Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
EarthVL: A Progressive Earth Vision-Language Understanding and Generation Framework
Junjue Wang, Yanfei Zhong, Zihang Chen +3
Earth vision has achieved milestones in geospatial object recognition but lacks exploration in object-relational reasoning, limiting comprehensive scene understanding. To address t…
cs.CV2025
DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding
Weihao Xuan, Junjue Wang, Heli Qi +5
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in visual understanding, but their application to long-term Earth observation analysis remains li…
cs.CV2023
EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering
Junjue Wang, Zhuo Zheng, Zihang Chen +2
Earth vision research typically focuses on extracting geospatial object locations and categories but neglects the exploration of relations between objects and comprehensive reasoni…