AI RESEARCH
AgroVG: A Large-Scale Multi-Source Benchmark for Agricultural Visual Grounding
arXiv CS.CV
•
ArXi:2605.22034v1 Announce Type: new Visual grounding, the task of localizing objects described by natural-language expressions, is a foundational capability for agricultural AI systems, enabling applications such as selective weeding, disease monitoring, and targeted harvesting. Reliable evaluation of agricultural visual grounding remains challenging because agricultural targets are often small, repetitive, occluded, or irregularly shaped, and instructions may refer to one, many, or no objects in an image.