An audiovisual and contextual approach for categorical and continuous emotion recognition in-the-wild

TL;DR

This paper presents a multi-modal, multi-stream deep learning framework for in-the-wild emotion recognition that incorporates facial, bodily, and contextual features to improve robustness under challenging conditions.

Contribution

It introduces a novel multi-stream CNN-RNN model leveraging audiovisual and contextual cues, demonstrating improved emotion recognition performance in unconstrained environments.

Findings

Multi-modal approach enhances recognition accuracy.

Inclusion of body and scene context improves robustness.

Model outperforms existing methods on Aff-Wild2 dataset.

Abstract

In this work we tackle the task of video-based audio-visual emotion recognition, within the premises of the 2nd Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW2). Poor illumination conditions, head/body orientation and low image resolution constitute factors that can potentially hinder performance in case of methodologies that solely rely on the extraction and analysis of facial features. In order to alleviate this problem, we leverage both bodily and contextual features, as part of a broader emotion recognition framework. We choose to use a standard CNN-RNN cascade as the backbone of our proposed model for sequence-to-sequence (seq2seq) learning. Apart from learning through the RGB input modality, we construct an aural stream which operates on sequences of extracted mel-spectrograms. Our extensive experiments on the challenging and newly assembled Aff-Wild2 dataset verify the validity of our intuitive multi-stream and multi-modal approach towards emotion recognition in-the-wild. Emphasis is being laid on the the beneficial influence of the human body and scene context, as aspects of the emotion recognition process that have been left relatively unexplored up to this point. All the code was implemented using PyTorch and is publicly available.