conftrace_

geo-spatial understanding

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

ground-view image (1) cross-view retrieval (1) aerial image (1) vision-language model (1) foundation model (1) multimodal dataset (1) diffusion model (1) visual grounding (1) image captioning (1) object detection (1)

Papers

GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding CVPR 2026 MMLandmarks: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding CVPR 2026