There are ubiquitous distribution shifts in the real world. However, dee...
Efficiency and trustworthiness are two eternal pursuits when applying de...
Reliable confidence estimation for deep neural classifiers is a challeng...
Label noise poses a serious threat to deep neural networks (DNNs). Emplo...
Reliable confidence estimation for the predictions is important in many
...
Detecting Out-of-distribution (OOD) inputs have been a critical issue fo...
In the last a few decades, deep neural networks have achieved remarkable...
Document images are now widely captured by handheld devices such as mobi...
Representation is a core issue in artificial intelligence. Humans use
di...
As camera-based documents are increasingly used, the rectification of
di...
Arbitrary-shaped text detection is an important and challenging task in
...
The accuracies for many pattern recognition tasks have increased rapidly...
Deep learning based approaches have achieved significant progresses in
d...
Scene text recognition has drawn great attentions in the community of
co...
Convolutional neural networks (CNNs) have been widely used for image
cla...
Conjugate gradient methods are a class of important methods for solving
...
Scene text recognition has attracted great interests from the computer v...
In this paper, we first provide a new perspective to divide existing hig...
Recent deep learning based approaches have achieved great success on
han...
Recent deep learning based methods have achieved the state-of-the-art
pe...
Convolutional neural network (CNN) has achieved state-of-the-art perform...