Ruijie Fan

One Query, Many Scales: Sparse Mixture-of-Experts for Efficient Hierarchical Cross-View Geo-Localization

This work introduces GeoMoE, a sparse mixture-of-experts dual encoder that decouples global multi-scale representation learning from local hierarchical search, and introduces VIGOR-M, a four-city benchmark with an explicit parent--child satellite hierarchy and held-out half-step galleries for single-resolution, cross-resolution, and hierarchical evaluation.