Video/Webinars
Webinar "Towards Transparent, Safe and Trustworthy AI for critical infrastructures"
This webinar focuses on the development of safe, explainable, and algorithmically transparent methods as part of the AI4REALNET project.
Video/Webinars
Webinar: Knowledge-Assisted AI Applications for Real-World Network Infrastructure
This webinar showcases how the AI4REALNET project is driving innovation in critical infrastructure through advanced AI applications.
Article/Books/eBooks
Uncertainty-Based Learning of a Lightweight Model for Multimodal Emotion Recognition
In this paper, the authors propose a lightweight neural network architecture that extracts and performs the analysis of multimodal information using the same audio and visual networks across multiple temporal segments.
Article/Books/eBooks
An Open Dataset of Synthetic Speech
This paper introduces a multilingual, multispeaker dataset composed of synthetic and natural speech, designed to foster research and benchmarking in synthetic speech detection.
Software resources
Word-Class Embeddings for Multiclass Text Classification
Code for Word-Class Embeddings (WCEs), a form of supervised embeddings especially suited for multiclass text classification.
Software resources
CO2A – Contrastive Conditional domain Alignment
A novel unsupervised domain adaptation approach for action recognition from videos, inspired by recent literature on contrastive learning.