A5062691207- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Recommender Systems and Techniques
- Security and Verification in Computing
- Software Engineering Research
- FinTech, Crowdfunding, Digital Finance
- Advanced Manufacturing and Logistics Optimization
- Advanced Graph Neural Networks
- Image Enhancement Techniques
- Internet Traffic Analysis and Secure E-voting
- Cybercrime and Law Enforcement Studies
- Blockchain Technology Applications and Security
- Auction Theory and Applications
- Advanced Vision and Imaging
- Topic Modeling
- Manufacturing Process and Optimization
- Flexible and Reconfigurable Manufacturing Systems
- Computer Graphics and Visualization Techniques
- Information and Cyber Security
- Terrorism, Counterterrorism, and Political Violence
China Three Gorges University
2024
University of Chinese Academy of Sciences
2019-2023
Institute of Information Engineering
2020-2022
Chinese Academy of Sciences
2020-2022
Indiana University Bloomington
2021
In this paper, we address the problem of simultaneous relighting and novel view synthesis a complex scene from multi-view images with limited number light sources. We propose an analysis-synthesis approach called Relit-NeuLF. Following recent neural 4D field network (NeuLF)[22], Relit-NeuLF first leverages two-plane representation to parameterize each ray in coordinate system, enabling efficient learning inference. Then, recover spatially-varying bidirectional reflectance distribution...
With the rapid development of Internet, number cyber threats increases exponentially. More and more come from new unexpected sources, leading organizations individuals to facing security risks vulnerabilities. Automatically obtaining structuring information cybersecurity news can help analysts identify useful quickly. Most existing studies on extracting events merely focused event detection task, aiming discover categorize plain text. However, such methods cannot capture as who performed...
Energy-efficient human–robot collaboration poses significant challenges to the sustainable operation of production systems. Therefore, our work proposes novel robotic edge intelligence address issue. First, is proposed fully utilize embedded computing capabilities robots, and state transition diagrams are developed for jobs, humans, respectively. Second, a multi-objective model designed energy-efficient scheduling problem evaluate performance energy efficiency as whole. Third, heuristic...
With the proliferation of information and rapid network development, attacks threats are on rise, identifying malicious traffic is crucial for security. However, distribution benign in real-world networks unbalanced, identification a environment with large amount unbalanced less known labelled still pressing problem. To tackle this issue, paper presents self-paced reweighting Positive-Unlabeled learning algorithm (SRPU) detecting imbalanced traffic. This approach includes training strategy...