Abstract: Camouflaged object detection (COD) remains a challenging task in computer vision due to the intrinsic similarity between camouflaged objects and their backgrounds. Traditional methods often ...

DETR-based methods, which use multi-layer transformer decoders to refine object queries iteratively, have shown promising performance in 3D indoor object detection. However, the scene point features ...

Abstract: In recent years, UAV object tracking has provided technical support across various fields. Most existing work relies on convolutional neural networks (CNNs) or visual transformers. However, ...

For some U.S. residents, it can take a day or two to reach the nearest national park. And when you finally arrive—especially during the busy summer months and shoulder seasons—the parks are often too ...