A5100779667- Distributed and Parallel Computing Systems
- Digital Media Forensic Detection
- Generative Adversarial Networks and Image Synthesis
- Advanced Data Storage Technologies
- Advanced Image Processing Techniques
- Parallel Computing and Optimization Techniques
- Face recognition and analysis
- Facial Nerve Paralysis Treatment and Research
- Advanced Authentication Protocols Security
- Cloud Data Security Solutions
- Pesticide Residue Analysis and Safety
- Cryptography and Data Security
- Spectroscopy and Chemometric Analyses
- Computational Drug Discovery Methods
- Advanced Data Compression Techniques
- Synthesis and Reactions of Organic Compounds
- Mast cells and histamine
- Multimodal Machine Learning Applications
Qingdao University of Science and Technology
2025
University of California, Riverside
2024
The University of Sydney
2023
Shanghai University
2023
South China Normal University
2020
Error-bounded lossy compression has been effective in significantly reducing the data storage/transfer burden while preserving reconstructed fidelity very well. Many error-bounded compressors have developed for a wide range of parallel and distributed use cases years. These are designed with distinct models design principles, such that each them features particular pros cons. In this paper we provide comprehensive survey emerging techniques different involving big to process. The key...
Long-term exposure to pesticides is associated with the incidence of cancer. With exponential increase in number new being synthesized, it becomes more and important evaluate toxicity by means simulated calculations. Based on existing data, machine learning methods can train model predictions effects novel pesticides, which have limited available data. Combined other technologies, this aid synthesis specific active structures, detect pesticide residues, identify their tolerable levels. This...
Error-bounded lossy compression has been a critical technique to significantly reduce the sheer amounts of simulation datasets for high-performance computing (HPC) scientific applications while effectively controlling data distortion based on user-specified error bound. In many real-world use cases, users must perform computational operations compressed (a.k.a. homomorphic compression). However, none existing error-bounded compressors support homomorphism, inevitably resulting in undesired...
Forgery of facial images and videos has increased the concern about digital security. It led to significant development detecting forgery data recently. However, data, especially published on Internet, are usually compressed with lossy compression algorithms such as H.264. The could significantly degrade performance recent detection algorithms. existing anti-compression focus enhancing in heavily but less consider adaption from various levels. We believe creating a capable handling unknown...
Forgery facial images and videos have increased the concern of digital security. It leads to significant development detecting forgery data recently. However, data, especially published on Internet, are usually compressed with lossy compression algorithms such as H.264. The could significantly degrade performance recent detection algorithms. existing anti-compression focus enhancing in heavily but less consider adaption from various levels. We believe creating a model that can handle unknown...
Facial forgery detection is a crucial but extremely challenging topic, with the fast development of techniques making synthetic artefact highly indistinguishable. Prior works show that by mining both spatial and frequency information performance deep learning models can be vastly improved. However, leveraging multiple types usually requires more than one branch in neural network, which makes model heavy cumbersome. Knowledge distillation, as an important technique for efficient modelling,...