Ensemble methods, traditionally built with independently trained de-correlated models, have
proven to be efficient methods for reducing the remaining residual generalization error …

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 …

Deep generative models have become an emerging topic in various research areas like
computer vision and signal processing. These models allow synthesizing realistic data …

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 …

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 …

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 …

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 …

Facial emotion recognition has attracted extensive attention from the affective computing
community and several approaches have been proposed, mainly providing classification of …

Multi-task learning is an effective learning strategy for deep-learning-based facial
expression recognition tasks. However, most existing methods take into limited …

Building models for human facial expression recognition (FER) is made difficult by
subjective, ambiguous and noisy annotations. This is especially true when assigning a …