Dual-Constrained Dynamical Neural ODEs for Ambiguity-aware Continuous Emotion Prediction

TL;DR

This paper introduces a novel dual-constrained Neural ODE framework for continuous emotion prediction that models the evolving ambiguity of emotions over time, ensuring valid distribution estimates and demonstrating promising results on a public dataset.

Contribution

It presents a new dual-constrained Neural ODE method that captures temporal emotion ambiguity and enforces distribution validity, advancing emotion modeling techniques.

Findings

Achieved promising performance on RECOLA dataset

Effectively models dynamic emotion distributions over time

Ensures validity of predicted emotion distributions

Abstract

There has been a significant focus on modelling emotion ambiguity in recent years, with advancements made in representing emotions as distributions to capture ambiguity. However, there has been comparatively less effort devoted to the consideration of temporal dependencies in emotion distributions which encodes ambiguity in perceived emotions that evolve smoothly over time. Recognizing the benefits of using constrained dynamical neural ordinary differential equations (CD-NODE) to model time series as dynamic processes, we propose an ambiguity-aware dual-constrained Neural ODE approach to model the dynamics of emotion distributions on arousal and valence. In our approach, we utilize ODEs parameterised by neural networks to estimate the distribution parameters, and we integrate additional constraints to restrict the range of the system outputs to ensure the validity of predicted distributions. We evaluated our proposed system on the publicly available RECOLA dataset and observed very promising performance across a range of evaluation metrics.