{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:03:35Z","timestamp":1764403415882,"version":"3.40.4"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819784929"},{"type":"electronic","value":"9789819784936"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-981-97-8493-6_27","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T20:02:50Z","timestamp":1730404970000},"page":"386-400","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["HANet: Hierarchical Attention Network for Remote Sensing Images Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4605-8577","authenticated-orcid":false,"given":"Hongming","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9023-3306","authenticated-orcid":false,"given":"Guang","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5871-4236","authenticated-orcid":false,"given":"Zhengjie","family":"Gao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7960-3264","authenticated-orcid":false,"given":"Yinwei","family":"Shen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6202-7595","authenticated-orcid":false,"given":"Hengao","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5277-8985","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5659-6611","authenticated-orcid":false,"given":"Yamin","family":"Han","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Cao et al.: Deep learning-based remote and social sensing data fusion for urban region function recognition. ISPRS J. Photogramm. Remote. Sens. 163, 82\u201397 (2020)","DOI":"10.1016\/j.isprsjprs.2020.02.014"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Che, R., Ma, X., Hong, T., Wang, X., Feng, T. and Zhang, W.: DBDAN: dual-branch dynamic attention network for semantic segmentation of remote sensing images. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 306\u2013317 (2023)","DOI":"10.1007\/978-981-99-8462-6_25"},{"key":"27_CR3","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"27_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. In: European Conference on Computer Vision (ECCV), pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"27_CR5","unstructured":"Dosovitskiy, A., et al.: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"27_CR6","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":"27_CR7","doi-asserted-by":"crossref","unstructured":"Kampffmeyer, M., Salberg, A.B. and Jenssen, R.: Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks. In: CVPR, pp. 1\u20139 (2016)","DOI":"10.1109\/CVPRW.2016.90"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., Hou, Q., Zheng, Z., Cheng, M.M., Yang, J. and Li, X.: Large selective kernel network for remote sensing object detection. In: ICCV, pp. 16794\u201316805 (2023)","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"27_CR9","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":"27_CR10","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":"27_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S. and Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., Prabhat, F.: Deep learning and process understanding for data-driven Earth system science. Nature 566(7743), 195\u2013204 (2019)","DOI":"10.1038\/s41586-019-0912-1"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Sahar, L., Muthukumar, S., French, S.P.: Using aerial imagery and GIS in automated building footprint extraction and shape recognition for earthquake risk assessment of urban inventories. IEEE Trans. Geosci. Remote. Sens. 48, 3511\u20133520 (2010)","DOI":"10.1109\/TGRS.2010.2047260"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Tong, X.Y., Xia, G.S., Lu, Q., Shen, H., Li, S., You, S., Zhang, L.: Land-cover classification with high-resolution remote sensing images using transferable deep models. Remote. Sens. Environ. pp.237 (2020)","DOI":"10.1016\/j.rse.2019.111322"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, R., Duan, C., Zhang, C., Meng, X., Fang, S.: A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images. IEEE Geosci. Remote. Sens. Lett. 1\u20135 (2021)","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"27_CR18","doi-asserted-by":"crossref","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)","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Wang et al.: MCAT-UNet: convolutional and cross-shaped window attention enhanced UNet for efficient high-resolution remote sensing image segmentation. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. 17, 9745\u20139758 (2024)","DOI":"10.1109\/JSTARS.2024.3397488"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Weiss, M., Jacob, F., Duveiller, G.: Remote sensing for agricultural applications: a meta-review. Remote. Sens. Environ. 236, 111402 (2020)","DOI":"10.1016\/j.rse.2019.111402"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 418\u2013434 (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Yin, J., et al.: Is-fusion: Instance-scene collaborative fusion for multimodal 3d object detection. In: Conference on Computer Vision and Pattern Recognition, pp. 14905\u201314915 (2024)","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Yin, J., Shen, J., Gao, X., Crandall, D.J. and Yang, R.: Graph neural network and spatiotemporal transformer attention for 3D video object detection from point clouds. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 9822\u20139835 (2023)","DOI":"10.1109\/TPAMI.2021.3125981"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Yuan, Q., et al.: Deep learning in environmental remote sensing: achievements and challenges. Remote. Sens. Environ. 241, 111716 (2020)","DOI":"10.1016\/j.rse.2020.111716"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., Agrawal, A.: Context encoding for semantic segmentation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, C., Jiang, W., Zhang, Y., Wang, W., Zhao, Q., Wang, C.: 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)","DOI":"10.1109\/TGRS.2022.3144894"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, C., Pan, X., Li, H., Gardiner, A., Sargent, I., Hare, J., Atkinson, P.M.: A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. ISPRS J. Photogramm. Remote. Sens. 140, 133\u2013144 (2018)","DOI":"10.1016\/j.isprsjprs.2017.07.014"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X. and Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2881\u20132890 (2016)","DOI":"10.1109\/CVPR.2017.660"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Rahman Siddiquee, 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, pp. 3\u201311(2018)","DOI":"10.1007\/978-3-030-00889-5_1"}],"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\/978-981-97-8493-6_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T19:09:56Z","timestamp":1744312196000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8493-6_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819784929","9789819784936"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8493-6_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}