A5101867063- Image and Signal Denoising Methods
- Remote-Sensing Image Classification
- Medical Image Segmentation Techniques
- Medical Imaging Techniques and Applications
- Recommender Systems and Techniques
- Image Enhancement Techniques
- Video Surveillance and Tracking Methods
- Online Learning and Analytics
- Advanced Image Fusion Techniques
- Remote Sensing in Agriculture
- Innovative Teaching and Learning Methods
South China University of Technology
2021-2024
Xidian University
2019
Peking University
2018
While self-attention has been successfully applied in a variety of natural language processing and computer vision tasks, its application Monte Carlo (MC) image denoising not yet well explored. This paper presents based MC deep learning network on the fact that is essentially non-local means filtering embedding space which makes it inherently very suitable for task. Particularly, we modify standard mechanism to an auxiliary feature guided considers by-products (e.g., buffers) rendering...
Remote sensing spatiotemporal prediction aims to infer future trends from historical data, e.g., videos and time series images, has a broad application prospect in many fields. The foundation model is promising research direction for information mining because of its robust feature extraction capability, made rapid progress natural scenes. Nevertheless, due the spatially multi-scale temporally properties remote these methods still encounter bottlenecks when applied sensing. Therefore, we...
The accuracy of learning resource recommendation is crucial to realizing precise teaching and personalized learning. We propose a novel collaborative filtering algorithm based on the student’s online sequential behavior improve resources recommendation. First, we extract events from his/her process. Then each are selected as basic analysis unit feature sequence that represents behavioral characteristics. extracted generates vector. Moreover, H-[Formula: see text] clustering clusters students...
Recently, single-image SVBRDF capture is formulated as a regression problem, which uses network to infer four maps from flash-lit image. However, the accuracy still not satisfactory since previous approaches usually adopt endto-end inference strategies. To mitigate challenge, we propose "auxiliary renderings" intermediate targets, through divide original end-to-end task into several easier sub-tasks, thus achieving better accuracy. Our contributions are threefold. First, design three (or two...