Abstract: Visual grounding in remote sensing (RSVG) images aims to detect specific objects associated with referring expressions in remote sensing images. Existing methods typically combine outputs of ...
Abstract: Visual grounding tasks aim to localize image regions based on natural language references. In this work, we ex-plore whether generative VLMs predominantly trained on image-text data could be ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results