Geospatial technologies have rapidly ascended to a position of paramount importance across the globe. By providing a better understanding of Earth’s ever-evolving landscape and our intricate...
Amazon’s papers at this year’s International Conference on Computer Vision, organized by topic. 3-D HAL3D: Hierarchical active learning for fine-grained 3D part labelingFenggen Yu, Yiming Qian,...
Amazon’s papers at this year’s Computer Vision and Pattern Recognition Conference (CVPR), sorted by research topic. 3-D perception Implicit surface contrastive clustering for LiDAR point cloudsZaiwei...
Most state-of-the-art computer vision models depend on supervised learning, in which labeled data is used for training. But labeling is costly, and the cost is compounded...