相关论文: Improving Cost Learning for JPEG Steganography by …

In text-to-image (T2I) generation applications, negative embeddings have proven to be a simple yet effective approach for enhancing generation quality. Typically, these negative embeddings are derived from user-defined negative prompts,…

Recent years have witnessed the prevailing progress of Generative Adversarial Networks (GANs) in image-to-image translation. However, the success of these GAN models hinges on ponderous computational costs and labor-expensive training data.…

Deformable image registration plays a critical role in various tasks of medical image analysis. A successful registration algorithm, either derived from conventional energy optimization or deep networks requires tremendous efforts from…

Linguistic steganography (LS) conceals the presence of communication by embedding secret information into a text. How to generate a high-quality text carrying secret information is a key problem. With the widespread application of deep…

For almost 10 years, the detection of a hidden message in an image has been mainly carried out by the computation of Rich Models (RM), followed by classification using an Ensemble Classifier (EC). In 2015, the first study using a…

Recently, learned image compression methods have been actively studied. Among them, entropy-minimization based approaches have achieved superior results compared to conventional image codecs such as BPG and JPEG2000. However, the quality…

With limited storage/bandwidth resources, input images to Computer Vision (CV) applications that use Deep Neural Networks (DNNs) are often encoded with JPEG that is tailored to Human Vision (HV). This paper presents Deep Selector-JPEG, an…

With the rapid progress of LLMs, high quality generative text has become widely available as a cover for text steganography. However, prevailing methods rely on hand-crafted or pre-specified strategies and struggle to balance efficiency,…

Multi-modal image registration is a challenging problem that is also an important clinical task for many real applications and scenarios. As a first step in analysis, deformable registration among different image modalities is often…

Object detection in still images has drawn a lot of attention over past few years, and with the advent of Deep Learning impressive performances have been achieved with numerous industrial applications. Most of these deep learning models…

An online resource scheduling framework is proposed for minimizing the sum of weighted task latency for all the Internet of things (IoT) users, by optimizing offloading decision, transmission power and resource allocation in the large-scale…

Offline safe reinforcement learning (RL) aims to learn policies from a fixed dataset while maximizing performance under cumulative cost constraints. In practice, deployment requirements often vary across scenarios, necessitating a single…

We propose a learning-based compression scheme that envelopes a standard codec between pre and post-processing deep CNNs. Specifically, we demonstrate improvements over prior approaches utilizing a compression-decompression network by…

Renewable energy resources (RERs) have been increasingly integrated into distribution networks (DNs) for decarbonization. However, the variable nature of RERs introduces uncertainties to DNs, frequently resulting in voltage fluctuations…

In 5G and Beyond networks, Artificial Intelligence applications are expected to be increasingly ubiquitous. This necessitates a paradigm shift from the current cloud-centric model training approach to the Edge Computing based collaborative…

Content-based image retrieval (CBIR) systems on pixel domain use low-level features, such as colour, texture and shape, to retrieve images. In this context, two types of image representations i.e. local and global image features have been…

Operating directly from raw high dimensional sensory inputs like images is still a challenge for robotic control. Recently, Reinforcement Learning methods have been proposed to solve specific tasks end-to-end, from pixels to torques.…

Training robots to navigate diverse environments is a challenging problem as it involves the confluence of several different perception tasks such as mapping and localization, followed by optimal path-planning and control. Recently released…

As deep neural networks (DNNs) have been integrated into critical systems, several methods to attack these systems have been developed. These adversarial attacks make imperceptible modifications to an image that fool DNN classifiers. We…

Deep reinforcement learning (DRL) algorithms require substantial samples and computational resources to achieve higher performance, which restricts their practical application and poses challenges for further development. Given the…