{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T21:02:49Z","timestamp":1780606969466,"version":"3.54.1"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.jvcir.2026.104820","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T23:07:08Z","timestamp":1776899228000},"page":"104820","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Dual-stream frequency-domain framework with contextual graph enhancer and consensus-difference fusion for cross-view geo-localization"],"prefix":"10.1016","volume":"118","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8640-2222","authenticated-orcid":false,"given":"Wenbo","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haitong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoyi","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7046-7587","authenticated-orcid":false,"given":"Yuehuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuntao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruonan","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104820_b1","series-title":"2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, June 23-28, 2013","first-page":"891","article-title":"Cross-view image geolocalization","author":"Lin","year":"2013"},{"key":"10.1016\/j.jvcir.2026.104820_b2","series-title":"Proceedings of the 19th International Conference on Multimedia 2011, Scottsdale, AZ, USA, November 28 - December 1, 2011","first-page":"1125","article-title":"Geo-localization of street views with aerial image databases","author":"Bansal","year":"2011"},{"key":"10.1016\/j.jvcir.2026.104820_b3","series-title":"2014 IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS 2014, Chicago, IL, USA, September 14-18, 2014","first-page":"192","article-title":"Vision based robot localization by ground to satellite matching in GPS-denied situations","author":"Viswanathan","year":"2014"},{"issue":"7","key":"10.1016\/j.jvcir.2026.104820_b4","doi-asserted-by":"crossref","first-page":"1667","DOI":"10.1109\/TMM.2019.2957990","article-title":"iWave: CNN-based wavelet-like transform for image compression","volume":"22","author":"Ma","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.jvcir.2026.104820_b5","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2015, Boston, MA, USA, June 7-12, 2015","first-page":"70","article-title":"On the location dependence of convolutional neural network features","author":"Workman","year":"2015"},{"key":"10.1016\/j.jvcir.2026.104820_b6","doi-asserted-by":"crossref","first-page":"4171","DOI":"10.1109\/TMM.2020.3037496","article-title":"Transformer encoder with multi-modal multi-head attention for continuous affect recognition","volume":"23","author":"Chen","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.jvcir.2026.104820_b7","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, la, USA, June 18-24, 2022","first-page":"1152","article-title":"TransGeo: Transformer is all you need for cross-view image geo-localization","author":"Zhu","year":"2022"},{"issue":"7","key":"10.1016\/j.jvcir.2026.104820_b8","doi-asserted-by":"crossref","first-page":"4376","DOI":"10.1109\/TCSVT.2021.3135013","article-title":"A transformer-based feature segmentation and region alignment method for UAV-view geo-localization","volume":"32","author":"Dai","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104820_b9","series-title":"International Joint Conference on Neural Networks, IJCNN 2023, Gold Coast, Australia, June 18-23, 2023","first-page":"1","article-title":"An efficient method based on multi-view semantic alignment for cross-view geo-localization","author":"Wang","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104820_b10","series-title":"Forty-First International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104820_b11","series-title":"LightM-UNet: Mamba assists in lightweight unet for medical image segmentation","author":"Liao","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104820_b12","series-title":"LocalMamba: Visual state space model with windowed selective scan","author":"Huang","year":"2024"},{"issue":"21","key":"10.1016\/j.jvcir.2026.104820_b13","doi-asserted-by":"crossref","first-page":"4050","DOI":"10.3390\/rs16214050","article-title":"AFA\u2013mamba: Adaptive feature alignment with global\u2013local mamba for hyperspectral and LiDAR data classification","volume":"16","author":"Li","year":"2024","journal-title":"Remote. Sens."},{"issue":"3","key":"10.1016\/j.jvcir.2026.104820_b14","doi-asserted-by":"crossref","first-page":"1456","DOI":"10.1109\/TCSVT.2023.3296074","article-title":"MCCG: a ConvNeXt-based multiple-classifier method for cross-view geo-localization","volume":"34","author":"Shen","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"1","key":"10.1016\/j.jvcir.2026.104820_b15","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1049\/cit2.12077","article-title":"Multi-scale attention encoder for street-to-aerial image geo-localization","volume":"8","author":"Li","year":"2023","journal-title":"CAAI Trans. Intell. Technol."},{"issue":"1","key":"10.1016\/j.jvcir.2026.104820_b16","doi-asserted-by":"crossref","first-page":"12597","DOI":"10.1038\/s41598-024-63363-7","article-title":"Local feature acquisition and global context understanding network for very high-resolution land cover classification","volume":"14","author":"Li","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.jvcir.2026.104820_b17","first-page":"1","article-title":"Cross-view object geo-localization in a local region with satellite imagery","volume":"61","author":"Sun","year":"2023","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"issue":"2","key":"10.1016\/j.jvcir.2026.104820_b18","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1109\/TCSVT.2021.3061265","article-title":"Each part matters: Local patterns facilitate cross-view geo-localization","volume":"32","author":"Wang","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104820_b19","article-title":"MMHCA: Multi-feature representations based on multi-scale hierarchical contextual aggregation for UAV-view geo-localization","author":"Nanhua","year":"2024","journal-title":"Chin. J. Aeronaut."},{"key":"10.1016\/j.jvcir.2026.104820_b20","first-page":"1","article-title":"Multibranch joint representation learning based on information fusion strategy for cross-view geo-localization","volume":"62","author":"Ge","year":"2024","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"10.1016\/j.jvcir.2026.104820_b21","doi-asserted-by":"crossref","unstructured":"Y. Bin, H. Li, Y. Xu, X. Xu, Y. Yang, H.T. Shen, Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval, in: Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, on, Canada, 29 October 2023- 3 November 2023, 2023, pp. 3041\u20133050.","DOI":"10.1145\/3581783.3612427"},{"key":"10.1016\/j.jvcir.2026.104820_b22","doi-asserted-by":"crossref","first-page":"5509","DOI":"10.1109\/TNNLS.2024.3381347","article-title":"Geometric matching for cross-modal retrieval","volume":"36","author":"Wang","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.jvcir.2026.104820_b23","doi-asserted-by":"crossref","unstructured":"G. Li, M. Qian, G. Xia, Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization, in: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024, 2024, pp. 16719\u201316729.","DOI":"10.1109\/CVPR52733.2024.01582"},{"key":"10.1016\/j.jvcir.2026.104820_b24","doi-asserted-by":"crossref","first-page":"1592","DOI":"10.1109\/JSTARS.2024.3502160","article-title":"CV-cities: Advancing cross-view geo-localization in global cities","volume":"18","author":"Huang","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"issue":"6","key":"10.1016\/j.jvcir.2026.104820_b25","doi-asserted-by":"crossref","first-page":"5091","DOI":"10.1109\/TCSVT.2023.3336844","article-title":"Patch similarity self-knowledge distillation for cross-view geo-localization","volume":"34","author":"Li","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104820_b26","series-title":"Modeling Sequences with Structured State Spaces","author":"Gu","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104820_b27","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104820_b28","unstructured":"A. Gu, K. Goel, A. Gupta, C. R\u00e9, On the Parameterization and Initialization of Diagonal State Space Models, in: Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, la, USA, November 28 - December 9, 2022, 2022."},{"key":"10.1016\/j.jvcir.2026.104820_b29","series-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104820_b30","series-title":"MambaVision: A hybrid mamba-transformer vision backbone","author":"Hatamizadeh","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104820_b31","series-title":"Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part XXI","first-page":"148","article-title":"Zigma: A dit-style zigzag mamba diffusion model","volume":"vol. 15079","author":"Hu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104820_b32","first-page":"1","article-title":"RS-mamba for large remote sensing image dense prediction","volume":"62","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"10.1016\/j.jvcir.2026.104820_b33","series-title":"VMamba: Visual state space model","author":"Liu","year":"2024"},{"issue":"1","key":"10.1016\/j.jvcir.2026.104820_b34","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1007\/s10994-024-06728-3","article-title":"Learning multi-axis representation in frequency domain for medical image segmentation","volume":"114","author":"Ruan","year":"2025","journal-title":"Mach. Learn."},{"key":"10.1016\/j.jvcir.2026.104820_b35","series-title":"FDG-diff: Frequency-domain-guided diffusion framework for compressed hazy image restoration","author":"Zhang","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104820_b36","first-page":"1","article-title":"Dual-domain optimization model based on discrete Fourier transform and frequency-domain fusion for remote sensing single-image super-resolution","volume":"63","author":"Shi","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104820_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105358","article-title":"EPFDNet: Camouflaged object detection with edge perception in frequency domain","volume":"154","author":"Fang","year":"2025","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.jvcir.2026.104820_b38","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, la, USA, June 18-24, 2022","first-page":"11966","article-title":"A ConvNet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104820_b39","article-title":"Hierarchical graph representation learning with differentiable pooling","volume":"vol. 31","author":"Ying","year":"2018"},{"key":"10.1016\/j.jvcir.2026.104820_b40","unstructured":"Y. Shi, L. Liu, X. Yu, H. Li, Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization, in: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, 2019, pp. 10090\u201310100."},{"key":"10.1016\/j.jvcir.2026.104820_b41","series-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019","first-page":"5617","article-title":"Lending orientation to neural networks for cross-view geo-localization","author":"Liu","year":"2019"},{"issue":"5","key":"10.1016\/j.jvcir.2026.104820_b42","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1007\/s11263-019-01186-0","article-title":"Image-based geo-localization using satellite imagery","volume":"128","author":"Hu","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104820_b43","first-page":"3480","article-title":"Cross-view geo-localization via learning disentangled geometric layout correspondence","author":"Zhang","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104820_b44","series-title":"IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023","first-page":"16801","article-title":"Sample4Geo: Hard negative sampling for cross-view geo-localisation","author":"Deuser","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104820_b45","series-title":"Simple, effective and general: A new backbone for cross-view image geo-localization","author":"Zhu","year":"2023"},{"issue":"2","key":"10.1016\/j.jvcir.2026.104820_b46","doi-asserted-by":"crossref","first-page":"720","DOI":"10.3390\/s23020720","article-title":"Uav\u2019s status is worth considering: A fusion representations matching method for geo-localization","volume":"23","author":"Zhu","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.jvcir.2026.104820_b47","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024","first-page":"16719","article-title":"Unleashing unlabeled data: A paradigm for cross-view geo-localization","author":"Li","year":"2024"},{"issue":"4","key":"10.1016\/j.jvcir.2026.104820_b48","doi-asserted-by":"crossref","first-page":"678","DOI":"10.3390\/rs16040678","article-title":"GeoViewMatch: A multi-scale feature-matching network for cross-view geo-localization using swin-transformer and contrastive learning","volume":"16","author":"Zhang","year":"2024","journal-title":"Remote. Sens."},{"key":"10.1016\/j.jvcir.2026.104820_b49","first-page":"1","article-title":"Transfg: A cross-view geo-localization of satellite and UAVs imagery pipeline using transformer-based feature aggregation and gradient guidance","volume":"62","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"10.1016\/j.jvcir.2026.104820_b50","article-title":"Multi-level embedding and alignment network with consistency and invariance learning for cross-view geo-localization","author":"Chen","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104820_b51","doi-asserted-by":"crossref","unstructured":"X. Wang, L. Zhang, Z. Fan, Y. Liu, C. Chen, F. Deng, From Coarse to Fine: A Matching and Alignment Framework for Unsupervised Cross-View Geo-Localization, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2025, pp. 8024\u20138032.","DOI":"10.1609\/aaai.v39i8.32865"},{"key":"10.1016\/j.jvcir.2026.104820_b52","series-title":"Robust cross-view geo-localization via content-viewpoint disentanglement","author":"Li","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104820_b53","series-title":"2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, December 7-13, 2015","first-page":"3961","article-title":"Wide-area image geolocalization with aerial reference imagery","author":"Workman","year":"2015"},{"key":"10.1016\/j.jvcir.2026.104820_b54","series-title":"MM \u201920: The 28th ACM International Conference on Multimedia, Virtual Event \/ Seattle, WA, USA, October 12-16, 2020","first-page":"1395","article-title":"University-1652: A multi-view multi-source benchmark for drone-based geo-localization","author":"Zheng","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104820_b55","series-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual, June 19-25, 2021","first-page":"3640","article-title":"VIGOR: cross-view image geo-localization beyond one-to-one retrieval","author":"Zhu","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104820_b56","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S104732032600115X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S104732032600115X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T20:10:06Z","timestamp":1780603806000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S104732032600115X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":56,"alternative-id":["S104732032600115X"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104820","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dual-stream frequency-domain framework with contextual graph enhancer and consensus-difference fusion for cross-view geo-localization","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104820","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104820"}}