Abstract: Recent advances in LiDAR representation learning with limited annotations show strong promise. Existing well-performed methods mainly focus on distilling the 2D representation into the 3D ...
Abstract: Object detection in remote sensing imagery is particularly challenging due to arbitrary object orientations, large scale variations, and dense scene layouts. This work presents EdgeYOLO-RS, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results