A5060769276- AI in cancer detection
- Anomaly Detection Techniques and Applications
- Human Pose and Action Recognition
- Cervical Cancer and HPV Research
- Gait Recognition and Analysis
- Remote-Sensing Image Classification
- Industrial Vision Systems and Defect Detection
- Radiomics and Machine Learning in Medical Imaging
- Remote Sensing and LiDAR Applications
- 3D Shape Modeling and Analysis
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Data Quality and Management
- Robotics and Sensor-Based Localization
- Bayesian Modeling and Causal Inference
- Advanced Graph Neural Networks
- Software System Performance and Reliability
- Concrete and Cement Materials Research
- Advanced Image and Video Retrieval Techniques
- IoT and Edge/Fog Computing
- Thermography and Photoacoustic Techniques
- Additive Manufacturing Materials and Processes
- Rock Mechanics and Modeling
- Innovative concrete reinforcement materials
- Domain Adaptation and Few-Shot Learning
Hohai University
2018-2025
Software (Spain)
2025
Harbin Engineering University
2024
University of Electronic Science and Technology of China
2024
Shaoxing University
2023
Ministry of Water Resources of the People's Republic of China
2023
Transformers have emerged as a transformative tool in various computer vision tasks, excelling at capturing long-range dependencies. Their potential applicability and scalability the interpretation of high-resolution remote sensing images (HRRSIs) thus garnered substantial interest. However, unlike natural images, HRRSIs present intricate scenes characterized by scale variations diverse appearances. These challenges underscore importance enabling networks to effectively assimilate both local...
Satellite-Drone Image Cross-View Geolocalization has wide applications. Due to the pronounced variations in visual features of 3D objects under different angles, cross-view image geolocalization remains an unresolved challenge. The key successful lies extracting crucial spatial structure information across scales image. Recent studies improve matching accuracy by introducing attention mechanism establish global associations among local features. However, existing methods primarily focus on...
Cervical cancer, the fourth most common fatal cancer in women, has a considerably increased cure rate if identified and treated at early stages. Computer-aided diagnosis technology is key for scaling up cervical screening. Computer-processed images of nuclei can help doctors better analyze diagnose extent lesions. However, lesion characteristics are mainly reflected cell nuclei, which will be significantly larger, with distorted boundary shapes deepened colors. What's worse that diseased...
Weld seam defect detection of industrial products is critical for product quality. In the weld image, main area only occupies a very small part. For more efficient detection, we propose segmentation method based on MGLNS-Retinex. Specifically, in order to solve problems low brightness, uneven illumination, and inconspicuous details first proposed an image enhancement algorithm called Multi Granularity Local Noise Suppression Retinex(MGLNS-Retinex). Then, threshold value iteration adopted...
With the development of multimedia, video surveillance systems are becoming more popular. However, current have a general function and unable to provide Intelligent perception.
Background and Objective: Cervical cancer is one of the severe diseases threatening women's health. Early detection diagnosis can significantly reduce risk, where cervical cytology classification indispensable. In recent years, computer-aided has become most effective techniques for screening cancer. This paper proposes a purified ensemble framework improved Inception networks classification.Methods: Our method be divided into four stages. Firstly, we employ diffusion model data augmentation...
With the booming of cloud computing, more and applications adopt services to implement their critical business. However, failures causing either service downtime or producing invalid results in such may range from a mere inconvenience significant monetary penalties even loss human lives. In systems, making highly dependable is one main challenges. Existing researches show that using fault injection for experimental assessment tolerance architecture still an open problem because complexity...