{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:35:37Z","timestamp":1767339337522,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785049"},{"type":"electronic","value":"9789819785056"}],"license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-8505-6_5","type":"book-chapter","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:04:13Z","timestamp":1730930653000},"page":"62-75","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Dual-Stream Network of\u00a0Vision Mamba and\u00a0CNN with\u00a0Auto-Scaling for\u00a0Remote Sensing Image Segmentation"],"prefix":"10.1007","author":[{"given":"Shitao","family":"Song","sequence":"first","affiliation":[]},{"given":"Ye","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jintao","family":"Su","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Aleissaee, A.A., Kumar, A., Anwer, R.M., Khan, S., Cholakkal, H., Xia, G.S., khan, F.S.: Transformers in remote sensing: a survey (2022)","DOI":"10.3390\/rs15071860"},{"key":"5_CR2","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: Proceedings of the European Conference on Computer Vision Workshops (ECCVW) (2022)","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"5_CR3","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":"5_CR4","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 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Chen, W., Jiang, Z., Wang, Z., Cui, K., Qian, X.: 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)","DOI":"10.1109\/CVPR.2019.00913"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Chung, J., Tai, Y.W., Tang, C.K.: Cascadepsp: toward class-agnostic and very high-resolution segmentation via global and local refinement (2020)","DOI":"10.1109\/CVPR42600.2020.00891"},{"key":"5_CR7","unstructured":"Contributors, M.: MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmsegmentation (2020)"},{"key":"5_CR8","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 x 16 words: transformers for image recognition at scale. ICLR (2021)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Fan, M., Lai, S., Huang, J., Wei, X., Chai, Z., Luo, J., Wei, X.: Rethinking bisenet for real-time semantic segmentation (2021)","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"5_CR10","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 Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"5_CR11","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"5_CR12","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. In: The International Conference on Learning Representations (ICLR) (2022)"},{"key":"5_CR13","unstructured":"Guo, M.H., Lu, C.Z., Hou, Q., Liu, Z., Cheng, M.M., Hu, S.M.: Segnext: rethinking convolutional attention design for semantic segmentation (2022)"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Guo, S., Liu, L., Gan, Z., Wang, Y., Zhang, W., Wang, C., Jiang, G., Zhang, W., Yi, R., Ma, L., et\u00a0al.: Isdnet: integrating shallow and deep networks for efficient ultra-high resolution segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4361\u20134370 (2022)","DOI":"10.1109\/CVPR52688.2022.00432"},{"key":"5_CR15","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR16","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. Geosci. Remote Sens. 60, 1\u201315 (2022). https:\/\/doi.org\/10.1109\/TGRS.2022.3144165","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"5_CR19","doi-asserted-by":"publisher","unstructured":"Jeong, J., Cho, A., Yoon, J., Nam, M., Kim, G., Kim, D., Kim, S.: Mission status of a geostationary environmental monitoring spectrometer: the development of a ground station system. In: IGARSS 2019\u20142019 IEEE International Geoscience and Remote Sensing Symposium, pp. 9052\u20139054 (2019).https:\/\/doi.org\/10.1109\/IGARSS.2019.8898424","DOI":"10.1109\/IGARSS.2019.8898424"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Ji, D., Zhao, F., Lu, H., Tao, M., Ye, J.: Ultra-high resolution segmentation with ultra-rich context: A novel benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23621\u201323630 (2023)","DOI":"10.1109\/CVPR52729.2023.02262"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Li, Q., Yang, W., Liu, W., Yu, Y., He, S.: From contexts to locality: Ultra-high resolution image segmentation via locality-aware contextual correlation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7252\u20137261 (2021)","DOI":"10.1109\/ICCV48922.2021.00716"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Liu, J., Yang, H., Zhou, H.Y., Xi, Y., Yu, L., Yu, Y., Liang, Y., Shi, G., Zhang, S., Zheng, H., Wang, S.: Swin-umamba: Mamba-based unet with imagenet-based pretraining. arXiv preprint arXiv:2402.03302 (2024)","DOI":"10.1007\/978-3-031-72114-4_59"},{"key":"5_CR23","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Liu, Y.: Vmamba: visual state space model. arXiv preprint arXiv:2401.10166 (2024)"},{"key":"5_CR24","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 (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"5_CR26","unstructured":"Ma, J., Li, F., Wang, B.: U-mamba: Enhancing long-range dependency for biomedical image segmentation. arXiv preprint arXiv:2401.04722 (2024)"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Maggiori, E., Tarabalka, Y., Charpiat, G., Alliez, P.: Can semantic labeling methods generalize to any city? the inria aerial image labeling benchmark. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS). IEEE (2017)","DOI":"10.1109\/IGARSS.2017.8127684"},{"key":"5_CR28","doi-asserted-by":"publisher","unstructured":"Qian, L., Chen, S., Jiang, H., Dai, X., Jia, K.: Quantitative monitoring of sugarcane typhoon disaster based on multi-source remote sensing data. In: 2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS), pp. 926\u2013930 (2022https:\/\/doi.org\/10.1109\/ICGMRS55602.2022.9849279","DOI":"10.1109\/ICGMRS55602.2022.9849279"},{"key":"5_CR29","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation (2015), http:\/\/arxiv.org\/abs\/1505.04597, cite arxiv:1505.04597Comment: conditionally accepted at MICCAI 2015"},{"key":"5_CR30","doi-asserted-by":"publisher","unstructured":"Ruan, J., Xiang, S.: VM-UNet: Vision Mamba UNet for Medical Image Segmentation. arXiv e-prints arXiv:2402.02491 (2024).https:\/\/doi.org\/10.48550\/arXiv.2402.02491","DOI":"10.48550\/arXiv.2402.02491"},{"key":"5_CR31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L.u., Polosukhin, I.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol.\u00a030. Curran Associates, Inc. (2017)"},{"key":"5_CR32","doi-asserted-by":"publisher","unstructured":"Wang, D., Zhang, J., Du, B., Xia, G.S., Tao, D.: An empirical study of remote sensing pretraining. IEEE Trans. Geoscience Remote Sensing 61, 1\u201320 (2023), https:\/\/doi.org\/10.1109\/TGRS.2022.3176603","DOI":"10.1109\/TGRS.2022.3176603"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Z., et\u00a0al.: Mamba-unet: Unet-like pure visual mamba for medical image segmentation. arXiv preprint arXiv:2402.05079 (2024)","DOI":"10.1007\/978-3-031-72111-3_34"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"5_CR35","doi-asserted-by":"publisher","unstructured":"Xian, W.: Construction of urban planning model based on remote sensing image data processing algorithm. In: 2023 2nd International Conference on 3D Immersion, Interaction and Multi-sensory Experiences (ICDIIME), pp. 367\u2013371 (2023). https:\/\/doi.org\/10.1109\/ICDIIME59043.2023.00077","DOI":"10.1109\/ICDIIME59043.2023.00077"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: European Conference on Computer Vision. Springer (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"5_CR37","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: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems. vol.\u00a034, pp. 12077\u201312090. Curran Associates, Inc. (2021)"},{"key":"5_CR38","unstructured":"Yue, Y., Li, Z.: Medmamba: Vision mamba for medical image classification. arXiv preprint arXiv:2403.03849 (2024)"},{"key":"5_CR39","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 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8505-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:04:30Z","timestamp":1730930670000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8505-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"ISBN":["9789819785049","9789819785056"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8505-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,7]]},"assertion":[{"value":"7 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}