{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:45:16Z","timestamp":1778085916647,"version":"3.51.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"The Natural Science Foundation of Shandong Province, China","award":["ZR2022MD090, ZR2024MF102"],"award-info":[{"award-number":["ZR2022MD090, ZR2024MF102"]}]},{"name":"The Natural Science Foundation of Shandong Province, China","award":["ZR2022MD090, ZR2024MF102"],"award-info":[{"award-number":["ZR2022MD090, ZR2024MF102"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s00530-025-02029-4","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T09:43:44Z","timestamp":1760694224000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Fourier aids CNN and transformer for semantic segmentation of remote sensing images"],"prefix":"10.1007","volume":"31","author":[{"given":"Jun","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youzhou","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baodi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keding","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"2029_CR1","first-page":"56","volume":"196","author":"X Huang","year":"2017","unstructured":"Huang, X., Wen, D., Li, J., Qin, R.: Multi-level monitoring of subtle urban changes for themegacities of China using high-resolution multi-viewsatellite imagery. Remote Sens. 196, 56\u201375 (2017)","journal-title":"Remote Sens."},{"issue":"3","key":"2029_CR2","first-page":"397","volume":"6","author":"G Kouziokas","year":"2017","unstructured":"Kouziokas, G., Perakis, K.: Decision support system based on artificial intelligence, GIS and remote sensing for sustainable public and judicial management. Eur. J. Sustain. Dev. 6(3), 397\u2013404 (2017)","journal-title":"Eur. J. Sustain. Dev."},{"key":"2029_CR3","first-page":"1","volume":"61","author":"L Fan","year":"2023","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. 61, 1\u201311 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2029_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2024.3490732","volume":"21","author":"Y Ma","year":"2024","unstructured":"Ma, Y., Wang, Y., Liu, X., Wang, H.: SWINT-RESNet: An improved remote sensing image segmentation model based on transformer. IEEE Geosci. Remote Sens. Lett. 21, 1\u20135 (2024)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"2029_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3230846","volume":"60","author":"X He","year":"2022","unstructured":"He, X., Zhou, Y., Zhao, J., Zhang, D., Yao, R., Xue, Y.: Swin transformer embedding UNet for remote sensing image semantic segmentation. IEEE Trans. Geosci. Remote Sens. 60, 1\u201315 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2029_CR6","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.isprsjprs.2020.09.025","volume":"169","author":"C Zhang","year":"2020","unstructured":"Zhang, C., Atkinson, P., Wen, Z.: Identifying and mapping individual plants in a highly diverse high-elevation ecosystem using UAV imagery and deep learning. ISPRS J. Photogramm Remote Sens. 169, 280\u2013291 (2020)","journal-title":"ISPRS J. Photogramm Remote Sens."},{"key":"2029_CR7","doi-asserted-by":"publisher","first-page":"11593","DOI":"10.1016\/j.rse.2019.111593","volume":"237","author":"C Zhang","year":"2020","unstructured":"Zhang, C., Harrison, P., Pan, X., Li, H., Atkinson, P.: Scale sequence joint deep learning (SS-JDL) for land use and land cover classification. Remote Sens. Environ. 237, 11593 (2020)","journal-title":"Remote Sens. Environ."},{"key":"2029_CR8","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2029_CR9","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Li, B., Tang, L., Kuang, S., Wu, S., Ding, S.: Detecting Camouflaged Object in Frequency Domain. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4494\u20134503 (2022)","DOI":"10.1109\/CVPR52688.2022.00446"},{"key":"2029_CR10","doi-asserted-by":"crossref","unstructured":"Qian, Y., Yin, G., Sheng, L., Chen, Z., Shao, J.: Thinking in frequency: Face forgery detection by mining frequency-aware clues. In: European conference on computer vision, pp. 86\u2013103 (2020)","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"2029_CR11","first-page":"1","volume":"61","author":"X Qiao","year":"2023","unstructured":"Qiao, X., Roy, S.K., Huang, W.: Multiscale neighborhood attention transformer with optimized Spatial pattern for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 61, 1\u201315 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2029_CR12","doi-asserted-by":"publisher","first-page":"10344","DOI":"10.1109\/JSTARS.2023.3328115","volume":"16","author":"X Qiao","year":"2023","unstructured":"Qiao, X., Huang, W.: A dual frequency transformer network for hyperspectral image classification. IEEE J. Sel. Top. Appl. Earth Obs Remote Sens. 16, 10344\u201310358 (2023)","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs Remote Sens."},{"key":"2029_CR13","doi-asserted-by":"crossref","unstructured":"Qiao, X., Huang, W.: Spectral-spatial-frequency transformer network for hyperspectral image classification. In: 2023 IEEE Sensors Applications Symposium (SAS), pp. 1\u20136 (2023)","DOI":"10.1109\/SAS58821.2023.10254115"},{"key":"2029_CR14","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhu, Y., Papandreou, G., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision (ECCV), pp. 833\u2013851 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2029_CR15","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":"2029_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.: 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":"2029_CR17","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 the IEEE\/CVF conference on computer vision and pattern recognition, pp. 3149\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"issue":"9","key":"2029_CR18","doi-asserted-by":"publisher","first-page":"6309","DOI":"10.1109\/TGRS.2020.2976658","volume":"58","author":"Q Liu","year":"2020","unstructured":"Liu, Q., Kampffmeyer, M., Jenssen, R., Salberg, A.: Dense dilated convolutions\u2019 merging network for land cover classification. IEEE Trans. Geosci. Remote Sens. 58(9), 6309\u20136320 (2020)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"16","key":"2029_CR19","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."},{"key":"2029_CR20","first-page":"1","volume":"60","author":"R Li","year":"2022","unstructured":"Li, R., Zheng, S., Zhang, C., Duan, C., Su, J., Wang, L.: Multiattention network for semantic segmentation of fine-resolution remote sensing images. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2029_CR21","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.U.: NetFormer: 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":"2029_CR22","first-page":"1","volume":"19","author":"L Li","year":"2022","unstructured":"Li, L., Duan, R., Zhang, C., Meng, C., Fang, X.: A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2022)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"2029_CR23","first-page":"15475","volume":"34","author":"Q Zhang","year":"2021","unstructured":"Zhang, Q., Yang, Y.: Rest: An efficient transformer for visual recognition. Adv. Neural Inf. Process. Syst. 34, 15475\u201315485 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"24","key":"2029_CR24","doi-asserted-by":"publisher","first-page":"5100","DOI":"10.3390\/rs13245100","volume":"13","author":"T Panboonyuen","year":"2021","unstructured":"Panboonyuen, T., Jitkajornwanich, K., Lawawirojwong, S., Srestasathiern, P., Vateekul, P.: Transformer-based decoder designs for semantic segmentation on remotely sensed images. Remote Sens. 13(24), 5100 (2021)","journal-title":"Remote Sens."},{"key":"2029_CR25","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, L., Luo, P.: SegFormer: Simple and efficient design for semantic segmentation with Transformers. Adv. Neural Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2029_CR26","first-page":"1","volume":"60","author":"C Jiang","year":"2022","unstructured":"Jiang, C., Zhang, W., Wang, Y., Zhao, W., Wang, Q.: Transformer and CNN hybrid deep neural network for semantic segmentation of very-high-resolution remote sensing imagery. IEEE Trans. Geosci. Remote Sens. 60, 1\u201320 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2029_CR27","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1109\/LRA.2020.3039744","volume":"6","author":"P Hu","year":"2021","unstructured":"Hu, P., Perazzi, F., Heilbron, F., Wang, O., Lin, Z., Saenko, S.: Real-time semantic segmentation with fast attention. IEEE Robot Autom. Lett. 6, 263\u2013270 (2021)","journal-title":"IEEE Robot Autom. Lett."},{"key":"2029_CR28","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"2029_CR29","first-page":"4479","volume":"33","author":"L Chi","year":"2020","unstructured":"Chi, L., Jiang, B., Mu, Y.: Fast fourier Convolution. Adv. Neural Inf. Process. Syst. 33, 4479\u20134488 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2029_CR30","doi-asserted-by":"crossref","unstructured":"Yu, Z., Zhao, C., Wang, Z., Qin, Y., Su, Z., Li, X., Zhou, F., Zhao, G.: Searching central difference convolutional networks for face anti-spoofing. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5295\u20135305 (2020)","DOI":"10.1109\/CVPR42600.2020.00534"},{"key":"2029_CR31","doi-asserted-by":"crossref","unstructured":"Chen, C., Fan, Q., Panda, R.: Crossvit: Cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"2029_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2024.3490732","volume":"21","author":"X Ma","year":"2024","unstructured":"Ma, X., Zhang, X., Pun, M.: Rs 3 mamba: Visual state space model for remote sensing image semantic segmentation. IEEE Geosci. Remote Sens. Lett. 21, 1\u20135 (2024)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"2029_CR33","first-page":"1","volume":"61","author":"X Li","year":"2023","unstructured":"Li, X., Xu, F., Liu, F., Lyu, X., Tong, Y., 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":"2","key":"2029_CR34","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1007\/s10278-022-00735-3","volume":"36","author":"M Yeung","year":"2023","unstructured":"Yeung, M., Rundo, L., Nan, Y., Sala, E., Yang, G.: Calibrating the dice loss to handle neural network overconfidence for biomedical image segmentation. J. Digit. Imaging. 36(2), 739\u2013752 (2023)","journal-title":"J. Digit. Imaging"},{"key":"2029_CR35","doi-asserted-by":"publisher","first-page":"107611","DOI":"10.1016\/j.patcog.2020.107611","volume":"110","author":"M Or\u0161i\u0107","year":"2021","unstructured":"Or\u0161i\u0107, M., \u0160egvi\u0107, S.: Efficient semantic segmentation with pyramidal fusion. Pattern Recogn. 110, 107611 (2021)","journal-title":"Pattern Recogn."},{"key":"2029_CR36","first-page":"04306","volume":"2102","author":"J Chen","year":"2021","unstructured":"Chen, J., Lu, Y., Yu, Q.: Transunet: Transformers make strong encoders for medical image segmentation. ArXiv Preprint arXiv. 2102, 04306 (2021)","journal-title":"ArXiv Preprint arXiv"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02029-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02029-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02029-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T06:59:48Z","timestamp":1766127588000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02029-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":36,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2029"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02029-4","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"4 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2025","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"451"}}