This paper presents a comprehensive study of Convolutional Neural Networks (CNN) and
transfer learning in the context of medical imaging. Medical imaging plays a critical role in …

Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

Video prediction is a challenging task. The quality of video frames from current state-of-the-
art (SOTA) generative models tends to be poor and generalization beyond the training data …

We show that standard Transformers without graph-specific modifications can lead to
promising results in graph learning both in theory and practice. Given a graph, we simply …

The growing energy and performance costs of deep learning have driven the community to
reduce the size of neural networks by selectively pruning components. Similarly to their …

Several image processing tasks, such as image classification and object detection, have
been significantly improved using Convolutional Neural Networks (CNN). Like ResNet and …

The recent research in semi-supervised learning (SSL) is mostly dominated by consistency
regularization based methods which achieve strong performance. However, they heavily …

Human pose estimation aims to locate the human body parts and build human body
representation (eg, body skeleton) from input data such as images and videos. It has drawn …

Abstract Convolutional Neural Networks (CNN) conduct image classification by activating
dominant features that correlated with labels. When the training and testing data are under …

Human pose estimation deeply relies on visual clues and anatomical constraints between
parts to locate keypoints. Most existing CNN-based methods do well in visual …