Abstract: Spectral super-resolution (SSR) can reconstruct hyperspectral images (HSIs) from images with fewer spectral bands, such as RGB images, to furnish critical spectral information for var-ious ...
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
Feedback