loading page

Faces in Event Streams (FES): An Annotated Face Dataset for Event Cameras
  • +1
  • Ulzhan Bissarinova ,
  • Tomiris Rakhimzhanova ,
  • Daulet Kenzhebalin ,
  • Huseyin Atakan Varol
Ulzhan Bissarinova
Author Profile
Tomiris Rakhimzhanova
Author Profile
Daulet Kenzhebalin
Author Profile
Huseyin Atakan Varol
Author Profile

Abstract

Faces in Event Streams dataset contains 689 minutes of recorded event streams, and 1.6 million annotated faces with bounding box and five point facial landmarks. Tha paper presents the dataset and corresponding models for detecting face and facial landmakrs directly from event stream data.