Video Representation Learning for Conversational Facial Expression Recognition Guided by Multiple View Reconstruction

Conversational facial expression recognition entails challenges such as handling of facial dynamics, small available datasets, low-intensity and fine-grained emotional expressions and extreme face angle. Towards addressing these challenges, we propose the Masking Action Units and Reconstructing multiple Angles (MAURA) pre-training. MAURA is an efficient self-supervised method that permits the use of small datasets, while preserving end-to-end conversational facial expression recognition with ...

MVP: Multimodal Emotion Recognition Based on Video and Physiological Signals

Human emotions entail a complex set of behavioral, physiological and cognitive changes. Current state-of-the-art models fuse the behavioral and physiological components using classic machine learning, rather than recent deep learning techniques. We propose to fill this gap, designing the Multimodal for Video and Physio (MVP) architecture, streamlined to fuse video and physiological signals. Differently then others approaches, MVP exploits the benefits of attention to enable the use of long in...

Challenging Behaviors in Children with Nonverbal Autism: A Questionnaire to Guide the Design of a Wearable Device for Biomarker Recording

Highlights: Approximately 25% of individuals affected with ASD exhibit severe language impairments and are more likely to have challenging behavioral issues. Recent research focuses on early detection and prevention of crises by utilizing biomarkers measuring stress signals before the onset of the crisis. Regarding design requirements, the trunk appears to be the preferred location for wearable devices in this population. The arm and wrist can be an alternative with encouraging results. These...

Intelligenza artificiale e responsabilità civile