Qiangkui Leng
YOU?
Author Swipe
View article: Mitigating Lipschitz Singularities in Long-Tailed Diffusion Models via Time-Step Sharing Strategy
Mitigating Lipschitz Singularities in Long-Tailed Diffusion Models via Time-Step Sharing Strategy Open
Diffusion models have demonstrated remarkable success in generating diverse and high-fidelity images. However, their performance often degrades when applied to long-tailed datasets, where head classes significantly outnumber tail classes. …
View article: FACDIM: A Face Image Super-Resolution Method That Integrates Conditional Diffusion Models with Prior Attributes
FACDIM: A Face Image Super-Resolution Method That Integrates Conditional Diffusion Models with Prior Attributes Open
Facial image super-resolution seeks to reconstruct high-quality details from low-resolution inputs, yet traditional methods, such as interpolation, convolutional neural networks (CNNs), and generative adversarial networks (GANs), often fal…
View article: Reference Point and Grid Method-Based Evolutionary Algorithm with Entropy for Many-Objective Optimization Problems
Reference Point and Grid Method-Based Evolutionary Algorithm with Entropy for Many-Objective Optimization Problems Open
In everyday scenarios, there are many challenges involving multi-objective optimization. As the count of objective functions rises to four or beyond, the problem’s complexity intensifies considerably, often making it challenging for tradit…
View article: STAFGCN: a spatial-temporal attention-based fusion graph convolution network for pedestrian trajectory prediction
STAFGCN: a spatial-temporal attention-based fusion graph convolution network for pedestrian trajectory prediction Open
Pedestrian trajectory prediction provides crucial data support for the development of smart cities. Existing pedestrian trajectory prediction methods often overlook the different types of pedestrian interactions and the micro-level spatial…
View article: OBMI: oversampling borderline minority instances by a two-stage Tomek link-finding procedure for class imbalance problem
OBMI: oversampling borderline minority instances by a two-stage Tomek link-finding procedure for class imbalance problem Open
Mitigating the impact of class imbalance datasets on classifiers poses a challenge to the machine learning community. Conventional classifiers do not perform well as they are habitually biased toward the majority class. Among existing solu…
View article: A Complexity Measure for Data Classification Based on KNN with Dynamic Optimal K-Value Finding
A Complexity Measure for Data Classification Based on KNN with Dynamic Optimal K-Value Finding Open
The outcome of data classification is affected not only by the goodness of the classifier, but also by the complexity of the data itself. As a result, quantifying the complexity of the data itself can serve as a reference point for evaluat…
View article: Top-k Approximate Selection for TypicalityQuery Results over Spatio-textual Data
Top-k Approximate Selection for TypicalityQuery Results over Spatio-textual Data Open
Spatial keyword query is a classical query processing mode for spatio-textual data, which aims to provide users the spatio-textual objects with the highest spatial proximity and textual similarity to the given query. However, the top-k res…
View article: HS-Gen: a hypersphere-constrained generation mechanism to improve synthetic minority oversampling for imbalanced classification
HS-Gen: a hypersphere-constrained generation mechanism to improve synthetic minority oversampling for imbalanced classification Open
Mitigating the impact of class-imbalance data on classifiers is a challenging task in machine learning. SMOTE is a well-known method to tackle this task by modifying class distribution and generating synthetic instances. However, most of t…
View article: Attention-Driven Residual-Dense Network for No-Reference Image Quality Assessment
Attention-Driven Residual-Dense Network for No-Reference Image Quality Assessment Open
View article: A Greedy Method for Constructing Minimal Multiconlitron
A Greedy Method for Constructing Minimal Multiconlitron Open
Multiconlitron is a general theoretical framework for constructing piecewise linear classifier. However, it contains a relatively large number of linear functions, resulting in complicated model structure and poor generalization ability. L…
View article: Construction of A General Academic Search Engine Based on Multi-source and Heterogeneous Data
Construction of A General Academic Search Engine Based on Multi-source and Heterogeneous Data Open
For researchers, the retrieval needs on multisource and heterogeneous academic data are increasingly urgent.However, the existing retrieval systems still have some shortcomings, such as expensive prices, poor integration, loss of informati…
View article: Teaching Resources Construction and Teaching Methods Research of Data Structure
Teaching Resources Construction and Teaching Methods Research of Data Structure Open
According to the characteristics of data structure and the requirements of practical personnel, the necessity and guiding ideology of the teaching resources construction and the teaching methods research of data structure are illustrated f…
View article: A Novel Multiclass Text Classification Algorithm Based on Multiconlitron
A Novel Multiclass Text Classification Algorithm Based on Multiconlitron Open
A novel multiclass text classification algorithm based on multiconlitron is proposed.The multiconlitron is constructed for each possible pair of classes in sample space, each of which is used to separate two classes.For the sample to be cl…