Mood as a Contextual Cue for Improved Emotion Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Narayana, Soujanya, Radwan, Ibrahim, Subramanian, Ramanathan, Goecke, Roland
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911776287752192
author Narayana, Soujanya
Radwan, Ibrahim
Subramanian, Ramanathan
Goecke, Roland
author_facet Narayana, Soujanya
Radwan, Ibrahim
Subramanian, Ramanathan
Goecke, Roland
contents Psychological studies observe that emotions are rarely expressed in isolation and are typically influenced by the surrounding context. While recent studies effectively harness uni- and multimodal cues for emotion inference, hardly any study has considered the effect of long-term affect, or \emph{mood}, on short-term \emph{emotion} inference. This study (a) proposes time-continuous \emph{valence} prediction from videos, fusing multimodal cues including \emph{mood} and \emph{emotion-change} ($Δ$) labels, (b) serially integrates spatial and channel attention for improved inference, and (c) demonstrates algorithmic generalisability with experiments on the \emph{EMMA} and \emph{AffWild2} datasets. Empirical results affirm that utilising mood labels is highly beneficial for dynamic valence prediction. Comparing \emph{unimodal} (training only with mood labels) vs \emph{multimodal} (training with mood and $Δ$ labels) results, inference performance improves for the latter, conveying that both long and short-term contextual cues are critical for time-continuous emotion inference.
format Preprint
id arxiv_https___arxiv_org_abs_2402_08413
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mood as a Contextual Cue for Improved Emotion Inference
Narayana, Soujanya
Radwan, Ibrahim
Subramanian, Ramanathan
Goecke, Roland
Human-Computer Interaction
Psychological studies observe that emotions are rarely expressed in isolation and are typically influenced by the surrounding context. While recent studies effectively harness uni- and multimodal cues for emotion inference, hardly any study has considered the effect of long-term affect, or \emph{mood}, on short-term \emph{emotion} inference. This study (a) proposes time-continuous \emph{valence} prediction from videos, fusing multimodal cues including \emph{mood} and \emph{emotion-change} ($Δ$) labels, (b) serially integrates spatial and channel attention for improved inference, and (c) demonstrates algorithmic generalisability with experiments on the \emph{EMMA} and \emph{AffWild2} datasets. Empirical results affirm that utilising mood labels is highly beneficial for dynamic valence prediction. Comparing \emph{unimodal} (training only with mood labels) vs \emph{multimodal} (training with mood and $Δ$ labels) results, inference performance improves for the latter, conveying that both long and short-term contextual cues are critical for time-continuous emotion inference.
title Mood as a Contextual Cue for Improved Emotion Inference
topic Human-Computer Interaction
url https://arxiv.org/abs/2402.08413