{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T08:43:04Z","timestamp":1770540184316,"version":"3.49.0"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T00:00:00Z","timestamp":1679875200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T00:00:00Z","timestamp":1679875200000},"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\/s11432-022-3599-y","type":"journal-article","created":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T16:02:54Z","timestamp":1680278574000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":76,"title":["MFVNet: a deep adaptive fusion network with multiple field-of-views for remote sensing image semantic segmentation"],"prefix":"10.1007","volume":"66","author":[{"given":"Yansheng","family":"Li","sequence":"first","affiliation":[]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Zhi","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Siwei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Tao","family":"He","sequence":"additional","affiliation":[]},{"given":"Yongjun","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,27]]},"reference":[{"key":"3599_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3230846","volume":"60","author":"Q He","year":"2022","unstructured":"He Q, Sun X, Yan Z, et al. Multi-object tracking in satellite videos with graph-based multitask modeling. IEEE Trans Geosci Remote Sens, 2022, 60: 1\u201313","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"3599_CR2","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.isprsjprs.2022.08.010","volume":"193","author":"Q He","year":"2022","unstructured":"He Q, Sun X, Diao W, et al. Transformer-induced graph reasoning for multimodal semantic segmentation in remote sensing. ISPRS J Photogrammetry Remote Sens, 2022, 193: 90\u2013103","journal-title":"ISPRS J Photogrammetry Remote Sens"},{"key":"3599_CR3","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.isprsjprs.2021.12.004","volume":"184","author":"X Sun","year":"2022","unstructured":"Sun X, Wang P, Yan Z, et al. FAIR1M: a benchmark dataset for fine-grained object recognition in high-resolution remote sensing imagery. ISPRS J Photogrammetry Remote Sens, 2022, 184: 116\u2013130","journal-title":"ISPRS J Photogrammetry Remote Sens"},{"key":"3599_CR4","doi-asserted-by":"publisher","first-page":"122301","DOI":"10.1007\/s11432-020-3077-5","volume":"64","author":"S L Fu","year":"2021","unstructured":"Fu S L, Xu F, Jin Y-Q. Reciprocal translation between SAR and optical remote sensing images with cascaded-residual adversarial networks. Sci China Inf Sci, 2021, 64: 122301","journal-title":"Sci China Inf Sci"},{"key":"3599_CR5","doi-asserted-by":"publisher","first-page":"121301","DOI":"10.1007\/s11432-020-3084-1","volume":"64","author":"Y F Gu","year":"2021","unstructured":"Gu Y F, Liu T Z, Gao G M, et al. Multimodal hyperspectral remote sensing: an overview and perspective. Sci China Inf Sci, 2021, 64: 121301","journal-title":"Sci China Inf Sci"},{"key":"3599_CR6","doi-asserted-by":"publisher","first-page":"8540","DOI":"10.1109\/TIP.2021.3117076","volume":"30","author":"J Mei","year":"2021","unstructured":"Mei J, Li R J, Gao W, et al. CoANet: connectivity attention network for road extraction from satellite imagery. IEEE Trans Image Process, 2021, 30: 8540\u20138552","journal-title":"IEEE Trans Image Process"},{"key":"3599_CR7","doi-asserted-by":"publisher","first-page":"7001","DOI":"10.1109\/JSTARS.2021.3093625","volume":"14","author":"D Rashkovetsky","year":"2021","unstructured":"Rashkovetsky D, Mauracher F, Langer M, et al. Wildfire detection from multisensor satellite imagery using deep semantic segmentation. IEEE J Sel Top Appl Earth Observations Remote Sens, 2021, 14: 7001\u20137016","journal-title":"IEEE J Sel Top Appl Earth Observations Remote Sens"},{"key":"3599_CR8","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1109\/TIP.2021.3134455","volume":"31","author":"L Ding","year":"2022","unstructured":"Ding L, Tang H, Liu Y, et al. Adversarial shape learning for building extraction in VHR remote sensing images. IEEE Trans Image Process, 2022, 31: 678\u2013690","journal-title":"IEEE Trans Image Process"},{"key":"3599_CR9","doi-asserted-by":"publisher","first-page":"112045","DOI":"10.1016\/j.rse.2020.112045","volume":"250","author":"Y Li","year":"2020","unstructured":"Li Y, Chen W, Zhang Y, et al. Accurate cloud detection in high-resolution remote sensing imagery by weakly supervised deep learning. Remote Sens Environ, 2020, 250: 112045","journal-title":"Remote Sens Environ"},{"key":"3599_CR10","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.isprsjprs.2021.02.009","volume":"175","author":"Y Li","year":"2021","unstructured":"Li Y, Shi T, Zhang Y, et al. Learning deep semantic segmentation network under multiple weakly-supervised constraints for cross-domain remote sensing image semantic segmentation. ISPRS J Photogrammetry Remote Sens, 2021, 175: 20\u201333","journal-title":"ISPRS J Photogrammetry Remote Sens"},{"key":"3599_CR11","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.isprsjprs.2022.02.013","volume":"186","author":"Y Li","year":"2022","unstructured":"Li Y, Zhou Y, Zhang Y, et al. DKDFN: domain knowledge-guided deep collaborative fusion network for multimodal unitemporal remote sensing land cover classification. ISPRS J Photogrammetry Remote Sens, 2022, 186: 170\u2013189","journal-title":"ISPRS J Photogrammetry Remote Sens"},{"key":"3599_CR12","doi-asserted-by":"crossref","unstructured":"Workman S, Rafique M U, Blanton H, et al. Revisiting near\/remote sensing with geospatial attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2022","DOI":"10.1109\/CVPR52688.2022.00182"},{"key":"3599_CR13","doi-asserted-by":"publisher","first-page":"5891","DOI":"10.1109\/TGRS.2020.3011913","volume":"59","author":"D Peng","year":"2021","unstructured":"Peng D, Bruzzone L, Zhang Y, et al. SemiCDNet: a semisupervised convolutional neural network for change detection in high resolution remote-sensing images. IEEE Trans Geosci Remote Sens, 2021, 59: 5891\u20135906","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"3599_CR14","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.isprsjprs.2021.12.005","volume":"184","author":"Q Zhu","year":"2022","unstructured":"Zhu Q, Guo X, Deng W, et al. Land-Use\/Land-Cover change detection based on a Siamese global learning framework for high spatial resolution remote sensing imagery. ISPRS J Photogrammetry Remote Sens, 2022, 184: 63\u201378","journal-title":"ISPRS J Photogrammetry Remote Sens"},{"key":"3599_CR15","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/TGRS.2005.843253","volume":"43","author":"M Datcu","year":"2005","unstructured":"Datcu M, Seidel K. Human-centered concepts for exploration and understanding of Earth observation images. IEEE Trans Geosci Remote Sens, 2005, 43: 601\u2013609","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"3599_CR16","volume-title":"Remote Sensing and Image Interpretation","author":"T Lillesand","year":"2015","unstructured":"Lillesand T, Kiefer R W, Chipman J. Remote Sensing and Image Interpretation. Hoboken: John Wiley & Sons, 2015"},{"key":"3599_CR17","series-title":"The Perception of Visual Information","first-page":"73","volume-title":"A multiscale geometric model of human vision","author":"R Haar","year":"1993","unstructured":"Haar R, Bart M T, Florack L. A multiscale geometric model of human vision. In: The Perception of Visual Information. New York: Springer, 1993. 73\u2013114"},{"key":"3599_CR18","volume-title":"Front-End Vision and Multi-Scale Image Analysis: Multi-Scale Computer Vision Theory and Applications, Written in Mathematica","author":"B M H Romeny","year":"2008","unstructured":"Romeny B M H. Front-End Vision and Multi-Scale Image Analysis: Multi-Scale Computer Vision Theory and Applications, Written in Mathematica. Berlin: Springer Science & Business Media, 2008"},{"key":"3599_CR19","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015. 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"3599_CR20","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":"3599_CR21","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, 2015. 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3599_CR22","doi-asserted-by":"crossref","unstructured":"Chen L, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of European Conference on Computer Vision, 2018. 801\u2013818","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"3599_CR23","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 the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 1925\u20131934","DOI":"10.1109\/CVPR.2017.549"},{"key":"3599_CR24","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, et al. Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"key":"3599_CR25","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, 2018. 418\u2013434","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"3599_CR26","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2021","unstructured":"Wang J, Sun K, Cheng T, et al. Deep high-resolution representation learning for visual recognition. IEEE Trans Pattern Anal Mach Intell, 2021, 43: 3349\u20133364","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3599_CR27","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, et al. Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE International Conference on Computer Vision, 2021","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3599_CR28","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":"3599_CR29","doi-asserted-by":"publisher","first-page":"120106","DOI":"10.1007\/s11432-019-2738-y","volume":"63","author":"S Ma","year":"2020","unstructured":"Ma S, Pang Y W, Pan J, et al. Preserving details in semantics-aware context for scene parsing. Sci China Inf Sci, 2020, 63: 120106","journal-title":"Sci China Inf Sci"},{"key":"3599_CR30","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":"3599_CR31","doi-asserted-by":"publisher","first-page":"140305","DOI":"10.1007\/s11432-019-2791-7","volume":"63","author":"N J He","year":"2020","unstructured":"He N J, Fang L Y, Plaza A. Hybrid first and second order attention Unet for building segmentation in remote sensing images. Sci China Inf Sci, 2020, 63: 140305","journal-title":"Sci China Inf Sci"},{"key":"3599_CR32","doi-asserted-by":"crossref","unstructured":"Li Q, Yang W, Liu W, et al. From contexts to locality: ultra-high resolution image segmentation via locality-aware contextual correlation. In: Proceedings of the IEEE International Conference on Computer Vision, 2021. 7252\u20137261","DOI":"10.1109\/ICCV48922.2021.00716"},{"key":"3599_CR33","doi-asserted-by":"publisher","first-page":"111322","DOI":"10.1016\/j.rse.2019.111322","volume":"237","author":"X Y Tong","year":"2020","unstructured":"Tong X Y, Xia G S, Lu Q, et al. Land-cover classification with high-resolution remote sensing images using transferable deep models. Remote Sens Environ, 2020, 237: 111322","journal-title":"Remote Sens Environ"},{"key":"3599_CR34","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1016\/j.rse.2017.01.026","volume":"191","author":"Z Li","year":"2017","unstructured":"Li Z, Shen H, Li H, et al. Multi-feature combined cloud and cloud shadow detection in GaoFen-1 wide field of view imagery. Remote Sens Environ, 2017, 191: 342\u2013358","journal-title":"Remote Sens Environ"},{"key":"3599_CR35","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H, et al. Dual attention network for scene segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019. 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"},{"key":"3599_CR36","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang X, Huang L, et al. CCNet: criss-cross attention for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, 2019. 603\u2013612","DOI":"10.1109\/ICCV.2019.00069"},{"key":"3599_CR37","doi-asserted-by":"publisher","first-page":"5367","DOI":"10.1109\/TGRS.2020.2964675","volume":"58","author":"L Ding","year":"2020","unstructured":"Ding L, Zhang J, Bruzzone L. Semantic segmentation of large-size VHR remote sensing images using a two-stage multiscale training architecture. IEEE Trans Geosci Remote Sens, 2020, 58: 5367\u20135376","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"3599_CR38","first-page":"1","volume":"60","author":"L Ding","year":"2022","unstructured":"Ding L, Lin D, Lin S, et al. Looking outside the window: wide-context transformer for the semantic segmentation of high-resolution remote sensing images. IEEE Trans Geosci Remote Sens, 2022, 60: 1\u201313","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"3599_CR39","doi-asserted-by":"crossref","unstructured":"Chen W, Jiang Z, Wang Z, et al. Collaborative global-local networks for memory-efficient segmentation of ultra-high resolution images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019. 8924\u20138933","DOI":"10.1109\/CVPR.2019.00913"},{"key":"3599_CR40","unstructured":"Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions. In: Proceedings of International Conference on Learning Representations, 2016"},{"key":"3599_CR41","unstructured":"Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks. In: Proceedings of Advances in Neural Information Processing Systems, 2014. 3104\u20133112"},{"key":"3599_CR42","unstructured":"Devlin J, Chang M, Lee K, et al. BERT: pre-training of deep bidirectional transformers for language understanding. 2018. ArXiv:1810.04805"},{"key":"3599_CR43","unstructured":"Yuan Y, Huang L, Guo J, et al. OCNet: object context network for scene parsing. 2021. ArXiv:1809.00916"},{"key":"3599_CR44","doi-asserted-by":"crossref","unstructured":"Li D, Hu J, Wang C, et al. Involution: inverting the inherence of convolution for visual recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021. 12321\u201312330","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"3599_CR45","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J, et al. CBAM: convolutional block attention module. In: Proceedings of European Conference on Computer Vision, 2018. 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"3599_CR46","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, 2018. 267\u2013283","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"3599_CR47","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16\u00d716 words: transformers for image recognition at scale. In: Proceedings of International Conference on Learning Representations, 2021"},{"key":"3599_CR48","unstructured":"Touvron H, Cord M, Douze M, et al. Training data-efficient image transformers & distillation through attention. In: Proceedings of International Conference on Machine Learning, 2021. 10347\u201310357"},{"key":"3599_CR49","doi-asserted-by":"crossref","unstructured":"Zheng S, Lu J, Zhao H, et al. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021. 6881\u20136890","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"3599_CR50","doi-asserted-by":"crossref","unstructured":"Cheng H K, Chung J, Tai Y, et al. CascadePSP: toward class-agnostic and very high-resolution segmentation via global and local refinement. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020. 8890\u20138899","DOI":"10.1109\/CVPR42600.2020.00891"},{"key":"3599_CR51","doi-asserted-by":"crossref","unstructured":"Li X, You A, Zhu Z, et al. Semantic flow for fast and accurate scene parsing. In: Proceedings of European Conference on Computer Vision, 2020. 775\u2013793","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"3599_CR52","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"3599_CR53","doi-asserted-by":"crossref","unstructured":"Liu C, Chen L, Schroff F, et al. Auto-DeepLab: hierarchical neural architecture search for semantic image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019. 82\u201392","DOI":"10.1109\/CVPR.2019.00017"},{"key":"3599_CR54","doi-asserted-by":"crossref","unstructured":"Zhang X, Xu H, Mo H, et al. DCNAs: densely connected neural architecture search for semantic image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021. 13956\u201313967","DOI":"10.1109\/CVPR46437.2021.01374"},{"key":"3599_CR55","doi-asserted-by":"publisher","first-page":"106622","DOI":"10.1016\/j.knosys.2020.106622","volume":"212","author":"X He","year":"2021","unstructured":"He X, Zhao K, Chu X. AutoML: a survey of the state-of-the-art. Knowledge-Based Syst, 2021, 212: 106622","journal-title":"Knowledge-Based Syst"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-022-3599-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-022-3599-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-022-3599-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T20:27:57Z","timestamp":1716150477000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-022-3599-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,27]]},"references-count":55,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["3599"],"URL":"https:\/\/doi.org\/10.1007\/s11432-022-3599-y","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,27]]},"assertion":[{"value":"19 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 October 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"140305"}}