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 ...