A5017030937- Anomaly Detection Techniques and Applications
- Network Security and Intrusion Detection
- Advanced Neural Network Applications
- Fault Detection and Control Systems
- Domain Adaptation and Few-Shot Learning
- Computer Graphics and Visualization Techniques
- Artificial Immune Systems Applications
- Advanced Image and Video Retrieval Techniques
- Generative Adversarial Networks and Image Synthesis
- Advanced Vision and Imaging
- COVID-19 diagnosis using AI
- Complex Network Analysis Techniques
- Advanced Graph Neural Networks
- Imbalanced Data Classification Techniques
- Topic Modeling
- Bacillus and Francisella bacterial research
- Industrial Vision Systems and Defect Detection
- Multimodal Machine Learning Applications
Sichuan University
2022-2024
Chongqing Jiaotong University
2023
Hiroshima University
2020-2021
Photorealistic stylization of 3D scenes aims to generate photorealistic images from arbitrary novel views according a given style image, while ensuring consistency when rendering video different viewpoints. Some existing methods using neural radiance fields can effectively predict stylized by combining the features image with multi-view train scenes. However, these view that contain undesirable artifacts. In addition, they cannot achieve universal for scene. Therefore, needs retrain scene...
3D scenes photorealistic stylization aims to generate images from arbitrary novel views according a given style image while ensuring consistency when rendering different viewpoints. Some existing methods with neural radiance fields can effectively predict stylized by combining the features of multi-view train scenes. However, these view that contain objectionable artifacts. Besides, they cannot achieve universal for scene. Therefore, styling must retrain scene representation network based on...
Knowledge distillation has been widely applied in semantic segmentation to reduce the model size and computational complexity. The prior knowledge methods for mainly focus on transferring spatial relation knowledge, neglecting transfer channel correlation feature space, which is vital segmentation. We propose a novel Channel Correlation Distillation (CCD) method solve this issue. between channels tells how likely these belong same categories. force student mimic teacher by minimizing...