These pages document active areas of research for VFRAME. We have assembled studies describing what we have developed, with links to published source code and data models.
Media Attribute Analysis
Using simple media attributes to understand large OSINT video datasets
Synthetic Datasets
Using 3D modeled scenes to build synthetic training datasets for objects in conflict zones
Scene Summarization
Content-based scene summarization to find the most representative frames in videos
Munition Detector
Training object detection algorithms to locate illegal munitions