A5033299469- Face and Expression Recognition
- Remote-Sensing Image Classification
- Advanced Image and Video Retrieval Techniques
- Machine Learning and ELM
- Domain Adaptation and Few-Shot Learning
- Sparse and Compressive Sensing Techniques
- Video Surveillance and Tracking Methods
- Human Pose and Action Recognition
- Neural Networks and Applications
- Image Retrieval and Classification Techniques
- Gaze Tracking and Assistive Technology
- Advanced Computing and Algorithms
- Fractional Differential Equations Solutions
- Medical Image Segmentation Techniques
- Ultrasound and Hyperthermia Applications
- Advanced Adaptive Filtering Techniques
- Advanced Algorithms and Applications
- Metaheuristic Optimization Algorithms Research
- Tendon Structure and Treatment
- Image Processing Techniques and Applications
- Emotion and Mood Recognition
- Model Reduction and Neural Networks
- Blind Source Separation Techniques
- Sports injuries and prevention
Nanjing Normal University
2021-2025
Nanjing University of Science and Technology
2019-2021
Peking University Shenzhen Hospital
2020
To defy the curse of dimensionality, inputs are always projected from original high-dimensional space into target low-dimension for feature extraction. However, due to existence noise and outliers, extraction task corrupted data is still a challenging problem. Recently, robust method called low rank embedding (LRE) was proposed. Despite success LRE in experimental studies, it also has many disadvantages: 1) The learned projection cannot quantitatively interpret importance features. 2) does...
In the fields of pattern recognition and data mining, two problems need to be addressed. First, curse dimensionality degrades performance many practical processing techniques. Second, due existence noise outliers, feature extraction on corrupted cannot effectively achieved. Recently, some representation based methods have produced promising results. However, these handle case in which nonlinear similarity exists failed provide quantized interpretability for importance features. this paper,...
Abstract Nonviral targeting technology has become promising as a form of gene therapy for diseases and injuries, such Achilles tendon injuries. In this study, we used avidin–biotin bridge positive–negative charge attractions to load the intercellular adhesion molecule-1 (ICAM-1) antibody basic fibroblast growth factor (bFGF) plasmid onto surface microbubbles. The saturated loading capacity 1.1 × 10 8 microbubble was 6.55 ± 0.53 µg. We established ICAM-1 antigen microenvironment using tumor...
In real applications, several unpredictable or uncertain factors could result in unpaired multiview data, i.e., the observed samples between views cannot be matched. Since joint clustering among is more effective than individual each view, we investigate (UMC), which a valuable but insufficiently studied problem. Due to lack of matched views, fail build connection views. Therefore, aim learn latent subspace shared by However, existing learning methods usually rely on To address this issue,...