{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:34:52Z","timestamp":1782833692465,"version":"3.54.5"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T00:00:00Z","timestamp":1703289600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T00:00:00Z","timestamp":1703289600000},"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":["Front. Comput. Sci."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s11704-023-2563-5","type":"journal-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T23:34:16Z","timestamp":1703288056000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Graph-Segmenter: graph transformer with boundary-aware attention for semantic segmentation"],"prefix":"10.1007","volume":"18","author":[{"given":"Zizhang","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanzhu","family":"Gan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,12,23]]},"reference":[{"issue":"1","key":"2563_CR1","doi-asserted-by":"publisher","first-page":"171306","DOI":"10.1007\/s11704-021-1186-y","volume":"17","author":"H Ruan","year":"2023","unstructured":"Ruan H, Song H, Liu B, Cheng Y, Liu Q. Intellectual property protection for deep semantic segmentation models. Frontiers of Computer Science, 2023, 17(1): 171306","journal-title":"Frontiers of Computer Science"},{"issue":"4","key":"2563_CR2","doi-asserted-by":"publisher","first-page":"164351","DOI":"10.1007\/s11704-022-1505-y","volume":"16","author":"D Zhang","year":"2022","unstructured":"Zhang D, Zhou Y, Zhao J, Yang Z, Dong H, Yao R, Ma H. Multi-granularity semantic alignment distillation learning for remote sensing image semantic segmentation. Frontiers of Computer Science, 2022, 16(4): 164351","journal-title":"Frontiers of Computer Science"},{"issue":"3","key":"2563_CR3","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1002\/rob.21918","volume":"37","author":"S Grigorescu","year":"2020","unstructured":"Grigorescu S, Trasnea B, Cocias T, Macesanu G. A survey of deep learning techniques for autonomous driving. Journal of Field Robotics, 2020, 37(3): 362\u2013386","journal-title":"Journal of Field Robotics"},{"issue":"3","key":"2563_CR4","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2021","unstructured":"Feng D, Haase-Sch\u00fctz C, Rosenbaum L, Hertlein H, Gl\u00e4ser C, Timm F, Wiesbeck W, Dietmayer K. Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(3): 1341\u20131360","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"1\u20133","key":"2563_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/0600000079","volume":"12","author":"J Janai","year":"2020","unstructured":"Janai J, G\u00fcney F, Behl A, Geiger A. Computer vision for autonomous vehicles: problems, datasets and state of the art. Foundations and Trends\u00ae in Computer Graphics and Vision, 2020, 12(1\u20133): 1\u2013308","journal-title":"Foundations and Trends\u00ae in Computer Graphics and Vision"},{"issue":"10","key":"2563_CR6","doi-asserted-by":"publisher","first-page":"3782","DOI":"10.1109\/TITS.2019.2892405","volume":"20","author":"E Arnold","year":"2019","unstructured":"Arnold E, Al-Jarrah O Y, Dianati M, Fallah S, Oxtoby D, Mouzakitis A. A survey on 3D object detection methods for autonomous driving applications. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(10): 3782\u20133795","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"2563_CR7","doi-asserted-by":"crossref","unstructured":"Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X, Cottrell G. Understanding convolution for semantic segmentation. In: Proceedings of the Winter Conference on Applications of Computer Vision. 2018, 1451\u20131460","DOI":"10.1109\/WACV.2018.00163"},{"key":"2563_CR8","doi-asserted-by":"crossref","unstructured":"Devlin J, Chang M W, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019, 4171\u20134186","DOI":"10.18653\/v1\/N19-1423"},{"key":"2563_CR9","doi-asserted-by":"crossref","unstructured":"Wang L, Li D, Zhu Y, Tian L, Shan Y. Dual super-resolution learning for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020, 3773\u20133782","DOI":"10.1109\/CVPR42600.2020.00383"},{"key":"2563_CR10","doi-asserted-by":"crossref","unstructured":"Yu C, Wang J, Gao C, Yu G, Shen C, Sang N. Context prior for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020, 12413\u201312422","DOI":"10.1109\/CVPR42600.2020.01243"},{"key":"2563_CR11","unstructured":"Rae J W, Potapenko A, Jayakumar S M, Lillicrap T P. Compressive transformers for long-range sequence modelling. In: Proceedings of the 8th International Conference on Learning Representations. 2020"},{"key":"2563_CR12","unstructured":"Lee J, Lee Y, Kim J, Kosiorek A, Choi S, Teh Y W. Set transformer: a framework for attention-based permutation-invariant neural networks. In: Proceedings of the 36th International Conference on Machine Learning. 2019, 3744\u20133753"},{"key":"2563_CR13","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N. An image is worth 16\u00d716 words: transformers for image recognition at scale. In: Proceedings of the 9th International Conference on Learning Representations. 2021"},{"key":"2563_CR14","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B. Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of IEEE\/CVF International Conference on Computer Vision. 2021, 9992\u201310002","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2563_CR15","unstructured":"Xie E, Wang W, Yu Z, Anandkumar A, Alvarez J M, Luo P. SegFormer: simple and efficient design for semantic segmentation with transformers. In: Proceedings of the 35th Conference on Neural Information Processing Systems. 2021"},{"key":"2563_CR16","unstructured":"Chu X, Tian Z, Wang Y, Zhang B, Ren H, Wei X, Xia H, Shen C. Twins: revisiting the design of spatial attention in vision transformers. In: Proceedings of the 35th Conference on Neural Information Processing Systems. 2021"},{"key":"2563_CR17","doi-asserted-by":"crossref","unstructured":"Fang J, Xie L, Wang X, Zhang X, Liu W, Tian Q. MSG-transformer: exchanging local spatial information by manipulating messenger tokens. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022, 12053\u201312062","DOI":"10.1109\/CVPR52688.2022.01175"},{"key":"2563_CR18","doi-asserted-by":"crossref","unstructured":"Wang P, Wang X, Wang F, Lin M, Chang S, Li H, Jin R. KVT: k-NN attention for boosting vision transformers. In: Proceedings of the 17th European Conference on Computer Vision. 2022, 285\u2013302","DOI":"10.1007\/978-3-031-20053-3_17"},{"key":"2563_CR19","unstructured":"Chu X, Zhang B, Tian Z, Wei X, Xia H. Do we really need explicit position encodings for vision transformers? 2021, arXiv preprint arXiv: 2102.10882"},{"key":"2563_CR20","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B. The cityscapes dataset for semantic urban scene understanding. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2016, 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"issue":"3","key":"2563_CR21","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou B, Zhao H, Puig X, Xiao T, Fidler S, Barriuso A, Torralba A. Semantic understanding of scenes through the ADE20K dataset. International Journal of Computer Vision, 2019, 127(3): 302\u2013321","journal-title":"International Journal of Computer Vision"},{"key":"2563_CR22","doi-asserted-by":"crossref","unstructured":"Mottaghi R, Chen X, Liu X, Cho N G, Lee S, Fidler S, Urtasun R, Yuille A. The role of context for object detection and semantic segmentation in the wild. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2014, 891\u2013898","DOI":"10.1109\/CVPR.2014.119"},{"key":"2563_CR23","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. 2015, 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"23","key":"2563_CR24","doi-asserted-by":"publisher","first-page":"16770","DOI":"10.1109\/JIOT.2020.3029957","volume":"8","author":"Y Shen","year":"2021","unstructured":"Shen Y, Zhang H, Fan Y, Lee A P, Xu L. Smart health of ultrasound telemedicine based on deeply represented semantic segmentation. IEEE Internet of Things Journal, 2021, 8(23): 16770\u201316778","journal-title":"IEEE Internet of Things Journal"},{"key":"2563_CR25","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J. Pyramid scene parsing network. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2017, 6230\u20136239","DOI":"10.1109\/CVPR.2017.660"},{"key":"2563_CR26","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 15th European Conference on Computer Vision. 2018, 833\u2013851","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2563_CR27","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, Lu H. Dual attention network for scene segmentation. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019, 3141\u20133149","DOI":"10.1109\/CVPR.2019.00326"},{"key":"2563_CR28","doi-asserted-by":"crossref","unstructured":"Ding H, Zhang H, Liu J, Li J, Feng Z, Jiang X. Interaction via bidirectional graph of semantic region affinity for scene parsing. In: Proceedings of IEEE\/CVF International Conference on Computer Vision. 2021, 15828\u201315838","DOI":"10.1109\/ICCV48922.2021.01555"},{"key":"2563_CR29","doi-asserted-by":"crossref","unstructured":"Yuan Y, Chen X, Wang J. Object-contextual representations for semantic segmentation. In: Proceedings of the European Conference on Computer Vision. 2020","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"2563_CR30","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 16th European Conference on Computer Vision. 2020, 775\u2013793","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"2563_CR31","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang X, Huang L, Huang C, Wei Y, Liu W. CCNet: crisscross attention for semantic segmentation. In: Proceedings of IEEE\/CVF International Conference on Computer Vision. 2019, 603\u2013612","DOI":"10.1109\/ICCV.2019.00069"},{"key":"2563_CR32","doi-asserted-by":"crossref","unstructured":"Li X, Zhao H, Han L, Tong Y, Tan S, Yang K. Gated fully fusion for semantic segmentation. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence. 2020, 11418\u201311425","DOI":"10.1609\/aaai.v34i07.6805"},{"key":"2563_CR33","doi-asserted-by":"crossref","unstructured":"He J, Deng Z, Zhou L, Wang Y, Qiao Y. Adaptive pyramid context network for semantic segmentation. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019, 7511\u20137520","DOI":"10.1109\/CVPR.2019.00770"},{"key":"2563_CR34","doi-asserted-by":"crossref","unstructured":"Ding H, Jiang X, Liu A Q, Thalmann N M, Wang G. Boundary-aware feature propagation for scene segmentation. In: Proceedings of IEEE\/CVF International Conference on Computer Vision. 2019, 6818\u20136828","DOI":"10.1109\/ICCV.2019.00692"},{"key":"2563_CR35","unstructured":"Mnih V, Heess N, Graves A, Kavukcuoglu K. Recurrent models of visual attention. In: Proceedings of the 27th International Conference on Neural Information Processing Systems. 2014, 2204\u20132212"},{"key":"2563_CR36","unstructured":"Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. In: Proceedings of the 3rd International Conference on Learning Representations. 2015"},{"key":"2563_CR37","unstructured":"Parmar N, Vaswani A, Uszkoreit J, Kaiser L, Shazeer N, Ku A, Tran D. Image transformer. In: Proceedings of the 35th International Conference on Machine Learning. 2018, 4055\u20134064"},{"key":"2563_CR38","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S. End-to-end object detection with transformers. In: Proceedings of the 16th European Conference on Computer Vision. 2020, 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2563_CR39","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J. Deformable DETR: deformable transformers for end-to-end object detection. In: Proceedings of the 9th International Conference on Learning Representations. 2021"},{"key":"2563_CR40","doi-asserted-by":"crossref","unstructured":"Wang Y, Xu Z, Wang X, Shen C, Cheng B, Shen H, Xia H. End-to-end video instance segmentation with transformers. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2021, 8737\u20138746","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"2563_CR41","unstructured":"Wang Y, Guizilini V, Zhang T, Wang Y, Zhao H, Solomon J. DETR3D: 3D object detection from multi-view images via 3D-to-2D queries. In: Proceedings of the Conference on Robot Learning. 2021, 180\u2013191"},{"key":"2563_CR42","doi-asserted-by":"crossref","unstructured":"Strudel R, Garcia R, Laptev I, Schmid C. Segmenter: transformer for semantic segmentation. In: Proceedings of IEEE\/CVF International Conference on Computer Vision. 2021, 7242\u20137252","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"2563_CR43","doi-asserted-by":"crossref","unstructured":"Zheng S, Lu J, Zhao H, Zhu X, Luo Z, Wang Y, Fu Y, Feng J, Xiang T, Torr P H S, Zhang L. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2021, 6877\u20136886","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"2563_CR44","unstructured":"Zhang L, Li X, Arnab A, Yang K, Tong Y, Torr P H S. Dual graph convolutional network for semantic segmentation. In: Proceedings of the 30th British Machine Vision Conference 2019. 2019, 254"},{"key":"2563_CR45","doi-asserted-by":"crossref","unstructured":"Pan S Y, Lu C Y, Lee S P, Peng W H. Weakly-supervised image semantic segmentation using graph convolutional networks. In: Proceedings of IEEE International Conference on Multimedia and Expo. 2021, 1\u20136","DOI":"10.1109\/ICME51207.2021.9428116"},{"issue":"3","key":"2563_CR46","doi-asserted-by":"publisher","first-page":"163309","DOI":"10.1007\/s11704-021-0004-x","volume":"16","author":"H Wang","year":"2022","unstructured":"Wang H, Dong L, Sun M. Local feature aggregation algorithm based on graph convolutional network. Frontiers of Computer Science, 2022, 16(3): 163309","journal-title":"Frontiers of Computer Science"},{"issue":"6","key":"2563_CR47","doi-asserted-by":"publisher","first-page":"166614","DOI":"10.1007\/s11704-021-0261-8","volume":"16","author":"J Wu","year":"2022","unstructured":"Wu J, He X, Wang X, Wang Q, Chen W, Lian J, Xie X. Graph convolution machine for context-aware recommender system. Frontiers of Computer Science, 2022, 16(6): 166614","journal-title":"Frontiers of Computer Science"},{"key":"2563_CR48","unstructured":"Bruna J, Zaremba W, Szlam A, LeCun Y. Spectral networks and locally connected networks on graphs. In: Proceedings of the 2nd International Conference on Learning Representations. 2014"},{"key":"2563_CR49","unstructured":"Velickovic P, Cucurull G, Casanova A, Romero A, Li\u00f2 P, Bengio Y. Graph attention networks. In: Proceedings of the 6th International Conference on Learning Representations. 2018"},{"key":"2563_CR50","doi-asserted-by":"crossref","unstructured":"Zhang L, Xu D, Arnab A, Torr P H S. Dynamic graph message passing networks. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020, 3723\u20133732","DOI":"10.1109\/CVPR42600.2020.00378"},{"key":"2563_CR51","doi-asserted-by":"crossref","unstructured":"Zhu Y, Xu X, Shen F, Ji Y, Gao L, Shen H T. PoseGTAC: graph transformer encoder-decoder with atrous convolution for 3D human pose estimation. In: Proceedings of the 30th International Joint Conference on Artificial Intelligence. 2021, 1359\u20131365","DOI":"10.24963\/ijcai.2021\/188"},{"key":"2563_CR52","doi-asserted-by":"crossref","unstructured":"Dong X, Long C, Xu W, Xiao C. Dual graph convolutional networks with transformer and curriculum learning for image captioning. In: Proceedings of the 29th ACM International Conference on Multimedia. 2021, 2615\u20132624","DOI":"10.1145\/3474085.3475439"},{"key":"2563_CR53","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D. Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 2018, 7444\u20137452","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"2563_CR54","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1109\/TMM.2021.3054526","volume":"24","author":"T Li","year":"2022","unstructured":"Li T, Zhang K, Shen S, Liu B, Liu Q, Li Z. Image co-saliency detection and instance co-segmentation using attention graph clustering based graph convolutional network. IEEE Transactions on Multimedia, 2022, 24: 492\u2013505","journal-title":"IEEE Transactions on Multimedia"},{"key":"2563_CR55","doi-asserted-by":"crossref","unstructured":"Li X, Yang Y, Zhao Q, Shen T, Lin Z, Liu H. Spatial pyramid based graph reasoning for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020, 8947\u20138956","DOI":"10.1109\/CVPR42600.2020.00897"},{"key":"2563_CR56","doi-asserted-by":"crossref","unstructured":"Hu H, Ji D, Gan W, Bai S, Wu W, Yan J. Class-wise dynamic graph convolution for semantic segmentation. In: Proceedings of the 16th European Conference on Computer Vision. 2020, 1\u201317","DOI":"10.1007\/978-3-030-58520-4_1"},{"key":"2563_CR57","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1109\/TMM.2021.3053393","volume":"24","author":"Y Zhang","year":"2022","unstructured":"Zhang Y, Liu M, He J, Pan F, Guo Y. Affinity fusion graph-based framework for natural image segmentation. IEEE Transactions on Multimedia, 2022, 24: 440\u2013450","journal-title":"IEEE Transactions on Multimedia"},{"key":"2563_CR58","doi-asserted-by":"publisher","first-page":"2335","DOI":"10.1109\/TMM.2020.3009499","volume":"23","author":"C Chen","year":"2021","unstructured":"Chen C, Qian S, Fang Q, Xu C. HAPGN: hierarchical attentive pooling graph network for point cloud segmentation. IEEE Transactions on Multimedia, 2021, 23: 2335\u20132346","journal-title":"IEEE Transactions on Multimedia"},{"key":"2563_CR59","doi-asserted-by":"publisher","first-page":"108372","DOI":"10.1016\/j.patcog.2021.108372","volume":"123","author":"Y Su","year":"2022","unstructured":"Su Y, Liu W, Yuan Z, Cheng M, Zhang Z, Shen X, Wang C. DLA-Net: learning dual local attention features for semantic segmentation of large-scale building facade point clouds. Pattern Recognition, 2022, 123: 108372","journal-title":"Pattern Recognition"},{"key":"2563_CR60","doi-asserted-by":"crossref","unstructured":"Liu Y, Yang S, Li B, Zhou W, Xu J, Li H, Lu Y. Affinity derivation and graph merge for instance segmentation. In: Proceedings of the 15th European Conference on Computer Vision. 2018, 708\u2013724","DOI":"10.1007\/978-3-030-01219-9_42"},{"issue":"1","key":"2563_CR61","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1109\/TKDE.2020.2981333","volume":"34","author":"Z Zhang","year":"2022","unstructured":"Zhang Z, Cui P, Zhu W. Deep learning on graphs: a survey. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(1): 249\u2013270","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"1","key":"2563_CR62","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2021","unstructured":"Wu Z, Pan S, Chen F, Long G, Zhang C, Yu P S. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4\u201324","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2563_CR63","unstructured":"Hamilton W L, Ying R, Leskovec J. Inductive representation learning on large graphs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 1025\u20131035"},{"key":"2563_CR64","unstructured":"Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th International Conference on Learning Representations. 2017"},{"key":"2563_CR65","doi-asserted-by":"crossref","unstructured":"Yin M, Yao Z, Cao Y, Li X, Zhang Z, Lin S, Hu H. Disentangled nonlocal neural networks. In: Proceedings of the 16th European Conference on Computer Vision. 2020, 191\u2013207","DOI":"10.1007\/978-3-030-58555-6_12"},{"key":"2563_CR66","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K. Non-local neural networks. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2018, 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2563_CR67","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 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2018, 3684\u20133692","DOI":"10.1109\/CVPR.2018.00388"},{"key":"2563_CR68","unstructured":"Chen L C, Collins M D, Zhu Y, Papandreou G, Zoph B, Schroff F, Adam H, Shlens J. Searching for efficient multi-scale architectures for dense image prediction. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018, 8713\u20138724"},{"key":"2563_CR69","doi-asserted-by":"crossref","unstructured":"Cheng B, Collins M D, Zhu Y, Liu T, Huang T S, Adam H, Chen L C. Panoptic-DeepLab: a simple, strong, and fast baseline for bottom-up panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020, 12472\u201312482","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"2563_CR70","doi-asserted-by":"crossref","unstructured":"Hou Q, Zhang L, Cheng M M, Feng J. Strip pooling: rethinking spatial pooling for scene parsing. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020, 4002\u20134011","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"2563_CR71","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 15th European Conference on Computer Vision. 2018, 334\u2013349","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"2563_CR72","doi-asserted-by":"crossref","unstructured":"Zhao H, Zhang Y, Liu S, Shi J, Loy C C, Lin D, Jia J. PSANet: point-wise spatial attention network for scene parsing. In: Proceedings of the 15th European Conference on Computer Vision. 2018, 270\u2013286","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"2563_CR73","unstructured":"Yuan Y, Huang L, Guo J, Zhang C, Chen X, Wang J. OCNet: object context network for scene parsing. 2018, arXiv preprint arXiv: 1809.00916"},{"key":"2563_CR74","doi-asserted-by":"crossref","unstructured":"Xiao T, Liu Y, Zhou B, Jiang Y, Sun J. Unified perceptual parsing for scene understanding. In: Proceedings of the 15th European Conference on Computer Vision. 2018, 432\u2013448","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"2563_CR75","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Wang Y, Li Y, Bao Y, Tang J, Lu H. Adaptive context network for scene parsing. In: Proceedings of IEEE\/CVF International Conference on Computer Vision. 2019, 6747\u20136756","DOI":"10.1109\/ICCV.2019.00685"},{"key":"2563_CR76","doi-asserted-by":"crossref","unstructured":"Huang Y, Kang D, Chen L, Zhe X, Jia W, Bao L, He X. CAR: class-aware regularizations for semantic segmentation. In: Proceedings of the 17th European Conference on Computer Vision. 2022, 518\u2013534","DOI":"10.1007\/978-3-031-19815-1_30"},{"key":"2563_CR77","doi-asserted-by":"crossref","unstructured":"Li X, Zhong Z, Wu J, Yang Y, Lin Z, Liu H. Expectation-maximization attention networks for semantic segmentation. In: Proceedings of IEEE\/CVF International Conference on Computer Vision. 2019, 9166\u20139175","DOI":"10.1109\/ICCV.2019.00926"},{"key":"2563_CR78","doi-asserted-by":"crossref","unstructured":"Ding H, Jiang X, Shuai B, Liu A Q, Wang G. Semantic correlation promoted shape-variant context for segmentation. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019, 8877\u20138886","DOI":"10.1109\/CVPR.2019.00909"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-023-2563-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11704-023-2563-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-023-2563-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T20:24:06Z","timestamp":1763583846000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11704-023-2563-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,23]]},"references-count":78,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["2563"],"URL":"https:\/\/doi.org\/10.1007\/s11704-023-2563-5","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,23]]},"assertion":[{"value":"5 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Competing interests\n                      The authors declare that they have no competing interests or financial conflicts to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"185327"}}