Deep neural networks are vulnerable to backdoor attacks (Trojans), where...
The ensemble method is a promising way to mitigate the overestimation is...
Warm-Start reinforcement learning (RL), aided by a prior policy obtained...
While lightweight ViT framework has made tremendous progress in image
su...
Recent researches show that the deep learning based object detection is
...
Digital twin has recently attracted growing attention, leading to intens...
Depth map super-resolution (DSR) has been a fundamental task for 3D comp...
A Backdoor attack (BA) is an important type of adversarial attack agains...
E-learning is a widely used learning method, but with the development of...
Metaverse is a new type of Internet application and social form that
int...
Autonomous highlight detection is crucial for enhancing the efficiency o...
This paper studies unsupervised/self-supervised whole-graph representati...
Convolution and self-attention are acting as two fundamental building bl...
Deep Neural Networks (DNNs) have been shown vulnerable to adversarial
(T...
In this work, we propose a Cross-view Contrastive Learning framework for...
Multi-Source Domain Adaptation (MSDA) focuses on transferring the knowle...
Along with the rapid development of Internet and cyber techniques, the
I...
This paper studies distributed Q-learning for Linear Quadratic Regulator...
System identification is a fundamental problem in reinforcement learning...
Transferring knowledges learned from multiple source domains to target d...
Applying the knowledge of an object detector trained on a specific domai...
In human-computer interaction, it is important to accurately estimate th...