{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T11:09:01Z","timestamp":1781780941865,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819620531","type":"print"},{"value":"9789819620548","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-2054-8_17","type":"book-chapter","created":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T15:45:21Z","timestamp":1735832721000},"page":"220-233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Cross-View Geo-Localization via\u00a0Learning Correspondence Semantic Similarity Knowledge"],"prefix":"10.1007","author":[{"given":"Guanli","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoheng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaochen","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guo","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi-Man","family":"Pun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"17_CR2","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arxiv (2020)"},{"key":"17_CR3","first-page":"1","volume":"62","author":"F Ge","year":"2024","unstructured":"Ge, F., et al.: Multibranch joint representation learning based on information fusion strategy for cross-view geo-localization. IEEE Trans. Geosci. Remote Sens. 62, 1\u201316 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Guo, X., Chen, X., Luo, S., Wang, S., Pun, C.M.: Dual-hybrid attention network for specular highlight removal. In: ACM MM (2024)","DOI":"10.1145\/3664647.3680745"},{"key":"17_CR5","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv (2015)"},{"key":"17_CR6","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: CVPR, pp. 7258\u20137267 (2018)","DOI":"10.1109\/CVPR.2018.00758"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Chen, X., Pun, C.M., Wang, S., Feng, W.: Mfdnet: multi-frequency deflare network for efficient nighttime flare removal. Vis. Comput. 1\u201314 (2024)","DOI":"10.1007\/s00371-024-03540-x"},{"key":"17_CR8","first-page":"1","volume":"62","author":"J Li","year":"2024","unstructured":"Li, J., Yang, C., Qi, B., Zhu, M., Wu, N.: 4SCIG: a four-branch framework to reduce the interference of sky area in cross-view image geo-localization. IEEE Trans. Geosci. Remote Sens. 62, 1\u201318 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Cross-domain visual prompting with spatial proximity knowledge distillation for histological image classification. J. Biomed. Inform. 104728 (2024)","DOI":"10.1016\/j.jbi.2024.104728"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, H.: Lending orientation to neural networks for cross-view geo-localization. In: CVPR, pp. 5624\u20135633 (2019)","DOI":"10.1109\/CVPR.2019.00577"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Weakly supervised semantic segmentation via saliency perception with uncertainty-guided noise suppression. Vis. Comput. 1\u201316 (2024)","DOI":"10.1007\/s00371-024-03574-1"},{"issue":"1","key":"17_CR12","doi-asserted-by":"publisher","first-page":"231","DOI":"10.3390\/rs15010231","volume":"15","author":"L Qiu","year":"2022","unstructured":"Qiu, L., Yu, D., Zhang, C., Zhang, X.: A local-global framework for semantic segmentation of multisource remote sensing images. Remote Sens. 15(1), 231 (2022)","journal-title":"Remote Sens."},{"key":"17_CR13","first-page":"1","volume":"20","author":"L Qiu","year":"2023","unstructured":"Qiu, L., Yu, D., Zhang, C., Zhang, X.: A semantics-geometry framework for road extraction from remote sensing images. IEEE Geosci. Remote Sens. Lett. 20, 1\u20135 (2023)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Qiu, L., Yu, D., Zhang, X., Zhang, C.: Efficient remote sensing segmentation with generative adversarial transformer. IEEE Geosci. Remote Sens. Lett. (2023)","DOI":"10.1109\/LGRS.2023.3339636"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Ren, S., Wei, F., Zhang, Z., Hu, H.: Tinymim: an empirical study of distilling mim pre-trained models. In: CVPR, pp. 3687\u20133697 (2023)","DOI":"10.1109\/CVPR52729.2023.00359"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"17_CR17","unstructured":"Shi, Y., Liu, L., Yu, X., Li, H.: Spatial-aware feature aggregation for image based cross-view geo-localization. In: NeurIPS, vol. 32 (2019)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Shi, Y., Yu, X., Campbell, D., Li, H.: Where am i looking at? Joint location and orientation estimation by cross-view matching. In: CVPR, pp. 4064\u20134072 (2020)","DOI":"10.1109\/CVPR42600.2020.00412"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Shi, Y., Yu, X., Liu, L., Zhang, T., Li, H.: Optimal feature transport for cross-view image geo-localization. In: AAAI, vol.\u00a034, pp. 11990\u201311997 (2020)","DOI":"10.1609\/aaai.v34i07.6875"},{"key":"17_CR20","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML, pp. 10347\u201310357 (2021)"},{"issue":"3","key":"17_CR21","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.1109\/TCSVT.2023.3293514","volume":"34","author":"T Wang","year":"2024","unstructured":"Wang, T., Li, J., Sun, C.: Dehi: a decoupled hierarchical architecture for unaligned ground-to-aerial geo-localization. IEEE Trans. Circuits Syst. Video Technol. 34(3), 1927\u20131940 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Wei, X., Zhang, T., Li, Y., Zhang, Y., Wu, F.: Multi-modality cross attention network for image and sentence matching. In: CVPR, pp. 10941\u201310950 (2020)","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhang, X., Chen, W., Liu, J., Xu, T., Wang, Z.: Muraldiff: diffusion for ancient murals restoration on large-scale pre-training. IEEE Trans. Emerg. Top. Comput. Intell. (2024)","DOI":"10.1109\/TETCI.2024.3359038"},{"issue":"20","key":"17_CR24","doi-asserted-by":"publisher","first-page":"11189","DOI":"10.3390\/app132011189","volume":"13","author":"Z Xu","year":"2023","unstructured":"Xu, Z., et al.: A review of image inpainting methods based on deep learning. Appl. Sci. 13(20), 11189 (2023)","journal-title":"Appl. Sci."},{"key":"17_CR25","unstructured":"Yang, H., Lu, X., Zhu, Y.: Cross-view geo-localization with layer-to-layer transformer. In: NeurIPS, vol. 34, pp. 29009\u201329020 (2021)"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Zhai, M., Bessinger, Z., Workman, S., Jacobs, N.: Predicting ground-level scene layout from aerial imagery. In: CVPR, pp. 867\u2013875 (2017)","DOI":"10.1109\/CVPR.2017.440"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H., Mao, Z., Zhang, K., Zhang, Y.: Show your faith: cross-modal confidence-aware network for image-text matching. In: AAAI, vol.\u00a036, pp. 3262\u20133270 (2022)","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"17_CR28","unstructured":"Zhang, X.F., Gu, C.C., Zhu, S.Y.: Memory augment is all you need for image restoration. arXiv (2023)"},{"key":"17_CR29","doi-asserted-by":"publisher","first-page":"1590","DOI":"10.1109\/LSP.2020.3019705","volume":"27","author":"X Zhang","year":"2020","unstructured":"Zhang, X., Chen, F., Wang, C., Tao, M., Jiang, G.P.: Sienet: siamese expansion network for image extrapolation. IEEE Signal Process. Lett. 27, 1590\u20131594 (2020)","journal-title":"IEEE Signal Process. Lett."},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, X., Xu, Z., Tang, H., Gu, C., Zhu, S., Guan, X.: Shadclips: when parameter-efficient fine-tuning with multimodal meets shadow removal (2024)","DOI":"10.21203\/rs.3.rs-4194150\/v1"},{"key":"17_CR31","unstructured":"Zhang, X., Zhao, Q., Tang, H., Gu, C., Zhu, S.: Enlighten-anything: when segment anything model meets low-light image enhancement. arXiv (2023)"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhao, Y., Gu, C., Lu, C., Zhu, S.: Spa-former: an effective and lightweight transformer for image shadow removal. In: IJCNN, pp.\u00a01\u20138 (2023)","DOI":"10.1109\/IJCNN54540.2023.10191081"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, X., Sultani, W., Zhou, Y., Wshah, S.: Cross-view geo-localization via learning disentangled geometric layout correspondence. In: AAAI, vol.\u00a037, pp. 3480\u20133488 (2023)","DOI":"10.1609\/aaai.v37i3.25457"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Zheng, F., et al.: Smaformer: synergistic multi-attention transformer for medical image segmentation. arXiv (2024)","DOI":"10.1109\/BIBM62325.2024.10822736"},{"key":"17_CR35","unstructured":"Zhu, L., et al.: Test-time intensity consistency adaptation for shadow detection. arXiv (2024)"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, S., Shah, M., Chen, C.: Transgeo: transformer is all you need for cross-view image geo-localization. In: CVPR, pp. 1162\u20131171 (2022)","DOI":"10.1109\/CVPR52688.2022.00123"},{"key":"17_CR37","unstructured":"Zhu, Y., Yang, H., Lu, Y., Huang, Q.: Simple, effective and general: a new backbone for cross-view image geo-localization. arXiv (2023)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2054-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T01:43:52Z","timestamp":1742694232000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2054-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620531","9789819620548"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2054-8_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"3 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}