Technical Report for Valence-Arousal Estimation in ABAW2 Challenge
This is an incremental improvement for emotion recognition researchers in computer vision competitions.
The authors tackled valence-arousal estimation in real-life affective behavior analysis using a two-stream model with label distribution smoothing, achieving Concordance Correlation Coefficients of 0.591 for valence and 0.617 for arousal on the validation set.
In this work, we describe our method for tackling the valence-arousal estimation challenge from ABAW2 ICCV-2021 Competition. The competition organizers provide an in-the-wild Aff-Wild2 dataset for participants to analyze affective behavior in real-life settings. We use a two stream model to learn emotion features from appearance and action respectively. To solve data imbalanced problem, we apply label distribution smoothing (LDS) to re-weight labels. Our proposed method achieves Concordance Correlation Coefficient (CCC) of 0.591 and 0.617 for valence and arousal on the validation set of Aff-wild2 dataset.