR3","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1007\/s11263-018-1070-x","volume":"126","author":"H A Alhaija","year":"2018","unstructured":"Alhaija H A, Mustikovela S K, Mescheder L, et al. Augmented reality meets computer vision: efficient data generation for urban driving scenes. Int J Comput Vis, 2018, 126: 961\u2013972","journal-title":"Int J Comput Vis"},{"key":"3590_CR4","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"3590_CR5","doi-asserted-by":"crossref","unstructured":"Hou Q, Zhang L, Cheng M M, et al. Strip pooling: rethinking spatial pooling for scene parsing. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"3590_CR6","doi-asserted-by":"publisher","first-page":"130105","DOI":"10.1007\/s11432-020-3065-4","volume":"64","author":"J P Feng","year":"2021","unstructured":"Feng J P, Wang X G, Liu W Y. Deep graph cut network for weakly-supervised semantic segmentation. Sci China Inf Sci, 2021, 64: 130105","journal-title":"Sci China Inf Sci"},{"key":"3590_CR7","doi-asserted-by":"crossref","unstructured":"Zhang D, Zhang H, Tang J, et al. Self-regulation for semantic segmentation. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2021","DOI":"10.1109\/ICCV48922.2021.00687"},{"key":"3590_CR8","doi-asserted-by":"crossref","unstructured":"Yuan Y, Chen X, Wang J. Object-contextual representations for semantic segmentation. In: Proceedings of European Conference on Computer Vision (ECCV), 2020","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"3590_CR9","doi-asserted-by":"crossref","unstructured":"Zhang H, Zhang H, Wang C, et al. Co-occurrent features in semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019","DOI":"10.1109\/CVPR.2019.00064"},{"key":"3590_CR10","unstructured":"Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions. In: Proceedings of International Conference on Learning Representations (ICLR), 2016"},{"key":"3590_CR11","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of International Conference on Neural Information Processing Systems (NeurIPS), 2017"},{"key":"3590_CR12","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, et al. Non-local neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00813"},{"key":"3590_CR13","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, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell, 2017, 40: 834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3590_CR14","doi-asserted-by":"crossref","unstructured":"Wang P, Chen P, Yuan Y, et al. Understanding convolution for semantic segmentation. In: Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV), 2018","DOI":"10.1109\/WACV.2018.00163"},{"key":"3590_CR15","doi-asserted-by":"crossref","unstructured":"Ahn J, Cho S, Kwak S. Weakly supervised learning of instance segmentation with inter-pixel relations. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019","DOI":"10.1109\/CVPR.2019.00231"},{"key":"3590_CR16","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, et al. Pyramid scene parsing network. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017","DOI":"10.1109\/CVPR.2017.660"},{"key":"3590_CR17","doi-asserted-by":"crossref","unstructured":"He J, Deng Z, Zhou L, et al. Adaptive pyramid context network for semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019","DOI":"10.1109\/CVPR.2019.00770"},{"key":"3590_CR18","unstructured":"Chen L C, Papandreou G, Schroff F, et al. Rethinking atrous convolution for semantic image segmentation. 2017. ArXiv:1706.05587"},{"key":"3590_CR19","doi-asserted-by":"crossref","unstructured":"Chen L C, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of European Conference on Computer Vision (ECCV), 2018","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"3590_CR20","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, et al. The Cityscapes dataset for semantic urban scene understanding. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016","DOI":"10.1109\/CVPR.2016.350"},{"key":"3590_CR21","doi-asserted-by":"crossref","unstructured":"Zhu Z, Xu M, Bai S, et al. Asymmetric non-local neural networks for semantic segmentation. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019","DOI":"10.1109\/ICCV.2019.00068"},{"key":"3590_CR22","doi-asserted-by":"crossref","unstructured":"Zhang D, Zhang H, Tang J, et al. Feature pyramid transformer. In: Proceedings of European Conference on Computer Vision (ECCV), 2020","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"3590_CR23","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang X, Huang L, et al. CCNet: criss-cross attention for semantic segmentation. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019","DOI":"10.1109\/ICCV.2019.00069"},{"key":"3590_CR24","unstructured":"Yuan Y, Wang J. OCNet: object context network for scene parsing. 2018. ArXiv:1809.00916"},{"key":"3590_CR25","doi-asserted-by":"crossref","unstructured":"Chen Y, Rohrbach M, Yan Z, et al. Graph-based global reasoning networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019","DOI":"10.1109\/CVPR.2019.00052"},{"key":"3590_CR26","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1007\/s11263-018-1075-5","volume":"126","author":"J Li","year":"2018","unstructured":"Li J, Ma A J, Yuen P C. Semi-supervised region metric learning for person re-identification. Int J Comput Vis, 2018, 126: 855\u2013874","journal-title":"Int J Comput Vis"},{"key":"3590_CR27","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Wang Y, et al. Adaptive context network for scene parsing. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019","DOI":"10.1109\/ICCV.2019.00685"},{"key":"3590_CR28","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1007\/s11263-018-1076-4","volume":"126","author":"C Ma","year":"2018","unstructured":"Ma C, Huang J B, Yang X, et al. Adaptive correlation filters with long-term and short-term memory for object tracking. Int J Comput Vis, 2018, 126: 771\u2013796","journal-title":"Int J Comput Vis"},{"key":"3590_CR29","doi-asserted-by":"crossref","unstructured":"Bello I, Zoph B, Vaswani A, et al. Attention augmented convolutional networks. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019","DOI":"10.1109\/ICCV.2019.00338"},{"key":"3590_CR30","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, et al. End-to-end object detection with transformers. In: Proceedings of European Conference on Computer Vision (ECCV), 2020","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3590_CR31","doi-asserted-by":"crossref","unstructured":"Shaw P, Uszkoreit J, Vaswani A. Self-attention with relative position representations. In: Proceedings of North American Chapter of the Association for Computational Linguistics (NAACL), 2018","DOI":"10.18653\/v1\/N18-2074"},{"key":"3590_CR32","unstructured":"Parmar N, Vaswani A, Uszkoreit J, et al. Image transformer. In: Proceedings of International Conference on Machine Learning (ICML), 2018"},{"key":"3590_CR33","unstructured":"Liu R, Lehman J, Molino P, et al. An intriguing failing of convolutional neural networks and the coordconv solution. In: Proceedings of International Conference on Neural Information Processing Systems (NeurIPS), 2018"},{"key":"3590_CR34","unstructured":"Huang C Z A, Vaswani A, Uszkoreit J, et al. Music transformer. In: Proceedings of International Conference on Neural Information Processing Systems (NeurIPS), 2018"},{"key":"3590_CR35","unstructured":"Shen Z, Zhang M, Zhao H, et al. Efficient attention: attention with linear complexities. In: Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV), 2021"},{"key":"3590_CR36","doi-asserted-by":"crossref","unstructured":"Selvaraju R R, Cogswell M, Das A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2017","DOI":"10.1109\/ICCV.2017.74"},{"key":"3590_CR37","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A, et al. Learning deep features for discriminative localization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016","DOI":"10.1109\/CVPR.2016.319"},{"key":"3590_CR38","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016","DOI":"10.1109\/CVPR.2016.90"},{"key":"3590_CR39","doi-asserted-by":"crossref","unstructured":"Zhou B, Zhao H, Puig X, et al. Scene parsing through ADE20K dataset. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017","DOI":"10.1109\/CVPR.2017.544"},{"key":"3590_CR40","doi-asserted-by":"publisher","first-page":"119103","DOI":"10.1007\/s11432-020-2967-3","volume":"65","author":"H B Gao","year":"2022","unstructured":"Gao H B, Guo F, Zhu J P, et al. Human motion segmentation based on structure constraint matrix factorization. Sci China Inf Sci, 2022, 65: 119103","journal-title":"Sci China Inf Sci"},{"key":"3590_CR41","doi-asserted-by":"publisher","first-page":"120104","DOI":"10.1007\/s11432-019-2718-7","volume":"63","author":"Z J Zhang","year":"2020","unstructured":"Zhang Z J, Pang Y W. CGNet: cross-guidance network for semantic segmentation. Sci China Inf Sci, 2020, 63: 120104","journal-title":"Sci China Inf Sci"},{"key":"3590_CR42","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of International Conference on Learning Representations (ICLR), 2014"},{"key":"3590_CR43","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017","DOI":"10.1109\/CVPR.2017.243"},{"key":"3590_CR44","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H, et al. Dual attention network for scene segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019","DOI":"10.1109\/CVPR.2019.00326"},{"key":"3590_CR45","doi-asserted-by":"crossref","unstructured":"Peng C, Zhang X, Yu G, et al. Large kernel matters\u2014improve semantic segmentation by global convolutional network. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017","DOI":"10.1109\/CVPR.2017.189"},{"key":"3590_CR46","doi-asserted-by":"crossref","unstructured":"Zhang Z, Zhang X, Peng C, et al. ExFuse: enhancing feature fusion for semantic segmentation. In: Proceedings of European Conference on Computer Vision (ECCV), 2018","DOI":"10.1007\/978-3-030-01249-6_17"},{"key":"3590_CR47","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, 2017, 39: 2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3590_CR48","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Proceedings of International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2015","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3590_CR49","doi-asserted-by":"crossref","unstructured":"Noh H, Hong S, Han B. Learning deconvolution network for semantic segmentation. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2015","DOI":"10.1109\/ICCV.2015.178"},{"key":"3590_CR50","unstructured":"Guo M H, Lu C Z, Liu Z N, et al. Visual attention network. 2022. ArXiv:2202.09741"},{"key":"3590_CR51","doi-asserted-by":"publisher","first-page":"108468","DOI":"10.1016\/j.patcog.2021.108468","volume":"124","author":"H Zhou","year":"2022","unstructured":"Zhou H, Qi L, Huang H, et al. CANet: co-attention network for RGB-D semantic segmentation. Pattern Recognition, 2022, 124: 108468","journal-title":"Pattern Recognition"},{"key":"3590_CR52","doi-asserted-by":"publisher","first-page":"160101","DOI":"10.1007\/s11432-020-3181-9","volume":"65","author":"D W Zhang","year":"2022","unstructured":"Zhang D W, Wang B, Wang G R, et al. Onfocus detection: identifying individual-camera eye contact from unconstrained images. Sci China Inf Sci, 2022, 65: 160101","journal-title":"Sci China Inf Sci"},{"key":"3590_CR53","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.3046647","volume":"44","author":"D W Zhang","year":"2022","unstructured":"Zhang D W, Zeng W, Yao J, et al. Weakly supervised object detection using proposal- and semantic-level relationships. IEEE Trans Pattern Anal Mach Intell, 2022, 44: 3349\u20133363","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3590_CR54","doi-asserted-by":"publisher","first-page":"5866","DOI":"10.1109\/TPAMI.2020.3046647","volume":"44","author":"D W Zhang","year":"2022","unstructured":"Zhang D W, Han J, Cheng G, et al. Weakly supervised object localization and detection: a survey. IEEE Trans Pattern Anal Mach Intell, 2022, 44: 5866\u20135885","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3590_CR55","doi-asserted-by":"crossref","unstructured":"Yang M, Yu K, Zhang C, et al. DenseASPP for semantic segmentation in street scenes. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00388"},{"key":"3590_CR56","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1109\/TIP.2020.3042065","volume":"30","author":"T Wu","year":"2020","unstructured":"Wu T, Tang S, Zhang R, et al. CGNet: a light-weight context guided network for semantic segmentation. IEEE Trans Image Process, 2020, 30: 1169\u20131179","journal-title":"IEEE Trans Image Process"},{"key":"3590_CR57","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1007\/s11263-018-01143-3","volume":"127","author":"B Kong","year":"2019","unstructured":"Kong B, Supan\u010di\u010d J, Ramanan D, et al. Cross-domain image matching with deep feature maps. Int J Comput Vis, 2019, 127: 1738\u20131750","journal-title":"Int J Comput Vis"},{"key":"3590_CR58","unstructured":"Li W, Wang X, Xia X, et al. SepViT: separable vision transformer. 2022. ArXiv:2203.15380"},{"key":"3590_CR59","doi-asserted-by":"crossref","unstructured":"Chen L, Zhang H, Xiao J, et al. SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017","DOI":"10.1109\/CVPR.2017.667"},{"key":"3590_CR60","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3590_CR61","doi-asserted-by":"crossref","unstructured":"Li X, Wang W, Hu X, et al. Selective kernel networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019","DOI":"10.1109\/CVPR.2019.00060"},{"key":"3590_CR62","doi-asserted-by":"crossref","unstructured":"Zhang H, Wu C, Zhang Z, et al. ResNeSt: split-attention networks. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"3590_CR63","unstructured":"Bello I. LambdaNetworks: modeling long-range interactions without attention. In: Proceedings of International Conference on Learning Representations (ICLR), 2021"},{"key":"3590_CR64","doi-asserted-by":"crossref","unstructured":"Tao C, Gao S, Shang M, et al. Get the point of my utterance! Learning towards effective responses with multi-head attention mechanism. In: Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2018","DOI":"10.24963\/ijcai.2018\/614"},{"key":"3590_CR65","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A, et al. Deep Learning. Cambridge: MIT Press, 2016"},{"key":"3590_CR66","doi-asserted-by":"crossref","unstructured":"Albawi S, Mohammed T A, Al-Zawi S. Understanding of a convolutional neural network. In: Proceedings of International Conference on Engineering and Technology (ICET), 2017","DOI":"10.1109\/ICEngTechnol.2017.8308186"},{"key":"3590_CR67","doi-asserted-by":"crossref","unstructured":"Zhong Z, Lin Z Q, Bidart R, et al. Squeeze-and-attention networks for semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020","DOI":"10.1109\/CVPR42600.2020.01308"},{"key":"3590_CR68","doi-asserted-by":"crossref","unstructured":"Sun K, Xiao B, Liu D, et al. Deep high-resolution representation learning for human pose estimation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019","DOI":"10.1109\/CVPR.2019.00584"},{"key":"3590_CR69","doi-asserted-by":"crossref","unstructured":"Zhang H, Dana K, Shi J, et al. Context encoding for semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00747"},{"key":"3590_CR70","unstructured":"Paszke A, Gross S, Massa F, et al. PyTorch: an imperative style, high-performance deep learning library. In: Proceedings of International Conference on Neural Information Processing Systems (NeurIPS), 2019"},{"key":"3590_CR71","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3590_CR72","doi-asserted-by":"crossref","unstructured":"Lin G, Milan A, Shen C, et al. RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017","DOI":"10.1109\/CVPR.2017.549"},{"key":"3590_CR73","unstructured":"Li Y, Gupta A. Beyond grids: learning graph representations for visual recognition. In: Proceedings of International Conference on Neural Information Processing Systems (NeurIPS), 2018"},{"key":"3590_CR74","doi-asserted-by":"crossref","unstructured":"Xiao T, Liu Y, Zhou B, et al. Unified perceptual parsing for scene understanding. In: Proceedings of European Conference on Computer Vision (ECCV), 2018","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"3590_CR75","doi-asserted-by":"crossref","unstructured":"Liang X, Zhou H, Xing E. Dynamic-structured semantic propagation network. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00085"},{"key":"3590_CR76","doi-asserted-by":"crossref","unstructured":"Zhao H, Zhang Y, Liu S, et al. PSANet: point-wise spatial attention network for scene parsing. In: Proceedings of European Conference on Computer Vision (ECCV), 2018","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"3590_CR77","doi-asserted-by":"crossref","unstructured":"Zhang R, Tang S, Zhang Y, et al. Scale-adaptive convolutions for scene parsing. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2017","DOI":"10.1109\/ICCV.2017.224"},{"key":"3590_CR78","unstructured":"Liang X, Hu Z, Zhang H, et al. Symbolic graph reasoning meets convolutions. In: Proceedings of International Conference on Neural Information Processing Systems (NeurIPS), 2018"},{"key":"3590_CR79","doi-asserted-by":"crossref","unstructured":"Kong S, Fowlkes C C. Recurrent scene parsing with perspective understanding in the loop. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00106"},{"key":"3590_CR80","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.patcog.2019.01.006","volume":"90","author":"Z Wu","year":"2019","unstructured":"Wu Z, Shen C, van den Hengel A. Wider or deeper: revisiting the ResNet model for visual recognition. Pattern Recognition, 2019, 90: 119\u2013133","journal-title":"Pattern Recognition"},{"key":"3590_CR81","doi-asserted-by":"crossref","unstructured":"Yu C, Wang J, Peng C, et al. BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Proceedings of European Conference on Computer Vision (ECCV), 2018","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"3590_CR82","doi-asserted-by":"crossref","unstructured":"Ke T W, Hwang J J, Liu Z, et al. Adaptive affinity fields for semantic segmentation. In: Proceedings of European Conference on Computer Vision (ECCV), 2018","DOI":"10.1007\/978-3-030-01246-5_36"},{"key":"3590_CR83","doi-asserted-by":"crossref","unstructured":"Yu C, Wang J, Peng C, et al. Learning a discriminative feature network for semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00199"},{"key":"3590_CR84","doi-asserted-by":"crossref","unstructured":"Ding H, Jiang X, Shuai B, et al. Semantic correlation promoted shape-variant context for segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019","DOI":"10.1109\/CVPR.2019.00909"},{"key":"3590_CR85","doi-asserted-by":"crossref","unstructured":"Cheng B, Chen L C, Wei Y, et al. SPGNet: semantic prediction guidance for scene parsing. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019","DOI":"10.1109\/ICCV.2019.00532"},{"key":"3590_CR86","doi-asserted-by":"crossref","unstructured":"Ding H, Jiang X, Liu A Q, et al. Boundary-aware feature propagation for scene segmentation. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019","DOI":"10.1109\/ICCV.2019.00692"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-021-3590-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-021-3590-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-021-3590-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T20:26:03Z","timestamp":1716150363000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-021-3590-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,9]]},"references-count":86,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["3590"],"URL":"https:\/\/doi.org\/10.1007\/s11432-021-3590-1","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,9]]},"assertion":[{"value":"26 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"142105"}}