Technical Report for Valence-Arousal Estimation on Affwild2 Dataset
Published in
arXiv.org(2021)External Links:
TL
TL;DR
This work uses MIMAMO Net \cite{deng2020mimamo} model to achieve information about micro-motion and macro-motion for improving video emotion recognition and achieve Concordance Correlation Coefficient of 0.415 and 0.511 for valence and arousal on the reselected validation set.
Abstract
In this work, we describe our method for tackling the valence-arousal estimation challenge from ABAW FG-2020 Competition. The competition organizers provide an in-the-wild Aff-Wild2 dataset for participants to analyze affective behavior in real-life settings. We use MIMAMO Net \cite{deng2020mimamo} model to achieve information about micro-motion and macro-motion for improving video emotion recognition and achieve Concordance Correlation Coefficient (CCC) of 0.415 and 0.511 for valence and arousal on the reselected validation set.
References13 items
1
Contrastive Adversarial Learning for Person Independent Facial Emotion Recognition
2
Multitask Emotion Recognition with Incomplete Labels
3
Analysing Affective Behavior in the First ABAW 2020 Competition
4
MIMAMO Net: Integrating Micro- and Macro-motion for Video Emotion Recognition
5