A5046919749- Face and Expression Recognition
- Sparse and Compressive Sensing Techniques
- Remote-Sensing Image Classification
- Advanced Computing and Algorithms
- Tensor decomposition and applications
- Advanced Image and Video Retrieval Techniques
- Advanced Image Fusion Techniques
- Image and Signal Denoising Methods
- Medical Image Segmentation Techniques
- Image Retrieval and Classification Techniques
- Computer Graphics and Visualization Techniques
- Generative Adversarial Networks and Image Synthesis
- Image Enhancement Techniques
- Advanced Clustering Algorithms Research
- Advanced Sensor and Control Systems
- Video Surveillance and Tracking Methods
- Advanced Algorithms and Applications
- Remote Sensing and Land Use
- Domain Adaptation and Few-Shot Learning
- 3D Shape Modeling and Analysis
- Medical Imaging Techniques and Applications
- Industrial Vision Systems and Defect Detection
- Aesthetic Perception and Analysis
- Cloud Computing and Remote Desktop Technologies
- Visual Attention and Saliency Detection
Minzu University of China
2017-2025
Shanghai Normal University
2025
Lanzhou University
2016-2018
Northwest Minzu University
2009-2017
Xi'an Jiaotong University
2011
Jilin Normal University
2004
Dimensionality reduction methods have commonly been used as a principled way to deal with the high dimensional data, unsupervised subspace learning is an effective approach of reduction. In this paper, we propose new method called low rank sparse preserving projection (LRSPP), which aims find projective vectors, and preserve both global structure locally linear data by constructing graph. The stable maximum generalized eigenvalue problem adopted allow efficient computation discriminant in...
In this paper, we present a hyper-Laplacian regularized method WHLR-MSC with new weighted tensor nuclear norm for multi-view subspace clustering. Specifically, firstly stack the representation matrices of different views into tensor, which neatly captures higher-order correlations between views. Secondly, in order to make all singular values have contributions based on tensor-Singular Value Decomposition (t-SVD), use constrain constructed can obtain class discrimination information sample...
Low-rank tensor completion (LRTC) plays an important role in many fields, such as machine learning, computer vision, image processing, and mathematical theory. Since rank minimization is NP-hard problem, one strategy that it converted into a convex relaxation nuclear norm (TNN) requires the repeated calculation of time-consuming SVD, other to convert some product two smaller tensors are easy fall local minimum. In order overcome above shortcomings, we propose robust factorization (RTF) model...
Since the uncertainty of a robot state changes over time, proposed is an adaptive simultaneous localisation and mapping (SLAM) algorithm based on Kullback-Leibler distance (KLD) sampling Markov chain Monte Carlo (MCMC) move step. First, it can adaptively determine number required particles by calculating KLD between posterior distribution approximated true at each Secondly, introduces MCMC step to increase particle variety. Both simulation experimental results demonstrate that obtain more...
Low rank representation (LRR) is one of the state-of-the-art methods for subspace clustering, which has been widely used in machine learning, data mining, and pattern recognition. The main objective LRR to seek lowest representations points based on a given dictionary. However, there are some drawbacks current LRR-based approaches: 1) original usually contain noise may not be representative as dictionary; 2) only global Euclidean structure considered, while local manifold structure, often...
Matrix factorization techniques have been frequently applied in computer vision and pattern recognition. Among them, self-representative matrix decomposition which chooses original data as the dictionary has received considerable attention dimension reduction representation. In this paper, we propose a Graph regularized Compact Self-representative Decomposition (GCSD) method using linear combination of directly obtaining low dimensional representation whole data. GCSD, local geometrical...
<title>Abstract</title> Dunhuang murals, treasured elements of our cultural heritage, have faced significant degradation due to prolonged environmental exposure, emphasizing an urgent need for sophisticated restoration methods. Current inpainting techniques, while valuable, often compromise the intricate balance between a mural's overall structure and its minute texture, leading subpar restorations with blurred regions inconsistencies. To address these shortcomings, research introduces...