134 papers with code • 1 benchmarks • 5 datasets
In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals.
Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality.
The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.
In this paper, we develop a novel unified framework called DeepText for text region proposal generation and text detection in natural images via a fully convolutional neural network (CNN).
Visual object tracking has been a fundamental topic in recent years and many deep learning based trackers have achieved state-of-the-art performance on multiple benchmarks.
In this paper, we take a slightly different viewpoint -- we find that precise positioning of raw points is not essential for high performance 3D object detection and that the coarse voxel granularity can also offer sufficient detection accuracy.