Multi-sensor modal fusion has demonstrated strong advantages in 3D objec...
Building a multi-modality multi-task neural network toward accurate and
...
Recently, the editing of neural radiance fields (NeRFs) has gained
consi...
We introduce a new task, novel view synthesis for LiDAR sensors. While
t...
While most recent autonomous driving system focuses on developing percep...
We introduce a novel approach that takes a single semantic mask as input...
Differentiable architecture search (DARTS) has been a mainstream directi...
Automatic data augmentation (AutoAugment) strategies are indispensable i...
There are two critical sensors for 3D perception in autonomous driving, ...
Fusing the camera and LiDAR information has become a de-facto standard f...
The release of tabular benchmarks, such as NAS-Bench-101 and NAS-Bench-2...
Weight sharing promises to make neural architecture search (NAS) tractab...
Weight sharing has become a de facto standard in neural architecture sea...
Weight sharing promises to make neural architecture search (NAS) tractab...
State-of-the-art segmentation methods rely on very deep networks that ar...
We identify a phenomenon, which we refer to as multi-model forgetting, t...
Neural Architecture Search (NAS) aims to facilitate the design of deep
n...
As mixed reality is gaining increased momentum, the development of effec...
Second-order pooling, a.k.a. bilinear pooling, has proven effective for
...
Convolutional Neural Networks (CNNs) have been successfully applied to m...