A5100695134- Advanced Image and Video Retrieval Techniques
- Image and Video Stabilization
- Advanced Image Fusion Techniques
- Fault Detection and Control Systems
- Medical Image Segmentation Techniques
- Advanced Neural Network Applications
- Advanced Data Processing Techniques
- Multimodal Machine Learning Applications
- Retinal Imaging and Analysis
- Advanced Image Processing Techniques
- Domain Adaptation and Few-Shot Learning
Beihang University
2014-2023
Institute of Art
2023
Open-vocabulary object detection aims to provide detectors trained on a fixed set of categories with the generalizability detect objects described by arbitrary text queries. Previous methods adopt knowledge distillation extract from Pretrained Vision-and-Language Models (PVLMs) and transfer it detectors. However, due non-adaptive proposal cropping single-level feature mimicking processes, they suffer information destruction during extraction inefficient transfer. To remedy these limitations,...
Video stabilization in atmosphere turbulent conditions is aimed at removing spatiotemporally varying distortions from video recordings. Conventional shaky approaches do not perform effectively under circumstances due to the erratic motion common those conditions. Using complex-valued image pyramids, we propose a method mitigate this videos. First, each frame of decomposed into different spatial frequencies using Laplacian pyramid. Second, Riesz transform adopted extract local amplitude and...
As most electronic system structure is complex and uncertain, this paper presents a new efficiency method for spacecraft electrical characteristics identification. PCA (Principal Component Analysis) feature extraction, offline FCM (Fuzzy C-means) clustering online SVM (Support Vector Machine) classifier introduced into the registration model. At first step of algorithm, get an expert training set by method, then using extraction to principal component. After make fast effective. These are...