A5102000132- Advanced Memory and Neural Computing
- Anomaly Detection Techniques and Applications
- Domain Adaptation and Few-Shot Learning
- Fault Detection and Control Systems
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Network Security and Intrusion Detection
- Time Series Analysis and Forecasting
- Visual perception and processing mechanisms
- Machine Fault Diagnosis Techniques
- Engineering Diagnostics and Reliability
- Advanced SAR Imaging Techniques
- Neural dynamics and brain function
- Heat Transfer and Boiling Studies
- Metaheuristic Optimization Algorithms Research
- Calibration and Measurement Techniques
- Cell Image Analysis Techniques
- Advanced Control Systems Design
- Extremum Seeking Control Systems
- Laser Design and Applications
- Target Tracking and Data Fusion in Sensor Networks
- Gear and Bearing Dynamics Analysis
- Multimodal Machine Learning Applications
- Optical Systems and Laser Technology
- Control Systems and Identification
University of Electronic Science and Technology of China
2023-2024
China University of Mining and Technology
2024
Wuhan University of Science and Technology
2023
Nanjing Forestry University
2019
Nanjing University of Aeronautics and Astronautics
2019
Harbin Institute of Technology
2008
Cross-modal remote sensing image-text retrieval (CMRSITR) aims to extract comprehensive information from diverse modalities. The primary challenge in this field is developing effective mappings between visual and textual modalities a shared latent space. Existing approaches generally focus on utilizing pre-trained unimodal models independently features each modality. However, these techniques often fall short achieving the critical alignment necessary for cross-modal matching. These...
Some reconstruction-based anomaly detection models in multivariate time series have brought impressive performance advancements but suffer from weak generalization ability and a lack of identification. These limitations can result the misjudgment models, leading to degradation overall performance. This paper proposes novel transformer-like model adopting contrastive learning module memory block (CLME) overcome above limitations. The tailored for data learn contextual relationships generate...