{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:41:58Z","timestamp":1783100518428,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819720910","type":"print"},{"value":"9789819720927","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-2092-7_17","type":"book-chapter","created":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T06:02:18Z","timestamp":1711692138000},"page":"332-353","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["AST: An Attention-Guided Segment Transformer for\u00a0Drone-Based Cross-View Geo-Localization"],"prefix":"10.1007","author":[{"given":"Zichuan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelei","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiguang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,30]]},"reference":[{"key":"17_CR1","first-page":"20014","volume":"34","author":"A Ali","year":"2021","unstructured":"Ali, A., et al.: XCIT: cross-covariance image transformers. Adv. Neural Inf. Process. Syst. 34, 20014\u201320027 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"17_CR2","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"17_CR3","first-page":"275","volume":"9","author":"DV Bui","year":"2022","unstructured":"Bui, D.V., Kubo, M., Sato, H.: A part-aware attention neural network for cross-view geo-localization between UAV and satellite. J. Rob. Network. Artif. Life 9(3), 275\u2013284 (2022)","journal-title":"J. Rob. Network. Artif. Life"},{"key":"17_CR4","unstructured":"Cao, H., et al.: Swin-unet: Unet-like pure transformer for medical image segmentation. arXiv:2105.05537 (2021)"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., Fan, Q., Panda, R.: Crossvit: cross-attention multi-scale vision transformer for image classification. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: IEEE Computer Society Conference on Computer Vision Pattern Recognition, vol.\u00a01, pp. 539\u2013546. IEEE (2005)","DOI":"10.1109\/CVPR.2005.202"},{"key":"17_CR7","first-page":"9355","volume":"34","author":"X Chu","year":"2021","unstructured":"Chu, X., et al.: Twins: revisiting the design of spatial attention in vision transformers. Adv. Neural Inf. Process. Syst. 34, 9355\u20139366 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"7","key":"17_CR8","doi-asserted-by":"publisher","first-page":"4376","DOI":"10.1109\/TCSVT.2021.3135013","volume":"32","author":"M Dai","year":"2021","unstructured":"Dai, M., Hu, J., Zhuang, J., Zheng, E.: A transformer-based feature segmentation and region alignment method for UAV-view geo-localization. IEEE Trans. Circ. Syst. Video Technol. 32(7), 4376\u20134389 (2021)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"17_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2018)"},{"issue":"1","key":"17_CR10","doi-asserted-by":"publisher","first-page":"47","DOI":"10.3390\/rs13010047","volume":"13","author":"L Ding","year":"2020","unstructured":"Ding, L., Zhou, J., Meng, L., Long, Z.: A practical cross-view image matching method between UAV and satellite for UAV-based geo-localization. Remote Sens. 13(1), 47 (2020)","journal-title":"Remote Sens."},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. In: Proceedings of IEEE\/CVF Conference on Computer Vision Pattern Recognition, pp. 12124\u201312134 (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"17_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv:2010.11929 (2020)"},{"key":"17_CR13","first-page":"15908","volume":"34","author":"K Han","year":"2021","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. Adv. Neural Inf. Process. Syst. 34, 15908\u201315919 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, pp. 11936\u201311945 (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Hu, S., Feng, M., Nguyen, R.M., Lee, G.H.: Cvm-net: cross-view matching network for image-based ground-to-aerial geo-localization. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition, pp. 7258\u20137267 (2018)","DOI":"10.1109\/CVPR.2018.00758"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"17_CR19","doi-asserted-by":"publisher","first-page":"3780","DOI":"10.1109\/TIP.2022.3175601","volume":"31","author":"J Lin","year":"2022","unstructured":"Lin, J., et al.: Joint representation learning and keypoint detection for cross-view geo-localization. IEEE Trans. Image Process. 31, 3780\u20133792 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Cui, Y., Belongie, S., Hays, J.: Learning deep representations for ground-to-aerial geolocalization. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition, pp. 5007\u20135015 (2015)","DOI":"10.1109\/CVPR.2015.7299135"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, H.: Lending orientation to neural networks for cross-view geo-localization. In: Proceedings of IEEE\/CVF Conference on Computer Vision Pattern Recognition, pp. 5624\u20135633 (2019)","DOI":"10.1109\/CVPR.2019.00577"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of IEEE\/CVF Conference on Computer Vision Pattern Recognition, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Lu, Z., Pu, T., Chen, T., Lin, L.: Content-aware hierarchical representation selection for cross-view geo-localization. In: Proceedings of Asian Conference on Computer Vision, pp. 4211\u20134224 (2022)","DOI":"10.1007\/978-3-031-26348-4_16"},{"key":"17_CR24","unstructured":"Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Pan, Z., Zhuang, B., Liu, J., He, H., Cai, J.: Scalable vision transformers with hierarchical pooling. In: Proceedings of IEEE\/CVF Conference on Computer Vision Pattern Recognition, pp. 377\u2013386 (2021)","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"17_CR26","unstructured":"Paszke, A., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"issue":"7","key":"17_CR27","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1109\/TPAMI.2018.2846566","volume":"41","author":"F Radenovi\u0107","year":"2018","unstructured":"Radenovi\u0107, F., Tolias, G., Chum, O.: Fine-tuning CNN image retrieval with no human annotation. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1655\u20131668 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR28","unstructured":"Shi, Y., Liu, L., Yu, X., Li, H.: Spatial-aware feature aggregation for image based cross-view geo-localization. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"issue":"7","key":"17_CR29","doi-asserted-by":"publisher","first-page":"4804","DOI":"10.1109\/TCSVT.2021.3121987","volume":"32","author":"X Tian","year":"2021","unstructured":"Tian, X., Shao, J., Ouyang, D., Shen, H.T.: UAV-satellite view synthesis for cross-view geo-localization. IEEE Trans. Circuits Syst. Video Technol. 32(7), 4804\u20134815 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Toker, A., Zhou, Q., Maximov, M., Leal-Taix\u00e9, L.: Coming down to earth: satellite-to-street view synthesis for geo-localization. In: Proceedings of IEEE\/CVF Conference on Computer Vision Pattern Recognition, pp. 6488\u20136497 (2021)","DOI":"10.1109\/CVPR46437.2021.00642"},{"key":"17_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"17_CR32","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/978-3-031-20053-3_17","volume-title":"ECCV 2022","author":"P Wang","year":"2022","unstructured":"Wang, P., et al.: KVT: k-nn attention for boosting vision transformers. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, vol. 13684, pp. 285\u2013302. Springer, Heidleberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_17"},{"issue":"2","key":"17_CR33","doi-asserted-by":"publisher","first-page":"867","DOI":"10.1109\/TCSVT.2021.3061265","volume":"32","author":"T Wang","year":"2021","unstructured":"Wang, T., et al.: Each part matters: local patterns facilitate cross-view geo-localization. IEEE Trans. Circuits Syst. Video Technol. 32(2), 867\u2013879 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Z., Cun, X., Bao, J., Zhou, W., Liu, J., Li, H.: Uformer: a general u-shaped transformer for image restoration. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, pp. 17683\u201317693 (2022)","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"17_CR36","first-page":"29009","volume":"34","author":"H Yang","year":"2021","unstructured":"Yang, H., Lu, X., Zhu, Y.: Cross-view geo-localization with layer-to-layer transformer. Adv. Neural Inf. Process. Syst. 34, 29009\u201329020 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Zhai, M., Bessinger, Z., Workman, S., Jacobs, N.: Predicting ground-level scene layout from aerial imagery. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition, pp. 867\u2013875 (2017)","DOI":"10.1109\/CVPR.2017.440"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wei, Y., Yang, Y.: University-1652: a multi-view multi-source benchmark for drone-based geo-localization. In: Proceedings of 28th ACM International Conference on Multimedia, pp. 1395\u20131403 (2020)","DOI":"10.1145\/3394171.3413896"},{"key":"17_CR39","unstructured":"Zhou, D., et al.: Deepvit: towards deeper vision transformer. arXiv:2103.11886 (2021)"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Zhu, S., Shah, M., Chen, C.: Transgeo: transformer is all you need for cross-view image geo-localization. In: Proceedings of IEEE\/CVF Conference on Computer Vision Pattern Recognition, pp. 1162\u20131171 (2022)","DOI":"10.1109\/CVPR52688.2022.00123"}],"container-title":["Lecture Notes in Computer Science","Computational Visual Media"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2092-7_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T07:06:08Z","timestamp":1731654368000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2092-7_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819720910","9789819720927"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2092-7_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"30 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Visual Media","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"10 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 April 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CVM submission system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"212","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"34","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"16% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}