{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T08:39:43Z","timestamp":1770799183716,"version":"3.50.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T00:00:00Z","timestamp":1767830400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T00:00:00Z","timestamp":1767830400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Philosophy and Social Sciences Planning Project of Tianjin","award":["TJGL19XSX-045"],"award-info":[{"award-number":["TJGL19XSX-045"]}]},{"name":"Philosophy and Social Sciences Planning Project of Tianjin","award":["TJGL19XSX-045"],"award-info":[{"award-number":["TJGL19XSX-045"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s00530-025-02128-2","type":"journal-article","created":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T11:40:16Z","timestamp":1767872416000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic segmentation network for remote sensing images based on category-aware cross-fusion"],"prefix":"10.1007","volume":"32","author":[{"given":"Zhongwei","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Zhaoyang","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Shudong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Haijie","family":"Qin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,8]]},"reference":[{"issue":"17","key":"2128_CR1","doi-asserted-by":"publisher","first-page":"4213","DOI":"10.3390\/rs14174213","volume":"14","author":"H Bai","year":"2022","unstructured":"Bai, H., Li, Z., Guo, H., Chen, H., Luo, P.: Urban green space planning based on remote sensing and geographic information systems. Remote Sens. 14(17), 4213 (2022)","journal-title":"Remote Sens."},{"key":"2128_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109570","volume":"227","author":"P Zhang","year":"2024","unstructured":"Zhang, P., Zhang, S., Wang, J., Sun, X.: Identifying rice lodging based on semantic segmentation architecture optimization with uav remote sensing imaging. Comput. Electron. Agric. 227, 109570 (2024)","journal-title":"Comput. Electron. Agric."},{"key":"2128_CR3","volume":"120","author":"A Jamali","year":"2023","unstructured":"Jamali, A., Roy, S.K., Li, J., Ghamisi, P.: Transu-net++: Rethinking attention gated transu-net for deforestation mapping. Int. J. Appl. Earth Obs. Geoinf. 120, 103332 (2023)","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"issue":"7","key":"2128_CR4","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1007\/s10346-022-01847-1","volume":"19","author":"Q Xu","year":"2022","unstructured":"Xu, Q., Ouyang, C., Jiang, T., Yuan, X., Fan, X., Cheng, D.: Mffenet and adanet: a robust deep transfer learning method and its application in high precision and fast cross-scene recognition of earthquake-induced landslides. Landslides 19(7), 1617\u20131647 (2022)","journal-title":"Landslides"},{"key":"2128_CR5","first-page":"1","volume":"61","author":"F Chen","year":"2023","unstructured":"Chen, F., Balzter, H., Zhou, F., Ren, P., Zhou, H.: Dgnet: distribution guided efficient learning for oil spill image segmentation. IEEE Trans. Geosci. Remote Sens. 61, 1\u201317 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2128_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109570","volume":"227","author":"P Zhang","year":"2024","unstructured":"Zhang, P., Zhang, S., Wang, J., Sun, X.: Identifying rice lodging based on semantic segmentation architecture optimization with uav remote sensing imaging. Comput. Electron. Agric. 227, 109570 (2024)","journal-title":"Comput. Electron. Agric."},{"key":"2128_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jenvman.2020.110392","volume":"263","author":"AP Rudke","year":"2020","unstructured":"Rudke, A.P., De Souza, V.A.S., Dos Santos, A.M., Xavier, A.C.F., Rotunno Filho, O.C., Martins, J.A.: Impact of mining activities on areas of environmental protection in the southwest of the amazon: A gis-and remote sensing-based assessment. J. Environ. Manag. 263, 110392 (2020)","journal-title":"J. Environ. Manag."},{"issue":"17","key":"2128_CR8","doi-asserted-by":"publisher","first-page":"4213","DOI":"10.3390\/rs14174213","volume":"14","author":"H Bai","year":"2022","unstructured":"Bai, H., Li, Z., Guo, H., Chen, H., Luo, P.: Urban green space planning based on remote sensing and geographic information systems. Remote Sens. 14(17), 4213 (2022)","journal-title":"Remote Sens."},{"key":"2128_CR9","first-page":"1","volume":"61","author":"F Chen","year":"2023","unstructured":"Chen, F., Balzter, H., Zhou, F., Ren, P., Zhou, H.: Dgnet: distribution guided efficient learning for oil spill image segmentation. IEEE Trans. Geosci. Remote Sens. 61, 1\u201317 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"2128_CR10","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1080\/01431160412331269698","volume":"26","author":"M Pal","year":"2005","unstructured":"Pal, M.: Random forest classifier for remote sensing classification. Int. J. Remote Sens. 26(1), 217\u2013222 (2005)","journal-title":"Int. J. Remote Sens."},{"key":"2128_CR11","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected crfs with gaussian edge potentials. Adv. Neural. Inf. Process. Syst. 24 (2011)"},{"key":"2128_CR12","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, proceedings, part III 18 (Springer, 2015). pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2128_CR13","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 European conference on computer vision (ECCV). pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2128_CR14","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"2128_CR15","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.isprsjprs.2020.09.019","volume":"170","author":"X Zheng","year":"2020","unstructured":"Zheng, X., Huan, L., Xia, G.S., Gong, J.: Parsing very high resolution urban scene images by learning deep convnets with edge-aware loss. ISPRS J. Photogramm. Remote. Sens. 170, 15\u201328 (2020)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"2128_CR16","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.isprsjprs.2021.09.005","volume":"181","author":"R Li","year":"2021","unstructured":"Li, R., Zheng, S., Zhang, C., Duan, C., Wang, L., Atkinson, P.M.: Abcnet: Attentive bilateral contextual network for efficient semantic segmentation of fine-resolution remotely sensed imagery. ISPRS J. Photogramm. Remote. Sens. 181, 84\u201398 (2021)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"2128_CR17","first-page":"1","volume":"19","author":"R Li","year":"2021","unstructured":"Li, R., Zheng, S., Duan, C., Su, J., Zhang, C.: Multistage attention resu-net for semantic segmentation of fine-resolution remote sensing images. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2021)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"2128_CR18","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"2128_CR19","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.isprsjprs.2020.09.019","volume":"170","author":"X Zheng","year":"2020","unstructured":"Zheng, X., Huan, L., Xia, G.S., Gong, J.: Parsing very high resolution urban scene images by learning deep convnets with edge-aware loss. ISPRS J. Photogramm. Remote. Sens. 170, 15\u201328 (2020)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"2128_CR20","doi-asserted-by":"crossref","unstructured":"Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., Wang, M.: Swin-unet: Unet-like pure transformer for medical image segmentation. In: European conference on computer vision (Springer, 2022). pp. 205\u2013218","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"2128_CR21","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., Zhou, Y.: Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)"},{"key":"2128_CR22","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.isprsjprs.2022.06.008","volume":"190","author":"L Wang","year":"2022","unstructured":"Wang, L., Li, R., Zhang, C., Fang, S., Duan, C., Meng, X., Atkinson, P.M.: Unetformer: A unet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery. ISPRS J. Photogramm. Remote. Sens. 190, 196\u2013214 (2022)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"2128_CR23","doi-asserted-by":"crossref","unstructured":"Fan, L., Zhou, Y., Liu, H., Li, Y., Cao, D.: Combining swin transformer with unet for remote sensing image semantic segmentation. IEEE Trans. Geosci. Remote Sens. (2023)","DOI":"10.1109\/TGRS.2023.3329152"},{"key":"2128_CR24","doi-asserted-by":"crossref","unstructured":"Wu, H., Huang, P., Zhang, M., Tang, W., Yu, X.: Cmtfnet: Cnn and multiscale transformer fusion network for remote sensing image semantic segmentation. IEEE Trans. Geosci. Remote Sens. (2023)","DOI":"10.1109\/TGRS.2023.3314641"},{"key":"2128_CR25","doi-asserted-by":"crossref","unstructured":"Ni, Y., Liu, J., Cui, J., Yang, Y., Wang, X.: Edge guidance network for semantic segmentation of high resolution remote sensing images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. (2023)","DOI":"10.1109\/JSTARS.2023.3316307"},{"key":"2128_CR26","doi-asserted-by":"crossref","unstructured":"Haase, D., Amthor, M.: Rethinking depthwise separable convolutions: How intra-kernel correlations lead to improved mobilenets. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 14600\u201314609 (2020)","DOI":"10.1109\/CVPR42600.2020.01461"},{"key":"2128_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Rahman\u00a0Siddiquee, M.M., Tajbakhsh, N., Liang, J.: 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 4 (Springer, 2018). pp. 3\u201311","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"2128_CR28","first-page":"1","volume":"60","author":"R Li","year":"2021","unstructured":"Li, R., Zheng, S., Zhang, C., Duan, C., Su, J., Wang, L., Atkinson, P.M.: Multiattention network for semantic segmentation of fine-resolution remote sensing images. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2128_CR29","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: Transformer for semantic segmentation, In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 7262\u20137272 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"2128_CR30","doi-asserted-by":"crossref","unstructured":"Ni, Y., Liu, J., Chi, W., Wang, X., Li, D.: Cgglnet: Semantic segmentation network for remote sensing images based on category-guided global-local feature interaction. IEEE Transactions on Geoscience and Remote Sensing (2024)","DOI":"10.1109\/TGRS.2024.3379398"},{"issue":"3","key":"2128_CR31","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1080\/01431161.2022.2030071","volume":"43","author":"R Li","year":"2022","unstructured":"Li, R., Wang, L., Zhang, C., Duan, C., Zheng, S.: $${\\rm A} ^2\\text{-FPN }$$ for semantic segmentation of fine-resolution remotely sensed images. Int. J. Remote Sens. 43(3), 1131\u20131155 (2022)","journal-title":"Int. J. Remote Sens."},{"key":"2128_CR32","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 the IEEE\/CVF international conference on computer vision. pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2128_CR33","doi-asserted-by":"crossref","unstructured":"Geng, J., Song, S., Jiang, W.: Dual-path feature aware network for remote sensing image semantic segmentation. IEEE Trans. Circ. Syst. Video Tech. (2023)","DOI":"10.1109\/TCSVT.2023.3317937"},{"key":"2128_CR34","doi-asserted-by":"crossref","unstructured":"Ma, X., Zhang, X., Pun, M.O., Liu, M.: A multilevel multimodal fusion transformer for remote sensing semantic segmentation. IEEE Trans. Geosci. Remote Sens. (2024)","DOI":"10.1109\/TGRS.2024.3373033"},{"key":"2128_CR35","doi-asserted-by":"crossref","unstructured":"Xiang, X., Gong, W., Li, S., Chen, J., Ren, T.: Tcnet: Multiscale fusion of transformer and cnn for semantic segmentation of remote sensing images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. (2024)","DOI":"10.1109\/JSTARS.2024.3349625"},{"key":"2128_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, H., Wang, C., Xie, J.: Co-occurrent features in semantic segmentation. In:Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 548\u2013557 (2019)","DOI":"10.1109\/CVPR.2019.00064"},{"key":"2128_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, F., Chen, Y., Li, Z., Hong, Z., Liu, J., Ma, F., Han, J., Ding, E.: Acfnet: Attentional class feature network for semantic segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 6798\u20136807 (2019)","DOI":"10.1109\/ICCV.2019.00690"},{"key":"2128_CR38","doi-asserted-by":"crossref","unstructured":"Lu, T., Wang, L., Wu, G.: Cga-net: Category guided aggregation for point cloud semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11693\u201311702 (2021)","DOI":"10.1109\/CVPR46437.2021.01152"},{"issue":"2","key":"2128_CR39","doi-asserted-by":"publisher","first-page":"361","DOI":"10.3390\/rs15020361","volume":"15","author":"M Yuan","year":"2023","unstructured":"Yuan, M., Ren, D., Feng, Q., Wang, Z., Dong, Y., Lu, F., Wu, X.: Mcafnet: A multiscale channel attention fusion network for semantic segmentation of remote sensing images. Remote Sens. 15(2), 361 (2023)","journal-title":"Remote Sens."},{"key":"2128_CR40","doi-asserted-by":"crossref","unstructured":"Wu, H., Huang, P., Zhang, M., Tang, W.: Ctfnet: Cnn-transformer fusion network for remote sensing image semantic segmentation. IEEE Geosci. Remote Sen. Lett. (2023)","DOI":"10.1109\/TGRS.2023.3314641"},{"key":"2128_CR41","first-page":"1","volume":"61","author":"X Li","year":"2023","unstructured":"Li, X., Xu, F., Liu, F., Lyu, X., Tong, Y., Xu, Z., Zhou, J.: A synergistical attention model for semantic segmentation of remote sensing images. IEEE Trans. Geosci. Remote Sens. 61, 1\u201316 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"16","key":"2128_CR42","doi-asserted-by":"publisher","first-page":"3065","DOI":"10.3390\/rs13163065","volume":"13","author":"L Wang","year":"2021","unstructured":"Wang, L., Li, R., Wang, D., Duan, C., Wang, T., Meng, X.: Transformer meets convolution: A bilateral awareness network for semantic segmentation of very fine resolution urban scene images. Remote Sens. 13(16), 3065 (2021)","journal-title":"Remote Sens."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02128-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02128-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02128-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T04:18:46Z","timestamp":1770783526000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02128-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,8]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2128"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02128-2","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,8]]},"assertion":[{"value":"3 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest\/Conflict of interest"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Informed consent","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"69"}}