Neuromorphic Valence and Arousal Estimation

TL;DR

This paper introduces a novel approach using neuromorphic data from event cameras to estimate emotional states from faces, demonstrating that models trained on simulated data can perform well on real data for valence and arousal prediction.

Contribution

It presents a new method of using neuromorphic data and simulation for emotion recognition, achieving state-of-the-art results without additional real-data training.

Findings

Models trained on simulated neuromorphic data perform well on real data.

Neuromorphic approaches can match or surpass traditional methods in emotion estimation.

Multiple models, both frame-based and video-based, are proposed and evaluated.

Abstract

Recognizing faces and their underlying emotions is an important aspect of biometrics. In fact, estimating emotional states from faces has been tackled from several angles in the literature. In this paper, we follow the novel route of using neuromorphic data to predict valence and arousal values from faces. Due to the difficulty of gathering event-based annotated videos, we leverage an event camera simulator to create the neuromorphic counterpart of an existing RGB dataset. We demonstrate that not only training models on simulated data can still yield state-of-the-art results in valence-arousal estimation, but also that our trained models can be directly applied to real data without further training to address the downstream task of emotion recognition. In the paper we propose several alternative models to solve the task, both frame-based and video-based.