Current state-of-the-art models for natural language understanding requi...
We develop a diffusion-based approach for various document layout sequen...
We study the problem of recognizing structured text, i.e. text that foll...
Text recognition is a long-standing research problem for document
digita...
Multimodal pre-training with text, layout, and image has achieved SOTA
p...
Pre-training of text and layout has proved effective in a variety of
vis...
In this paper, we propose Text-Aware Pre-training (TAP) for Text-VQA and...
A well-trained Convolutional Neural Network can easily be pruned without...
Detecting camouflaged moving foreground objects has been known to be
dif...
Multi-channel speech enhancement with ad-hoc sensors has been a challeng...
Foreground detection has been widely studied for decades due to its
impo...