Despite their strong modeling capacities, Convolutional Neural Networks
...
Convolutional Neural Networks (CNNs) do not have a predictable recogniti...
In this paper, we build upon the weakly-supervised generation mechanism ...
Depth sensing is a critical component of autonomous driving technologies...
We present an approach to predict future video frames given a sequence o...
We present a novel formulation to removing reflection from polarized ima...
It is critical to predict the motion of surrounding vehicles for self-dr...
While the depth of modern Convolutional Neural Networks (CNNs) surpasses...
We design a multiscopic vision system that utilizes a low-cost monocular...
We present an approach with a novel differentiable flow-to-depth layer f...
Federated learning has a variety of applications in multiple domains by
...
We present a learning-based approach with pose perceptual loss for autom...
We present a fully automatic approach to video colorization with
self-re...
This paper shows that when applying machine learning to digital zoom for...
We present a learning-based approach to computing solutions for certain
...
We present an end-to-end deep learning approach to denoising speech sign...
We present an approach to separating reflection from a single image. The...
Imaging in low light is challenging due to low photon count and low SNR....
We present a semi-parametric approach to photographic image synthesis fr...
We present an approach to accelerating a wide variety of image processin...
We present an approach to synthesizing photographic images conditioned o...
We present a global optimization approach to optical flow estimation. Th...
The Imagenet Large Scale Visual Recognition Challenge (ILSVRC) is the on...