Cross-view geo-localization plays a critical role in Unmanned Aerial Vehicle (UAV) localization and navigation. However, significant challenges arise from the drastic viewpoint differences and appearance variations between images. Existing methods predominantly rely on semantic features from RGB images, often neglecting the importance of spatial structural information in capturing viewpoint-invariant features. To address this issue, we incorporate geometric structural information from normal images and introduce a Joint perception network to integrate RGB and Normal images (JRN-Geo). Our approach utilizes a dual-branch feature extraction framework, leveraging a Difference-Aware Fusion Module (DAFM) and Joint-Constrained Interaction Aggregation (JCIA) strategy to enable deep fusion and joint-constrained semantic and structural information representation. Furthermore, we propose a 3D geographic augmentation technique to generate potential viewpoint variation samples, enhancing the network's ability to learn viewpoint-invariant features. Extensive experiments on the University-1652 and SUES-200 datasets validate the robustness of our method against complex viewpoint variations, achieving state-of-the-art performance.

Mood disorders, particularly Bipolar Disorder (BD), present significant challenges in accurate diagnosis due to their complex neurobiological underpinnings. While recent advancements in neuroimaging techniques have provided valuable insights, the integration of multimodal data remains a critical challenge. This paper introduces a novel dual-stream neural architecture that leverages both structural and functional MRI data for mood disorder classification. Our large multimodal model uniquely combines advanced mathematical frameworks with domain adaptation techniques to address the inherent heterogeneity in neuroimaging data across different populations. We propose a theoretical foundation rooted in information geometry and optimal transport theory to formalize the domain adaptation problem in the context of neuroimaging analysis. Our method demonstrates superior performance in cross-domain mood disorder classification. Furthermore, we provide rigorous theoretical guarantees on the convergence and generalization capabilities of our model, establishing a new benchmark for robust and interpretable multimodal neuroimaging analysis in psychiatric diagnostics.