Impact of annotation modality on label quality and model performance in the automatic assessment of laughter in-the-wild

J Vargas-Quiros, L Cabrera-Quiros… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Although laughter is known to be a multimodal signal, it is primarily annotated from audio. It
is unclear how laughter labels may differ when annotated from modalities like video, which …

An accurate real-time method to detect the smile facial expression

L Persona, F Meloni, AA Macedo - … of the 29th Brazilian Symposium on …, 2023 - dl.acm.org
The rapid advancement of technology has significantly improved our ability to interact with
electronic devices and derive meaning from this interaction. One crucial aspect of human …

Social-MAE: A Transformer-Based Multimodal Autoencoder for Face and Voice

H Bohy, M Tran, K El Haddad, T Dutoit… - 2024 IEEE 18th …, 2024 - ieeexplore.ieee.org
Human social behaviors are inherently multi-modal necessitating the development of
powerful audiovisual models for their perception. In this paper, we present Social-MAE, our …

Sensing the mood of a conversation using non-verbal cues with Deep Learning

H Bohy - 2022 10th International Conference on Affective …, 2022 - ieeexplore.ieee.org
In this project, we aim to explore the use of non-verbal cues (NVCs) in sensing
conversational mood. Our definition of conversational mood relates to how interpersonal …

Leveraging Anomaly Detection for Affective Computing Applications

S Hamieh - 2024 - theses.hal.science
Recent technological advancements have paved the way for automation in various sectors,
from education to autonomous driving, collaborative robots, and customer service. This has …