A5101809225- Computational Drug Discovery Methods
- Face and Expression Recognition
- Advanced Steganography and Watermarking Techniques
- Video Surveillance and Tracking Methods
- Chaos-based Image/Signal Encryption
- Digital Media Forensic Detection
- Domain Adaptation and Few-Shot Learning
- Analytical Chemistry and Chromatography
- Geographic Information Systems Studies
- IoT-based Smart Home Systems
- Advanced Image and Video Retrieval Techniques
- Plant Genetic and Mutation Studies
- Advanced Neural Network Applications
- Soybean genetics and cultivation
- Nematode management and characterization studies
- Potato Plant Research
- Peanut Plant Research Studies
- Image Enhancement Techniques
- Machine Learning in Materials Science
- Dam Engineering and Safety
- Plant Pathogenic Bacteria Studies
- Cell Image Analysis Techniques
- Oil and Gas Production Techniques
- Agricultural pest management studies
- Human Pose and Action Recognition
Wuhan University
2015-2025
Urumqi Vocational University
2022
Segmentation of the prostate from Magnetic Resonance Imaging (MRI) plays an important role in cancer diagnosis. However, lack clear boundary and significant variation shapes appearances make automatic segmentation very challenging. In past several years, approaches based on deep learning technology have made progress segmentation. those mainly paid attention to features contexts within each single slice a 3D volume. As result, this kind faces many difficulties when segmenting base apex due...
Due to their excellent drug-like and pharmacokinetic properties, small molecule drugs are widely used treat various diseases, making them a critical component of drug discovery. In recent years, with the rapid development deep learning (DL) techniques, DL-based discovery methods have achieved performance in prediction accuracy, speed, complex molecular relationship modeling compared traditional machine approaches. These advancements enhance screening efficiency optimization, they provide...
The field of Remote Sensing Domain Generalization (RSDG) has emerged as a critical and valuable research frontier, focusing on developing models that generalize effectively across diverse scenarios. Despite the substantial domain gaps in RS images are characterized by variabilities such location, wavelength, sensor type, this area remains underexplored: (1) Current cross-domain methods primarily focus Adaptation (DA), which adapts to predefined domains rather than unseen ones; (2) Few...
摘要:
To achieve a high embedding capacity (EC) without any distortion in the directly decrypted result, reversible data hiding encrypted images (RDH-EI) scheme based on full bit-plane compression (FBPC) is proposed. FBPC designed to vacate as much room possible before image encryption. enrich adjacent redundancy within most significant bit (MSB) planes, we use flip prediction first MSB and then replace other planes with XOR result between that plane its higher level one successively. Hilbert...
Conventional deep learning methods typically employ supervised for drug response prediction (DRP). This entails dependence on labeled data from drugs model training. However, practical applications in the preclinical screening phase demand that DRP models predict responses novel compounds, often with unknown responses. presents a challenge, rendering unsuitable such scenarios. In this paper, we propose zero-shot solution task screening. Specifically, Multi-branch Multi-Source Domain...