Shaowei Weng
YOU?
Author Swipe
View article: Effective Modeling of Critical Contextual Information for TDNN-based Speaker Verification
Effective Modeling of Critical Contextual Information for TDNN-based Speaker Verification Open
Today, Time Delay Neural Network (TDNN) has become the mainstream architecture for speaker verification task, in which the ECAPA-TDNN is one of the state-of-the-art models. The current works that focus on improving TDNN primarily address t…
View article: Recognition of flight cadets brain functional magnetic resonance imaging data based on machine learning analysis
Recognition of flight cadets brain functional magnetic resonance imaging data based on machine learning analysis Open
The rapid advancement of the civil aviation industry has attracted significant attention to research on pilots. However, the brain changes experienced by flight cadets following their training remain, to some extent, an unexplored territor…
View article: HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution Open
Transformer-based methods have demonstrated excellent performance on super-resolution visual tasks, surpassing conventional convolutional neural networks. However, existing work typically restricts self-attention computation to non-overlap…
View article: Irregular Feature Enhancer for Low-dose CT Denoising
Irregular Feature Enhancer for Low-dose CT Denoising Open
So far, deep learning based networks have been wildly applied in Low-Dose Computed Tomography (LDCT) image denoising. However, they usually adopt symmetric convolution to achieve regular feature extraction, but cannot effectively extract i…
View article: Application of Improved Quasi-Affine Transformation Evolutionary Algorithm in Power System Stabilizer Optimization
Application of Improved Quasi-Affine Transformation Evolutionary Algorithm in Power System Stabilizer Optimization Open
This paper proposes a parameter coordination optimization design of a power system stabilizer (PSS) based on an improved quasi-affine transformation evolutionary (QUATRE) algorithm to suppress low-frequency oscillation and improve the dyna…
View article: Acquired superior oblique muscle palsy after smooth functional endoscopic sinus surgery: A case report
Acquired superior oblique muscle palsy after smooth functional endoscopic sinus surgery: A case report Open
Purpose: To present an iatrogenic superior oblique muscle palsy after smooth functional endoscopic sinus surgery. Case report: A 68-year-old man with hypertension & dyslipidemia presented with persistent binocular oblique diplopia for 3 mo…
View article: Multi-Layer Mini-Sudoku Based High-Capacity Data Hiding Method
Multi-Layer Mini-Sudoku Based High-Capacity Data Hiding Method Open
The main purpose of data hiding is to hide secret data imperceptibly into multimedia, ensuring secure data transmission. Existing magic matrix-based data hiding schemes cannot achieve satisfactory visual quality for a given low payload bec…
View article: A Novel Adjustable RDH Method for AMBTC-Compressed Codes Using One-to-Many Map
A Novel Adjustable RDH Method for AMBTC-Compressed Codes Using One-to-Many Map Open
Most existing AMBTC (absolute moment block truncation coding)-based reversible data hiding (RDH) schemes cannot be decoded by traditional AMBTC decoders, because they change the coding structure of the AMBTC compressed code stream, which i…
View article: An Improved Slime Mold Algorithm and its Application for Optimal Operation of Cascade Hydropower Stations
An Improved Slime Mold Algorithm and its Application for Optimal Operation of Cascade Hydropower Stations Open
A recently modern stochastic optimization algorithm has been developed by observing the life of slime mold physarum polycephalum in nature. The algorithm is called the slime mold algorithm (SMA) with an excellent exploratory capacity and e…
View article: Two-Layer Reversible Data Hiding Based on AMBTC Image With (7, 4) Hamming Code
Two-Layer Reversible Data Hiding Based on AMBTC Image With (7, 4) Hamming Code Open
In Malik et al.'s method, each pixel can be embedded with log23 bits by being modified at most 1. Thus, their method achieves significant hiding capacity while maintaining good visual quality. However, in their method, the first lower and …
View article: An Improved Integer Transform Combining with an Irregular Block Partition
An Improved Integer Transform Combining with an Irregular Block Partition Open
After conducting deep research on all existing reversible data hiding (RDH) methods based on Alattar’s integer transform, we discover that the frequently-used method in obtaining the difference value list of an image block may lead to high…
View article: Hybrid Scheme of Image’s Regional Colorization Using Mask R-CNN and Poisson Editing
Hybrid Scheme of Image’s Regional Colorization Using Mask R-CNN and Poisson Editing Open
Image colorization is a creative process of reasonably adding colors on gray-scale images to generate well-pleasing colorized images. The existing colorization methods normally require user-supplied hints of color points and doodles, or ha…
View article: Improved K-Pass Pixel Value Ordering Based Data Hiding
Improved K-Pass Pixel Value Ordering Based Data Hiding Open
K-pass pixel value ordering (PVO) is an effective reversible data hiding (RDH) technique. In k-pass PVO, the complexity measurement may lead to a weak estimation result because the unaltered pixels in a block are excluded to estimate block…
View article: Image Neural Style Transfer With Preserving the Salient Regions
Image Neural Style Transfer With Preserving the Salient Regions Open
Neural style transfer recently has become one of the most popular topics in academic research and industrial application. The existing methods can generate synthetic images by transferring different styles of some images to another given c…
View article: Copy-move Forgery Detection Robust to Various Transformation and Degradation Attacks
Copy-move Forgery Detection Robust to Various Transformation and Degradation Attacks Open
Trying to deal with the problem of low robustness of Copy-Move Forgery Detection (CMFD) under various transformation and degradation attacks, a novel CMFD method is proposed in this paper.The main advantages of proposed work include: (1) D…
View article: Joint Adaptive Coding and Reversible Data Hiding for AMBTC Compressed Images
Joint Adaptive Coding and Reversible Data Hiding for AMBTC Compressed Images Open
This paper proposes a joint coding and reversible data hiding method for absolute moment block truncation coding (AMBTC) compressed images. Existing methods use a predictor to predict the quantization levels of AMBTC codes. Equal-length in…
View article: Deep Learning for Detection of Object-Based Forgery in Advanced Video
Deep Learning for Detection of Object-Based Forgery in Advanced Video Open
Passive video forensics has drawn much attention in recent years. However, research on detection of object-based forgery, especially for forged video encoded with advanced codec frameworks, is still a great challenge. In this paper, we pro…