A5018361121- Topic Modeling
- 3D Shape Modeling and Analysis
- Computational and Text Analysis Methods
- Mental Health via Writing
- 3D Surveying and Cultural Heritage
- Data Stream Mining Techniques
- Caching and Content Delivery
- Natural Language Processing Techniques
- Microplastics and Plastic Pollution
- Advanced Image Fusion Techniques
- Recommender Systems and Techniques
- Advanced Image Processing Techniques
- Recycling and Waste Management Techniques
- Image and Signal Denoising Methods
- Membrane Separation Technologies
- Metaheuristic Optimization Algorithms Research
- Robotics and Sensor-Based Localization
Shandong Jianzhu University
2024
Jilin Province Science and Technology Department
2024
Jilin University
2024
East China University of Science and Technology
2024
Beihang University
2022-2024
Shandong University of Science and Technology
2024
The evaluation of factual accuracy in large vision language models (LVLMs) has lagged behind their rapid development, making it challenging to fully reflect these models' knowledge capacity and reliability. In this paper, we introduce the first factuality-based visual question-answering benchmark Chinese, named ChineseSimpleVQA, aimed at assessing factuality LVLMs across 8 major topics 56 subtopics. key features include a focus on Chinese language, diverse types, multi-hop question...
Infrared images are susceptible to interference from a variety of factors during acquisition and transmission, resulting in the inclusion mixed noise, which seriously affects accuracy subsequent vision tasks. To solve this problem, we designed noise removal algorithm for infrared based on improved CycleGAN. First, proposed ResNet-E Block that incorporates EMA (Efficient Multi-Scale Attention Module) build generator it using skip-connection structure improve network’s ability remove different...