Most of the existing LiDAR-inertial navigation systems are based on
fram...
The pose-only (PO) visual representation has been proven to be equivalen...
We study the problem of semantic segmentation calibration. For image
cla...
Recently, data-driven inertial navigation approaches have demonstrated t...
In this paper, we raise up an emerging personal data protection problem ...
We are living in the era of Big Data and witnessing the explosion of dat...
In the era of data explosion, a growing number of data-intensive computi...
An accurate and efficient forecasting system is imperative to the preven...
This paper is concerned with ranking many pre-trained deep neural networ...
As news and social media exhibit an increasing amount of manipulative
po...
Matching information across image and text modalities is a fundamental
c...
We study how to leverage Web images to augment human-curated object dete...
White box adversarial perturbations are sought via iterative optimizatio...
We study how to train a student deep neural network for visual recogniti...
We propose a new task towards more practical application for image gener...
Object frequency in the real world often follows a power law, leading to...
Speaker diarization, which is to find the speech segments of specific
sp...
There is an increasing number of pre-trained deep neural network models....
As deep neural networks (DNNs) have become increasingly important and
po...
Deep Neural Network (DNN) trained by the gradient descent method is know...
In this paper, we present a new inpainting framework for recovering miss...
Powerful adversarial attack methods are vital for understanding how to
c...
Recent advancements in recurrent neural network (RNN) research have
demo...
Nonconvex and nonsmooth problems have recently attracted considerable
at...
There is a growing interest in designing models that can deal with image...
The success of deep neural networks often relies on a large amount of la...
In this paper, we focus on solving an important class of nonconvex
optim...
The large volume of video content and high viewing frequency demand auto...
Despite being impactful on a variety of problems and applications, the
g...
The recent success of deep neural networks is powered in part by large-s...