Skip to content

W-Net

Home / Concepts / W-Net

W-Net

Auto-generated stub. Edit this file to add more details.

A deep learning architecture composed of two stacked 3D U-Nets with skip connections for spatiotemporal feature extraction in image time-series.

Why It Matters

Central architecture for spatiotemporal feature extraction in moving object detection.

Evidence

Our approach uses two stacked 3D U-Nets with skip connections, which we call a W-Net

Metadata & Links