{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:53:12Z","timestamp":1784231592636,"version":"3.55.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,5,18]],"date-time":"2024-05-18T00:00:00Z","timestamp":1715990400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,18]],"date-time":"2024-05-18T00:00:00Z","timestamp":1715990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62371015"],"award-info":[{"award-number":["62371015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Natural Science Foundation,China","award":["L211017"],"award-info":[{"award-number":["L211017"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s00371-024-03416-0","type":"journal-article","created":{"date-parts":[[2024,5,18]],"date-time":"2024-05-18T11:01:50Z","timestamp":1716030110000},"page":"1273-1291","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Unpaved road segmentation of UAV imagery via a global vision transformer with dilated cross window self-attention for dynamic map"],"prefix":"10.1007","volume":"41","author":[{"given":"Wensheng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiafeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,18]]},"reference":[{"issue":"1","key":"3416_CR1","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1017\/S0373463320000375","volume":"74","author":"F Liu","year":"2021","unstructured":"Liu, F., Liu, Y., Nie, Z., Gao, Y.: Precise single-frequency positioning using low-cost receiver with the aid of lane-level map matching for land vehicle navigation. J. Navig. 74(1), 24\u201337 (2021). https:\/\/doi.org\/10.1017\/S0373463320000375","journal-title":"J. Navig."},{"issue":"1","key":"3416_CR2","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/s00371-023-02791-4","volume":"40","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Xiu, Y.: Image stitching based on human visual system and SIFT algorithm. Vis. Comput. 40(1), 427\u2013439 (2024). https:\/\/doi.org\/10.1007\/s00371-023-02791-4","journal-title":"Vis. Comput."},{"issue":"2","key":"3416_CR3","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1109\/36.992826","volume":"40","author":"W Shi","year":"2002","unstructured":"Shi, W., Zhu, C.: The line segment match method for extracting road network from high-resolution satellite images. IEEE Trans. Geosci. Remote Sens. 40(2), 511\u2013514 (2002). https:\/\/doi.org\/10.1109\/36.992826","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"3416_CR4","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.isprsjprs.2014.01.008","volume":"90","author":"X Huang","year":"2014","unstructured":"Huang, X., Lu, Q., Zhang, L.: A multi-index learning approach for classification of high-resolution remotely sensed images over urban areas. J. Photogramm. Remote Sens. 90(1), 36\u201348 (2014). https:\/\/doi.org\/10.1016\/j.isprsjprs.2014.01.008","journal-title":"J. Photogramm. Remote Sens."},{"issue":"7","key":"3416_CR5","doi-asserted-by":"publisher","first-page":"1713","DOI":"10.1109\/TITS.2016.2622280","volume":"18","author":"H Zhou","year":"2017","unstructured":"Zhou, H., Kong, H., Wei, L., Creighton, D., Nahavandi, S.: On detecting road regions in a single UAV image. IEEE Trans. Intell. Transp. Syst. 18(7), 1713\u20131722 (2017). https:\/\/doi.org\/10.1109\/TITS.2016.2622280","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"9","key":"3416_CR6","doi-asserted-by":"publisher","first-page":"7209","DOI":"10.1109\/TGRS.2019.2912301","volume":"57","author":"X Yang","year":"2019","unstructured":"Yang, X., Li, X., Ye, Y., Lau, R.Y.K., Zhang, X., Huang, X.: Road detection and centerline extraction via deep recurrent convolutional neural network U-Net. IEEE Trans. Geosci. Remote Sens. 57(9), 7209\u20137220 (2019). https:\/\/doi.org\/10.1109\/TGRS.2019.2912301","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"3416_CR7","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1109\/TII.2021.3085669","volume":"18","author":"J Li","year":"2022","unstructured":"Li, J., Chen, J., Sheng, B., Li, P., Yang, P., Feng, D.D., Qi, J.: Automatic detection and classification system of domestic waste via multimodel cascaded convolutional neural network. IEEE Trans. Ind. Informat. 18(1), 163\u2013173 (2022). https:\/\/doi.org\/10.1109\/TII.2021.3085669","journal-title":"IEEE Trans. Ind. Informat."},{"issue":"8","key":"3416_CR8","doi-asserted-by":"publisher","first-page":"4499","DOI":"10.1109\/TNNLS.2021.3116209","volume":"34","author":"Z Xie","year":"2023","unstructured":"Xie, Z., Zhang, W., Sheng, B., Li, P., Chen, C.L.P.: BaGFN: Broad attentive graph fusion network for high-order feature interactions. IEEE Trans. Neural Networks Learn. Syst. 34(8), 4499\u20134513 (2023). https:\/\/doi.org\/10.1109\/TNNLS.2021.3116209","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"issue":"7","key":"3416_CR9","doi-asserted-by":"publisher","first-page":"6662","DOI":"10.1109\/TCYB.2021.3079311","volume":"52","author":"B Sheng","year":"2022","unstructured":"Sheng, B., Li, P., Ali, R., Chen, C.L.P.: Improving video temporal consistency via broad learning system. IEEE Trans. Cybern. 52(7), 6662\u20136675 (2022). https:\/\/doi.org\/10.1109\/TCYB.2021.3079311","journal-title":"IEEE Trans. Cybern."},{"issue":"1","key":"3416_CR10","doi-asserted-by":"publisher","first-page":"2226","DOI":"10.1109\/TMM.2022.3144890","volume":"25","author":"N Jiang","year":"2023","unstructured":"Jiang, N., Sheng, B., Li, P., Lee, T.-Y.: PhotoHelper: Portrait photographing guidance via deep feature retrieval and fusion. IEEE Trans. Multim. 25(1), 2226\u20132238 (2023). https:\/\/doi.org\/10.1109\/TMM.2022.3144890","journal-title":"IEEE Trans. Multim."},{"issue":"6","key":"3416_CR11","doi-asserted-by":"publisher","first-page":"4673","DOI":"10.1109\/TGRS.2020.3016086","volume":"59","author":"P Shamsolmoali","year":"2021","unstructured":"Shamsolmoali, P., Zareapoor, M., Zhou, H., Wang, R., Yang, J.: Road segmentation for remote sensing images using adversarial spatial pyramid networks. IEEE Trans. Geosci. Remote Sens. 59(6), 4673\u20134688 (2021). https:\/\/doi.org\/10.1109\/TGRS.2020.3016086","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"3416_CR12","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1007\/s12524-019-01077-4","volume":"48","author":"PK Soni","year":"2020","unstructured":"Soni, P.K., Rajpal, N., Mehta, R.: Semiautomatic road extraction framework based on shape features and LS-SVM from high-resolution images. J. Indian Soc. Remote Sens. 48(1), 513\u2013524 (2020). https:\/\/doi.org\/10.1007\/s12524-019-01077-4","journal-title":"J. Indian Soc. Remote Sens."},{"issue":"2","key":"3416_CR13","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.ejrs.2021.01.004","volume":"24","author":"PK Soni","year":"2021","unstructured":"Soni, P.K., Rajpal, N., Mehta, R.: Road network extraction using multi-layered filtering and tensor voting from aerial images. Egypt. J. Remote Sens. Space Sci. 24(2), 211\u2013219 (2021). https:\/\/doi.org\/10.1016\/j.ejrs.2021.01.004","journal-title":"Egypt. J. Remote Sens. Space Sci."},{"issue":"11","key":"3416_CR14","doi-asserted-by":"publisher","first-page":"21505","DOI":"10.1109\/TITS.2022.3192473","volume":"23","author":"S Gong","year":"2022","unstructured":"Gong, S., Zhou, H., Xue, F., Fang, C., Li, Y., Zhou, Y.: FastRoadSeg: Fast monocular road segmentation network. IEEE Trans. Intel. Trans. Syst. 23(11), 21505\u201321514 (2022). https:\/\/doi.org\/10.1109\/TITS.2022.3192473","journal-title":"IEEE Trans. Intel. Trans. Syst."},{"issue":"8","key":"3416_CR15","doi-asserted-by":"publisher","first-page":"11162","DOI":"10.1109\/TITS.2021.3101053","volume":"23","author":"H Zhang","year":"2022","unstructured":"Zhang, H., Song, Y., Chen, Y., Zhong, H., Liu, L., Wang, Y., Akilan, T., Wu, Q.M.J.: MRSDI-CNN: Multi-model rail surface defect inspection system based on convolutional neural networks. IEEE Trans. Intel. Trans. Syst. 23(8), 11162\u201311177 (2022). https:\/\/doi.org\/10.1109\/TITS.2021.3101053","journal-title":"IEEE Trans. Intel. Trans. Syst."},{"issue":"6","key":"3416_CR16","doi-asserted-by":"publisher","first-page":"1758","DOI":"10.1109\/TCSVT.2019.2905881","volume":"30","author":"X Liang","year":"2020","unstructured":"Liang, X., Zhang, J., Zhuo, L., Li, Y., Tian, Q.: Small object detection in unmanned aerial vehicle images using feature fusion and scaling-based single shot detector with spatial context analysis. IEEE Trans. Circuits Syst. Video Technol. 30(6), 1758\u20131770 (2020). https:\/\/doi.org\/10.1109\/TCSVT.2019.2905881","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3416_CR17","doi-asserted-by":"publisher","unstructured":"Wang, Y., Park, J.: Transitional asymmetric non-local neural networks for real-world dirt road segmentation. In: Int. Conf. Pattern Recognit., pp. 6949\u20136956 (2021). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412882","DOI":"10.1109\/ICPR48806.2021.9412882"},{"issue":"9","key":"3416_CR18","doi-asserted-by":"publisher","first-page":"9352","DOI":"10.1109\/TCYB.2021.3050558","volume":"52","author":"X Li","year":"2021","unstructured":"Li, X., Zhao, Z., Wang, Q.: ABSSNet: Attention-based spatial segmentation network for traffic scene understanding. IEEE Trans. Cyber. 52(9), 9352\u20139362 (2021). https:\/\/doi.org\/10.1109\/TCYB.2021.3050558","journal-title":"IEEE Trans. Cyber."},{"issue":"7","key":"3416_CR19","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1080\/15481603.2021.1972713","volume":"58","author":"A Abdollahi","year":"2021","unstructured":"Abdollahi, A., Pradhan, B., Alamri, A.: RoadVecNet: A new approach for simultaneous road network segmentation and vectorization from aerial and google earth imagery in a complex urban set-up. GISci. Remote Sens. 58(7), 1151\u20131174 (2021). https:\/\/doi.org\/10.1080\/15481603.2021.1972713","journal-title":"GISci. Remote Sens."},{"issue":"1","key":"3416_CR20","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1016\/j.eswa.2021.115090","volume":"183","author":"MA Elhassan","year":"2021","unstructured":"Elhassan, M.A., Huang, C., Yang, C., Munea, T.L.: DSANet: Dilated spatial attention for real-time semantic segmentation in urban street scenes. Expert Syst. Appl. 183(1), 1150\u20131190 (2021). https:\/\/doi.org\/10.1016\/j.eswa.2021.115090","journal-title":"Expert Syst. Appl."},{"issue":"9","key":"3416_CR21","doi-asserted-by":"publisher","first-page":"5520","DOI":"10.1109\/TITS.2020.2987819","volume":"22","author":"S Liu","year":"2021","unstructured":"Liu, S., Zhang, H., Shao, L., Yang, J.: Built-in depth-semantic coupled encoding for scene parsing, vehicle detection, and road segmentation. IEEE Trans. Intel. Trans. Syst. 22(9), 5520\u20135534 (2021). https:\/\/doi.org\/10.1109\/TITS.2020.2987819","journal-title":"IEEE Trans. Intel. Trans. Syst."},{"issue":"1","key":"3416_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3188908","volume":"60","author":"W Chen","year":"2022","unstructured":"Chen, W., Zhou, G., Liu, Z., Li, X., Zheng, X., Wang, L.: NIGAN: A framework for mountain road extraction integrating remote sensing road-scene neighborhood probability enhancements and improved conditional generative adversarial network. IEEE Trans. Geos. Remote Sens. 60(1), 1\u201315 (2022). https:\/\/doi.org\/10.1109\/TGRS.2022.3188908","journal-title":"IEEE Trans. Geos. Remote Sens."},{"key":"3416_CR23","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with Transformers. In: Eur. Conf. Comput. Vis., pp. 213\u2013229 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"11","key":"3416_CR24","doi-asserted-by":"publisher","first-page":"13489","DOI":"10.1109\/TPAMI.2023.3293885","volume":"45","author":"Z Chen","year":"2023","unstructured":"Chen, Z., Qiu, G., Li, P., Zhu, L., Yang, X., Sheng, B.: MNGNAS: Distilling adaptive combination of multiple searched networks for one-shot neural architecture search. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13489\u201313508 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3293885","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3416_CR25","doi-asserted-by":"publisher","unstructured":"Chen, T., Jiang, D., Li, R.: Swin Transformers make strong contextual encoders for VHR image road extraction. In: IEEE Int. Geosci. Remote Sens. Symp., pp. 3019\u20133022 (2022). https:\/\/doi.org\/10.1109\/IGARSS46834.2022.9883628","DOI":"10.1109\/IGARSS46834.2022.9883628"},{"issue":"1","key":"3416_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3168697","volume":"60","author":"L Ding","year":"2022","unstructured":"Ding, L., Lin, D., Lin, S., Zhang, J., Cui, X., Wang, Y., Tang, H., Bruzzone, L.: Looking outside the window: wide-context transformer for the semantic segmentation of high-resolution remote sensing images. IEEE Trans. Geos. Remote Sens. 60(1), 1\u201313 (2022). https:\/\/doi.org\/10.1109\/TGRS.2022.3168697","journal-title":"IEEE Trans. Geos. Remote Sens."},{"key":"3416_CR27","doi-asserted-by":"publisher","unstructured":"Li, A., Jiao, J., Li, N., Qi, W., Xu, W., Pang, M.: Conmw Transformer: A general vision Transformer backbone with merged-window attention. In: Int. Conf. on Image Process., pp. 1551\u20131555 (2022). https:\/\/doi.org\/10.1109\/ICIP46576.2022.9897179","DOI":"10.1109\/ICIP46576.2022.9897179"},{"key":"3416_CR28","doi-asserted-by":"publisher","unstructured":"Gao, L., Liu, H., Yang, M., Chen, L., Wan, Y., Xiao, Z., Qian, Y.: STransFuse: Fusing swin Transformer and convolutional neural network for remote sensing image semantic segmentation. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 14(1), 10990\u201311003 (2021). https:\/\/doi.org\/10.1109\/JSTARS.2021.3119654","DOI":"10.1109\/JSTARS.2021.3119654"},{"issue":"1","key":"3416_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3144165","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. Geos. Remote Sens. 60(1), 1\u201315 (2022). https:\/\/doi.org\/10.1109\/TGRS.2022.3144165","journal-title":"IEEE Trans. Geos. Remote Sens."},{"key":"3416_CR30","doi-asserted-by":"publisher","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P. H.: Rethinking semantic segmentation from a sequence-to-sequence perspective with Transformers. In: IEEE Conf. Comput. Vis. Pattern Recognit., pp. 6881\u20136890 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00681","DOI":"10.1109\/CVPR46437.2021.00681"},{"issue":"1","key":"3416_CR31","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: Efficient attention pyramid Transformer for image processing. IEEE Trans. Multim. 25(1), 50\u201361 (2023). https:\/\/doi.org\/10.1109\/TMM.2021.3120873","journal-title":"IEEE Trans. Multim."},{"key":"3416_CR32","doi-asserted-by":"publisher","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: IEEE Int. Conf. Comput. Vis., pp. 10012\u201310022 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3416_CR33","doi-asserted-by":"publisher","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Eur. Conf. Comput. Vis., pp. 418\u2013434 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"3416_CR34","doi-asserted-by":"publisher","unstructured":"Gao, X., Sun, X., Yan, M., Sun, H., Fu, K., Zhang, Y., Ge, Z.: Road extraction from remote sensing images by multiple feature pyramid network. In: IEEE Int. Geosci. Remote Sens. Symp., pp. 6907\u20136910 (2018). https:\/\/doi.org\/10.1109\/IGARSS.2018.8519093","DOI":"10.1109\/IGARSS.2018.8519093"},{"key":"3416_CR35","doi-asserted-by":"publisher","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: IEEE Conf. Comput. Vis. Pattern Recognit., pp. 6230\u20136239 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.660","DOI":"10.1109\/CVPR.2017.660"},{"key":"3416_CR36","doi-asserted-by":"publisher","unstructured":"Dong, X., Bao, J., Chen, D., Zhang, W., Yu, N., Yuan, L., Chen, D., Guo, B.: CSwin Transformer: A general vision Transformer backbone with cross-shaped windows. In: IEEE Conf. Comput. Vis. Pattern Recognit., pp. 12114\u201312124 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01181","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"3416_CR37","doi-asserted-by":"publisher","unstructured":"Demir, I., Koperski, K., Lindenbaum, D., Pang, G., Huang, J., Basu, S., Hughes, F., Tuia, D., Raskar, R.: DeepGlobe 2018: A challenge to parse the earth through satellite images. In: IEEE Conf. Comput. Vis. Pattern Recognit. Workshop, pp. 172\u2013181 (2018). https:\/\/doi.org\/10.1109\/CVPRW.2018.00031","DOI":"10.1109\/CVPRW.2018.00031"},{"key":"3416_CR38","doi-asserted-by":"publisher","unstructured":"Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. In: Eur. Conf. Comput. Vis., pp. 173\u2013190 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_11","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"3416_CR39","doi-asserted-by":"publisher","unstructured":"Chen, L., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-Decoder with atrous separable convolution for semantic image segmentation. In: Eur. Conf. Comput. Vis., pp. 801\u2013818 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"3416_CR40","doi-asserted-by":"publisher","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: CCNet: Criss-cross attention for semantic segmentation. In: IEEE Int. Conf. Comput. Vis., pp. 603\u2013612 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00069","DOI":"10.1109\/ICCV.2019.00069"},{"issue":"3","key":"3416_CR41","doi-asserted-by":"publisher","first-page":"3448","DOI":"10.1109\/TITS.2022.3228042","volume":"24","author":"H Pan","year":"2023","unstructured":"Pan, H., Hong, Y., Sun, W., Jia, Y.: Deep dual-resolution networks for real-time and accurate semantic segmentation of traffic scenes. IEEE Trans. Intell. Transp. Syst. 24(3), 3448\u20133460 (2023). https:\/\/doi.org\/10.1109\/TITS.2022.3228042","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3416_CR42","doi-asserted-by":"publisher","unstructured":"Xu, J., Xiong, Z., Bhattacharyya, S. P.: PIDNet: A real-time semantic segmentation network inspired by PID controllers. In: IEEE Conf. Comput. Vis. Pattern Recognit., pp. 19529\u201319539 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01871","DOI":"10.1109\/CVPR52729.2023.01871"},{"key":"3416_CR43","doi-asserted-by":"publisher","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pyramid vision Transformer: A versatile backbone for dense prediction without convolutions. In: Eur. Conf. Comput. Vis., pp. 548\u2013558 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00061","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"3416_CR44","doi-asserted-by":"publisher","unstructured":"Yu, Q., Xia, Y., Bai, Y., Lu, Y., Yuille, A. L., Shen, W.: Glance-and-gaze vision Transformer. In: Adv. Neural Inf. Process. Syst., pp. 12990\u201313003 (2021). https:\/\/doi.org\/10.48550\/arXiv.2106.02277","DOI":"10.48550\/arXiv.2106.02277"},{"key":"3416_CR45","doi-asserted-by":"publisher","unstructured":"Hassani, A., Walton, S., Li, J., Li, S., Shi, H.: Neighborhood attention Transformer. In: IEEE Conf. Comput. Vis. Pattern Recognit., pp. 6185\u20136194 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00599","DOI":"10.1109\/CVPR52729.2023.00599"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03416-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03416-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03416-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,3]],"date-time":"2025-02-03T12:37:09Z","timestamp":1738586229000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03416-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,18]]},"references-count":45,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["3416"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03416-0","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,18]]},"assertion":[{"value":"9 April 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2024","order":2,"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 that there are no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}