Self-Supervised Approach for Facial Movement Based Optical Flow

no code implementations • 4 May 2021 • Muhannad Alkaddour, Usman Tariq, Abhinav Dhall

The aim of this work is threefold: (1) exploring self-supervised techniques to generate optical flow ground truth for face images; (2) computing baseline results on the effects of using face data to train Convolutional Neural Networks (CNN) for predicting optical flow; and (3) using the learned optical flow in micro-expression recognition to demonstrate its effectiveness.

Micro Expression Recognition Micro-Expression Recognition +1