2 papers
cs.CV2026
WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding
Xianzhi Ma, Shujun Wang, Xiaohan Li +3
Ultra-High-Resolution (UHR) remote sensing image understanding requires Vision-Language Models (VLMs) to capture both the global scene layout and sparse yet task-critical local det…
cs.CV2025
GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing
Xianzhi Ma, Jianhui Li, Changhua Pei +1
The application of Vision-Language Models (VLMs) in remote sensing (RS) image understanding has achieved notable progress, demonstrating the basic ability to recognize and describe…