- Advanced Image and Video Retrieval Techniques
- Domain Adaptation and Few-Shot Learning
- Infrared Target Detection Methodologies
- Video Surveillance and Tracking Methods
- Multimodal Machine Learning Applications
Xidian University
2022-2023
For visual question answering on remote sensing (RSVQA), current methods scarcely consider geospatial objects typically with large-scale differences and positional sensitive properties. Besides, modeling reasoning the relationships between entities have rarely been explored, which leads to one-sided inaccurate answer predictions. In this article, a novel method called spatial hierarchical network (SHRNet) is proposed, endows (RS) (VQA) system enhanced visual–spatial capability. Specifically,...
As a fundamental task for research in satellite videos (SVs), object tracking is used to track the target of interest traffic evaluation, military security, and so forth. The current technology remote sensing field makes it possible moving targets with relatively high frame rate image resolution. However, objects under this special view are often small blurry, making hard extract deep features effectively. result, quite few learning (DL) methods were proposed SVs. In addition, evaluation...