Search Results for author:
Found 3 papers, 1 papers with code
AdvGen: Physical Adversarial Attack on Face Presentation Attack Detection Systems
We propose AdvGen, an automated Generative Adversarial Network, to simulate print and replay attacks and generate adversarial images that can fool state-of-the-art PADs in a physical domain attack setting.
Learning Deep and Compact Models for Gesture Recognition
The final model is less than $1~MB$ in size, which is less than one hundredth of our initial model, with a drop of $7\%$ in accuracy, and is suitable for real-time gesture recognition on mobile devices.
Ranked #1 on
Gesture Recognition
on Chalearn 2014
Panoramic Stereo Videos With a Single Camera
We present a practical solution for generating 360 degree stereo panoramic videos using a single camera.
