Recent advances in computer vision and other types of artificial intelligence offer an opportunity for facial recognition to ...
Abstract: To address the challenges of small and medium-sized target recognition, as well as inconspicuous foreground features in complex backgrounds, this paper proposes a novel visual object ...
InstructSAM is a training-free framework for Instruction-Oriented Object Counting, Detection, and Segmentation (InstructCDS). We construct EarthInstruct, an InstructCDS benchmark for remote sensing.
Abstract: Small uncrewed autonmous vehicles (UAVs) equipped with deep learning models are increasingly used to detect small objects both on the ground and in aerial environments. Since small objects ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results