A5111512698- Iterative Learning Control Systems
- Image Processing Techniques and Applications
- Industrial Vision Systems and Defect Detection
- 3D Shape Modeling and Analysis
- Advanced Image and Video Retrieval Techniques
- Control Systems in Engineering
- Advanced Measurement and Metrology Techniques
- Medical Image Segmentation Techniques
- Generative Adversarial Networks and Image Synthesis
- Advanced Data Compression Techniques
- Gear and Bearing Dynamics Analysis
- Speech and Audio Processing
University of Cincinnati
2024-2025
University of Jinan
2024
Ritsumeikan University
2015
Diffusion models have made impressive progress in text-to-image synthesis. However, training such large-scale (e.g. Stable Diffusion), from scratch requires high computational costs and massive high-quality text-image pairs, which becomes unaffordable other languages. To handle this challenge, we propose IAP, a simple but effective method to transfer English into Chinese. IAP optimizes only separate Chinese text encoder with all parameters fixed align semantics space the one CLIP. achieve...
The objective of this study is to propose a novel methodology for intracranial pressure (ICP) waveform subpeak identification by incorporating arterial blood (ABP) and electrocardiogram (ECG) signals from patients who have undergone traumatic brain injury (TBI).
Abstract This paper explores a new virtual metrology method using Dual Linear Kalman Filter (DLKF) to track the gradual data variations in semiconductor manufacturing process. The prediction of Material Removal Rate (MRR) Chemical Mechanical Planarization (CMP) is adopted demonstrate results. proposed approach ensures dynamic tracking CMP process changes and jointly updates state parameter accordingly for MRR prediction. recursive nature DLKF allows drifts self-adjusting parameters...
Semantic understanding of images remains an important research challenge in machine intelligence and statistical learning.It mainly includes two steps: feature extraction classification.This study aims to explore a generalized framework motivated by the popularly used Bag-of-feature (BOF) super-vector coding using local descriptor, which is intuitively time -consuming for computation.In other hand, effortless on only exploring color edge histogram with uniformly quantized space, are...