Recent CNN and Transformer-based models tried to utilize frequency and
p...
Scene text image super-resolution (STISR), aiming to improve image quali...
Deep models have been widely and successfully used in image manipulation...
Image representation is critical for many visual tasks. Instead of
repre...
Real-world recognition system often encounters a plenty of unseen labels...
Recently, deep learning methods have shown great success in 3D point clo...
Regression tree (RT) has been widely used in machine learning and data m...
Recently, deep neural networks (DNNs) have been widely and successfully ...