Efficient facial feature learning with wide ensemble-based convolutional neural networks
Ensemble methods, traditionally built with independently trained de-correlated models, have
proven to be efficient methods for reducing the remaining residual generalization error …
proven to be efficient methods for reducing the remaining residual generalization error …
Emotional speech-driven animation with content-emotion disentanglement
To be widely adopted, 3D facial avatars must be animated easily, realistically, and directly
from speech signals. While the best recent methods generate 3D animations that are …
from speech signals. While the best recent methods generate 3D animations that are …
Generative adversarial networks in human emotion synthesis: A review
N Hajarolasvadi, MA Ramirez, W Beccaro… - IEEE …, 2020 - ieeexplore.ieee.org
Deep generative models have become an emerging topic in various research areas like
computer vision and signal processing. These models allow synthesizing realistic data …
computer vision and signal processing. These models allow synthesizing realistic data …
Continual learning for affective robotics: Why, what and how?
Creating and sustaining closed-loop dynamic and social interactions with humans require
robots to continually adapt towards their users' behaviours, their affective states and moods …
robots to continually adapt towards their users' behaviours, their affective states and moods …
The facechannel: a fast and furious deep neural network for facial expression recognition
Current state-of-the-art models for automatic facial expression recognition (FER) are based
on very deep neural networks that are effective but rather expensive to train. Given the …
on very deep neural networks that are effective but rather expensive to train. Given the …
Neural Emotion Director: Speech-preserving semantic control of facial expressions in" in-the-wild" videos
FP Papantoniou, PP Filntisis… - Proceedings of the …, 2022 - openaccess.thecvf.com
In this paper, we introduce a novel deep learning method for photo-realistic manipulation of
the emotional state of actors in" in-the-wild" videos. The proposed method is based on a …
the emotional state of actors in" in-the-wild" videos. The proposed method is based on a …
Continual learning for affective robotics: A proof of concept for wellbeing
Sustaining real-world human-robot interactions re-quires robots to be sensitive to human
behavioural idiosyn-crasies and adapt their perception and behaviour models to cater to …
behavioural idiosyn-crasies and adapt their perception and behaviour models to cater to …
Deep learning-based approach for continuous affect prediction from facial expression images in valence-arousal space
Facial emotion recognition has attracted extensive attention from the affective computing
community and several approaches have been proposed, mainly providing classification of …
community and several approaches have been proposed, mainly providing classification of …
Deep multi-task learning for facial expression recognition and synthesis based on selective feature sharing
Multi-task learning is an effective learning strategy for deep-learning-based facial
expression recognition tasks. However, most existing methods take into limited …
expression recognition tasks. However, most existing methods take into limited …
Large-scale facial expression recognition using dual-domain affect fusion for noisy labels
Building models for human facial expression recognition (FER) is made difficult by
subjective, ambiguous and noisy annotations. This is especially true when assigning a …
subjective, ambiguous and noisy annotations. This is especially true when assigning a …