Progressive Spatio-Temporal Bilinear Network with Monte Carlo Dropout for Landmark-based Facial Expression Recognition with Uncertainty Estimation

06/08/2021
by   Negar Heidari, et al.
7

Deep neural networks have been widely used for feature learning in facial expression recognition systems. However, small datasets and large intra-class variability can lead to overfitting. In this paper, we propose a method which learns an optimized compact network topology for real-time facial expression recognition utilizing localized facial landmark features. Our method employs a spatio-temporal bilinear layer as backbone to capture the motion of facial landmarks during the execution of a facial expression effectively. Besides, it takes advantage of Monte Carlo Dropout to capture the model's uncertainty which is of great importance to analyze and treat uncertain cases. The performance of our method is evaluated on three widely used datasets and it is comparable to that of video-based state-of-the-art methods while it has much less complexity.

READ FULL TEXT

page 1

page 5

research
04/16/2019

LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition from Image Sequences

Recognizing facial expressions is one of the central problems in compute...
research
05/10/2022

Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild

Previous methods for dynamic facial expression in the wild are mainly ba...
research
03/14/2023

SimFLE: Simple Facial Landmark Encoding for Self-Supervised Facial Expression Recognition in the Wild

One of the key issues in facial expression recognition in the wild (FER-...
research
11/29/2017

Learning Spatio-temporal Features with Partial Expression Sequences for on-the-Fly Prediction

Spatio-temporal feature encoding is essential for encoding facial expres...
research
12/15/2022

Combating Uncertainty and Class Imbalance in Facial Expression Recognition

Recognition of facial expression is a challenge when it comes to compute...
research
11/16/2018

Mode Variational LSTM Robust to Unseen Modes of Variation: Application to Facial Expression Recognition

Spatio-temporal feature encoding is essential for encoding the dynamics ...
research
10/21/2017

A Generative Restricted Boltzmann Machine Based Method for High-Dimensional Motion Data Modeling

Many computer vision applications involve modeling complex spatio-tempor...

Please sign up or login with your details

Forgot password? Click here to reset