Efficient Feature Extraction and Late Fusion Strategy for Audiovisual Emotional Mimicry Intensity Estimation
This work addresses the problem of estimating emotional intensity from audiovisual data for affective computing applications, but it is incremental as it combines existing methods without major innovations.
The paper tackled the Emotional Mimicry Intensity Estimation challenge by extracting visual features from ResNet18 and AUs, and audio features from Wav2Vec2.0, then using late fusion to average predictions, achieving an average Pearson's correlation coefficient of 0.3288 on the validation set.
In this paper, we present the solution to the Emotional Mimicry Intensity (EMI) Estimation challenge, which is part of 6th Affective Behavior Analysis in-the-wild (ABAW) Competition.The EMI Estimation challenge task aims to evaluate the emotional intensity of seed videos by assessing them from a set of predefined emotion categories (i.e., "Admiration", "Amusement", "Determination", "Empathic Pain", "Excitement" and "Joy"). To tackle this challenge, we extracted rich dual-channel visual features based on ResNet18 and AUs for the video modality and effective single-channel features based on Wav2Vec2.0 for the audio modality. This allowed us to obtain comprehensive emotional features for the audiovisual modality. Additionally, leveraging a late fusion strategy, we averaged the predictions of the visual and acoustic models, resulting in a more accurate estimation of audiovisual emotional mimicry intensity. Experimental results validate the effectiveness of our approach, with the average Pearson's correlation Coefficient($ρ$) across the 6 emotion dimensionson the validation set achieving 0.3288.