Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers

MB Akçay, K Oğuz - Speech Communication, 2020 - Elsevier
Speech is the most natural way of expressing ourselves as humans. It is only natural then to
extend this communication medium to computer applications. We define speech emotion …

Emoca: Emotion driven monocular face capture and animation

R Daněček, MJ Black, T Bolkart - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
As 3D facial avatars become more widely used for communication, it is critical that they
faithfully convey emotion. Unfortunately, the best recent methods that regress parametric 3D …

Distribution matching for heterogeneous multi-task learning: a large-scale face study

D Kollias, V Sharmanska, S Zafeiriou - arxiv preprint arxiv:2105.03790, 2021 - arxiv.org
Multi-Task Learning has emerged as a methodology in which multiple tasks are jointly
learned by a shared learning algorithm, such as a DNN. MTL is based on the assumption …

Affect analysis in-the-wild: Valence-arousal, expressions, action units and a unified framework

D Kollias, S Zafeiriou - arxiv preprint arxiv:2103.15792, 2021 - arxiv.org
Affect recognition based on subjects' facial expressions has been a topic of major research
in the attempt to generate machines that can understand the way subjects feel, act and react …

Macro-and micro-expressions facial datasets: A survey

H Guerdelli, C Ferrari, W Barhoumi, H Ghazouani… - Sensors, 2022 - mdpi.com
Automatic facial expression recognition is essential for many potential applications. Thus,
having a clear overview on existing datasets that have been investigated within the …

Expression, affect, action unit recognition: Aff-wild2, multi-task learning and arcface

D Kollias, S Zafeiriou - arxiv preprint arxiv:1910.04855, 2019 - arxiv.org
Affective computing has been largely limited in terms of available data resources. The need
to collect and annotate diverse in-the-wild datasets has become apparent with the rise of …

Estimation of continuous valence and arousal levels from faces in naturalistic conditions

A Toisoul, J Kossaifi, A Bulat, G Tzimiropoulos… - Nature Machine …, 2021 - nature.com
Facial affect analysis aims to create new types of human–computer interactions by enabling
computers to better understand a person's emotional state in order to provide ad hoc help …

Ferv39k: A large-scale multi-scene dataset for facial expression recognition in videos

Y Wang, Y Sun, Y Huang, Z Liu… - Proceedings of the …, 2022 - openaccess.thecvf.com
Current benchmarks for facial expression recognition (FER) mainly focus on static images,
while there are limited datasets for FER in videos. It is still ambiguous to evaluate whether …

Context-aware emotion recognition networks

J Lee, S Kim, S Kim, J Park… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Traditional techniques for emotion recognition have focused on the facial expression
analysis only, thus providing limited ability to encode context that comprehensively …

M3er: Multiplicative multimodal emotion recognition using facial, textual, and speech cues

T Mittal, U Bhattacharya, R Chandra, A Bera… - Proceedings of the AAAI …, 2020 - aaai.org
We present M3ER, a learning-based method for emotion recognition from multiple input
modalities. Our approach combines cues from multiple co-occurring modalities (such as …