3D object detection has achieved significant performance in many fields,...
Occluded and long-range objects are ubiquitous and challenging for 3D ob...
In real-world applications, deep learning models often run in non-statio...
Data augmentations are important in training high-performance 3D object
...
3D object detection in point clouds is a core component for modern robot...
Developing neural models that accurately understand objects in 3D point
...
While multi-class 3D detectors are needed in many robotics applications,...
Cross-entropy loss and focal loss are the most common choices when train...
This paper proposes a method for computing the visible occluding contour...
Predicting the future motion of multiple agents is necessary for plannin...
Unsupervised learning methods have recently shown their competitiveness
...
As autonomous driving systems mature, motion forecasting has received
in...
In this paper, we investigate a private and cache-enabled unmanned aeria...
Existing neural network architectures in computer vision — whether desig...
In this paper, we propose a novel secure random caching scheme for
large...
Machine learning models are usually evaluated according to the average c...
In this paper, we study normalization methods for neural networks from t...
Deep learning algorithms, in particular 2D and 3D fully convolutional ne...
In this paper, we propose Weight Standardization (WS) to accelerate deep...
Recently, Neural Architecture Search (NAS) has successfully identified n...
Referring object detection and referring image segmentation are importan...
This is an opinion paper about the strengths and weaknesses of Deep Nets...
In this paper, we study the problem of parsing structured knowledge grap...
Direct-sequence spread spectrum (DSSS) has been recognized as an effecti...
We propose a method for learning CNN structures that is more efficient t...
Generating adversarial examples is an intriguing problem and an importan...
In this paper, we are interested in the few-shot learning problem. In
pa...
In this paper we are interested in the problem of image segmentation giv...
In this paper, we reveal the importance and benefits of introducing
seco...
Attention mechanisms have recently been introduced in deep learning for
...