{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:04:35Z","timestamp":1755993875160,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Portuguese Recovery and Resilience Plan","award":["C645008882-00000055"],"award-info":[{"award-number":["C645008882-00000055"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia - FCT","award":["UIDB\/50021\/2020"],"award-info":[{"award-number":["UIDB\/50021\/2020"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,13]]},"DOI":"10.1145\/3615886.3627751","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T06:21:13Z","timestamp":1700461273000},"page":"20-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Detailed Analysis on the Use of General-purpose Vision Transformers for Remote Sensing Image Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4239-1915","authenticated-orcid":false,"given":"Miguel","family":"Gon\u00e7alves","sequence":"first","affiliation":[{"name":"Instituto Superior T\u00e9cnico and INESC-ID, University of Lisbon, Lisbon, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3856-2936","authenticated-orcid":false,"given":"Bruno","family":"Martins","sequence":"additional","affiliation":[{"name":"Instituto Superior T\u00e9cnico and INESC-ID, University of Lisbon, Lisbon, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8837-4637","authenticated-orcid":false,"given":"Jacinto","family":"Estima","sequence":"additional","affiliation":[{"name":"Department of Informatics and CISUC, University of Coimbra, Coimbra, Portugal"}]}],"member":"320","published-online":{"date-parts":[[2023,11,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2019.8759329"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3168697"},{"key":"e_1_3_2_1_3_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929 (2020)."},{"volume-title":"Proceedings of the IEEE International Conference on Computer Vision.","author":"Grauman K.","key":"e_1_3_2_1_4_1","unstructured":"K. Grauman and T. Darrell. 2005. The pyramid match kernel: discriminative classification with sets of image features. In Proceedings of the IEEE International Conference on Computer Vision."},{"key":"e_1_3_2_1_5_1","volume-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. CoRR abs\/1406.4729","author":"He Kaiming","year":"2014","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2014. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. CoRR abs\/1406.4729 (2014)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3230846"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3188257"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIBCB48159.2020.9277638"},{"key":"e_1_3_2_1_9_1","volume-title":"RemoteNet: Remote Sensing Image Segmentation Network based on Global-Local Information. CoRR abs\/2302.13084","author":"Kumar Satyawant","year":"2023","unstructured":"Satyawant Kumar, Abhishek Kumar, and Dong-Gyu Lee. 2023. RemoteNet: Remote Sensing Image Segmentation Network based on Global-Local Information. CoRR abs\/2302.13084 (2023)."},{"volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.","author":"Lazebnik S.","key":"e_1_3_2_1_10_1","unstructured":"S. Lazebnik, C. Schmid, and J. Ponce. 2006. Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_11_1","first-page":"1","article-title":"Multistage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images","volume":"19","author":"Li Rui","year":"2022","unstructured":"Rui Li, Shunyi Zheng, Chenxi Duan, Jianlin Su, and Ce Zhang. 2022. Multistage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images. IEEE Geoscience and Remote Sensing Letters 19 (2022), 1--5.","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"e_1_3_2_1_12_1","volume-title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. CoRR abs\/2103.14030","author":"Liu Ze","year":"2021","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. CoRR abs\/2103.14030 (2021)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi11030165"},{"key":"e_1_3_2_1_14_1","volume-title":"CoRR abs\/1706.03762","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. CoRR abs\/1706.03762 (2017)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301377"},{"key":"e_1_3_2_1_16_1","first-page":"1","article-title":"A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images","volume":"19","author":"Wang Libo","year":"2022","unstructured":"Libo Wang, Rui Li, Chenxi Duan, Ce Zhang, Xiaoliang Meng, and Shenghui Fang. 2022. A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images. IEEE Geoscience and Remote Sensing Letters 19 (2022), 1--5.","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"e_1_3_2_1_18_1","volume-title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions. CoRR abs\/2102.12122","author":"Xie Enze","year":"2021","unstructured":"WenhaiWang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. 2021. Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions. CoRR abs\/2102.12122 (2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. CoRR abs\/2105.15203","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, and Ping Luo. 2021. SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. CoRR abs\/2105.15203 (2021)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3189825"},{"key":"e_1_3_2_1_21_1","volume-title":"Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attention. CoRR abs\/2201.01615","author":"Yan Haotian","year":"2022","unstructured":"Haotian Yan, Chuang Zhang, and MingWu. 2022. Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attention. CoRR abs\/2201.01615 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"FDA: Fourier Domain Adaptation for Semantic Segmentation. CoRR abs\/2004.05498","author":"Yang Yanchao","year":"2020","unstructured":"Yanchao Yang and Stefano Soatto. 2020. FDA: Fourier Domain Adaptation for Semantic Segmentation. CoRR abs\/2004.05498 (2020)."},{"key":"e_1_3_2_1_23_1","volume-title":"Malof","author":"Yaris Can","year":"2021","unstructured":"Can Yaris, Bohao Huang, Kyle Bradbury, and Jordan M. Malof. 2021. Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery. CoRR abs\/2104.14032 (2021)."}],"event":{"name":"SIGSPATIAL '23: The 31st ACM International Conference on Advances in Geographic Information Systems","sponsor":["SIGSPATIAL ACM Special Interest Group on Spatial Information"],"location":"Hamburg Germany","acronym":"SIGSPATIAL '23"},"container-title":["Proceedings of the 6th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3615886.3627751","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3615886.3627751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T02:26:24Z","timestamp":1755915984000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3615886.3627751"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,13]]},"references-count":23,"alternative-id":["10.1145\/3615886.3627751","10.1145\/3615886"],"URL":"https:\/\/doi.org\/10.1145\/3615886.3627751","relation":{},"subject":[],"published":{"date-parts":[[2023,11,13]]},"assertion":[{"value":"2023-11-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}