-
Article
Swin transformer and ResNet based deep networks for low-light image enhancement
Low-light image enhancement is a long-term low-level vision problem, which aims to improve the visual quality of images captured in low illumination environment. Convolutional neural network (CNN) is the found...
-
Chapter and Conference Paper
A Multi-party Private Set Union Protocol Against Malicious Adversary
Our protocol, grounded on the principles of SPDZ technology and the Bloom Filter, aims to efficiently compute the union of datasets from multiple participants without exposing individual participants’ data. In...
-
Article
Local weight coupled network: multi-modal unequal semi-supervised domain adaptation
Existing semi-supervised domain adaptation (SSDA) approaches on visual classification usually assume that the labelled source data are only collected from single modality. However, since single source data can...
-
Chapter and Conference Paper
A Comparison of Discrete Event Simulator and Real-Time Emulator for Mobile Ad Hoc Network
Network research requires testing tools to evaluate new protocols and algorithms. Since implementing and verifying these protocols and algorithms on real network devices is time-consuming and costly, widely-us...
-
Chapter and Conference Paper
A Reinforcement Learning Based Resource Access Strategy for Satellite-Terrestrial Integrated Networks
The satellite-terrestrial integrated network (STIN) has recently attracted considerable attention. The problem studied in this paper is how the access controller located at the ground station selects the best-...
-
Chapter and Conference Paper
An Efficient Privacy-Preserving Scheme for Traffic Monitoring Services in Vehicular Networks
Traffic monitoring services show great potential for improving the traffic efficiency in vehicular networks. Drivers can obtain the latest information on their upcoming routes by sending location-based queries...
-
Article
Three-stage Stackelberg game based edge computing resource management for mobile blockchain
Blockchain can provide a dependable environment for mobile applications. Mining, as an important component in blockchain, requires a lot of computing resources, and hence resource limited moblie devices are un...
-
Article
An improved steganography without embedding based on attention GAN
Steganography is an art to hide information in the carriers to prevent from being detected, while steganalysis is the opposite art to detect the presence of the hidden information. With the development of deep...
-
Chapter and Conference Paper
Cartographer Algorithm and System Implementation Based on Enhanced Pedestrian Filtering of Inspection Robot
Aiming at the problem that the pedestrian filtering function is unstable in the subway station hall with heavy traffic in the cartographer and the generated map has related noise that affects later path planni...
-
Article
A steganographic method based on gain quantization for iLBC speech streams
Under the premise of ensuring good speech quality and resistance to steganalysis, how to embed as much information as possible into low-bit-rate speech is a challenge. The existing research mainly focuses on l...
-
Chapter and Conference Paper
A Novel Approach of Steganalysis to Deal with Steganographic Algorithm Mismatch
Steganalysis is the art to detect the hiding information introduced by the algorithm of steganography. When steganalysis model is trained on the image set with stego images produced by a certain type of stegan...
-
Chapter and Conference Paper
Diagonal Symmetric Pattern Based Illumination Invariant Measure for Severe Illumination Variations
This paper proposes a diagonal symmetric pattern (DSP) to develop the illumination invariant measure for severe illumination variations. Firstly, the subtraction of two diagonal symmetric pixels is defined as ...
-
Chapter and Conference Paper
Latency-Aware Data Placements for Operational Cost Minimization of Distributed Data Centers
A large amount of data are stored in geographically distributed data centers interconnected by the Internet. The power consumption for running the servers storing the data and inter-data center network transpo...
-
Chapter and Conference Paper
One-Time, Oblivious, and Unlinkable Query Processing Over Encrypted Data on Cloud
Location-based services (LBSs) are widely deployed in commercial services. These services always depend on a service provider, e.g., a cloud server, to store the enormous amounts of geospatial data and to proc...
-
Article
Study on the interaction between the cover source mismatch and texture complexity in steganalysis
Cover source mismatch (CSM) occurs when a detection classifier for steganalysis trained on objects from one cover source is tested on another source. However, it is very hard to find the same sources as suspic...
-
Chapter and Conference Paper
Multi-kernel Collaboration-Induced Fuzzy Local Information C-Means Algorithm for Image Segmentation
As an advanced method in the field of image segmentation, the fuzzy local information c-means (FLICM) algorithm has the problem of which segmentation performance is degraded when neighboring pixels are pollute...
-
Article
Face recognition under varying illumination based on singular value decomposition and retina modeling
Face recognition under the influence of complex illumination is a challenging problem to be solved. The common treatments for minimizing the affection of illumination variation are illumination preprocessing a...
-
Article
Wavelet denoising with generalized bivariate prior model
This paper presents a novel wavelet method based on a prior model of wavelet coefficient with a generalized bivariate distribution function. The generalized bivariate prior model extends the isotropic bivariat...
-
Article
How people share digital images in social networks: a questionnaire-based study of privacy decisions and access control
The blind sharing of digital images in social networks may lead to threats to privacy. Currently, privacy decision recommendations and access control mechanisms are inadequate with respect to sharing digital i...
-
Article
Illumination robust single sample face recognition based on ESRC
The extended sparse representation classifier (ESRC) is one of the state-of-the-art solutions for single sample face recognition, but it performs unsatisfactorily under varying illumination. There are two main...