A5101448944- Advanced Neural Network Applications
- Advanced Graph Neural Networks
- Brain Tumor Detection and Classification
- Recommender Systems and Techniques
- Medical Image Segmentation Techniques
- Cryptography and Data Security
- Early Childhood Education and Development
- Parental Involvement in Education
- Radiomics and Machine Learning in Medical Imaging
- Topic Modeling
- Privacy-Preserving Technologies in Data
- Stochastic Gradient Optimization Techniques
- Smart Agriculture and AI
- Child and Adolescent Psychosocial and Emotional Development
- Generative Adversarial Networks and Image Synthesis
- Spectroscopy and Chemometric Analyses
- AI in cancer detection
- Medical Imaging and Analysis
- Visual Attention and Saliency Detection
- Ziziphus Jujuba Studies and Applications
- Industrial Vision Systems and Defect Detection
- Advanced Image Processing Techniques
- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Remote Sensing in Agriculture
Xijing University
2024-2025
Changzhou University
2023-2025
Southwestern University of Finance and Economics
2023-2024
Beijing Institute of Technology
2020
East China Normal University
2019
Shanghai Key Laboratory of Trustworthy Computing
2019
Graph Contrastive Learning (GCL) has drawn much research interest due to its strong ability capture both graph structure and node attribute information in a self-supervised manner. Current GCL methods usually adopt Neural Networks (GNNs) as the base encoder, which typically relies on homophily assumption of networks overlooks similarity space. There are many scenarios where such cannot be satisfied, or plays crucial role. In order design more robust mechanism, we develop novel preserving...
In recent years, deep learning has witnessed astonishing success in the field of remote sensing images. Generally, requires a large amount labeled training data. Nevertheless, sensing, sufficient data are scarce because often difficult, expensive, or time-consuming to obtain. To address these problems, we propose curriculum semi-supervised framework (DCLSSF) for image scene classification. This employs multimodal method which can realize classification images on range easy–difficult....
Machine learning, particularly the neural network (NN), is extensively exploited in dizzying applications. In order to reduce burden of computing for resource-constrained clients, a large number historical private datasets are required be outsourced semi-trusted or malicious cloud model training and evaluation. To achieve privacy preservation, most existing work either technique public key fully homomorphic encryption (FHE) resulting considerable computational cost ciphertext expansion,...
Video style transfer is a challenging task that requires not only stylizing video frames but also preserving temporal consistency among them. Many existing methods resort to optical flow for maintaining the in stylized videos. However, sensitive occlusions and rapid motions, its training processing speed quite slow, which makes it less practical real-world applications. In this paper, we propose novel fast method explores both global local without estimating flow. To preserve of entire...
The Transformer architecture has gained widespread acceptance in image segmentation. However, it sacrifices local feature details and necessitates extensive data for training, posing challenges to its integration into computer-aided medical To address the above challenges, we introduce CCFNet, a collaborative cross-fusion network, which continuously fuses CNN interactively exploit context dependencies. In particular, when integrating features Transformer, correlations between global tokens...
Compared to the surface defect detection of industrial products produced according specified processes, defects in naturally grown red jujubes poses unique and significant challenges for researchers. The high diversity defects, subtle distinctions from background, low contrast, varying scales, presence levels noise images are among factors that greatly amplify complexity tasks. Existing methods show some deficiencies addressing these issues, mainly due insufficient feature extraction...
This study explores the relationship between parenting styles and children's ability to concentrate. The focus of this research is investigate influence parental on attentional abilities, as play a crucial role in shaping behaviors, cognitive development, various abilities. While several studies have examined link different aspects child specifically investigating concentrate limited. To address gap, total 133 children aged 5 7 years, along with their parents, participated study. Parenting...