{"type":"ScholarlyArticle","title":"A Structural-Analysis-Based Information Fusion for Multi-Modal Cross-View Geo-Localization","authors":[{"name":"Xu Yan","slug":"xu-yan","given":"Xu","family":"Yan","affiliation":""},{"name":"Xiaoran Zhang","slug":"xiaoran-zhang","given":"Xiaoran","family":"Zhang","affiliation":""},{"name":"Ziwei Shi","slug":"ziwei-shi","given":"Ziwei","family":"Shi","affiliation":""},{"name":"Yu Zang","slug":"yu-zang","given":"Yu","family":"Zang","affiliation":""},{"name":"Weiquan Liu","slug":"weiquan-liu","given":"Weiquan","family":"Liu","affiliation":""},{"name":"Cheng Wang","slug":"cheng-wang","given":"Cheng","family":"Wang","affiliation":""}],"abstract":"Cross-view geo-localization (CVGL) aims at localizing a ground-level query by retrieving its corresponding match from a database of geo-tagged satellite images. Existing multi-modal CVGL methods lack a structured design in the fusion stage, limiting their ability to fully exploit the information from multiple modalities. To overcome this limitation, we propose a Structural-Analysis-Based fusion principle that guides the design of network architecture. Following this principle, we present Decoupled Query Fusion (DQF), a novel fusion module that decouples feature interactions through role-specific learnable queries. These learnable queries aggregate features into distinct slots. Specifically, modality-specific queries capture unique information from each modality, while cross-modal queries extract redundant and synergistic information between different modalities. To better discriminate positive samples at varying geographic distances, we further propose Geo-aware Circle Loss, which adaptively weights supervision signal based on the geographical distance between samples and anchors. Extensive experiments on large-scale benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches. Comprehensive ablation studies further validate the effectiveness of each component. Our code and models will be made publicly available.","doi":"10.24963/ijcai.2026/218","url":"https://ijcai.org/proceedings/2026/218","pdf":"https://ijcai.org/proceedings/2026/0218.pdf","markdown":"https://ijcai.org/proceedings/2026/218.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/218","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":218,"pages":{"first":1956,"last":1964},"keywords":["Computer Vision: Multimodal learning","Computer Vision: 3D computer vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}