Displaying 10 resources
White paper White paper

Holistic framework for AI in critical network infrastructures

This document establishes the main foundations of the AI4REALNET project, in particular, the following key outcomes: - The formal specification of domain-specific use cases (UCs), replicating real-world operating scenarios involving human operators t
Category
Action and Interaction Technologies, Real-time context aware decision making, Policy, Regulation, Certificates, and Standards, Best practices in deployment, Legal framework and regulation, Recommendations towards policy changes, Reasoning and decision-making Technologies, Hybrid Decision Making, Trustworthiness, Systems, methodologies, hardware, and tools, Support tools, System architectures
Target audience
ADR Experts and Associations, Individual Citizens/Members of the Society, Policy Makers, Private Sector, Public Sector, Researchers and Academic
Source
Adra-e
Article/Books/eBooks 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.
Category
Multi-modal interaction
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Software resources 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.
Category
Multi-modal interaction, Sensing of motion and mechanical properties
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Software resources Software resources

pygrank

pygrank is an open source framework to define, run and evaluate node ranking algorithms. It provides object-oriented and extensively unit-tested algorithmic components, such as graph filters, post-processors, measures, benchmarks, and online tuning.
Category
Multi-modal interaction
Target audience
ADR Experts and Associations, Private Sector, Researchers and Academic
Source
Adra-e
Software resources Software resources

InDistill

InDistill enchances the effectiveness of the Knowledge Distillation procedure by leveraging the properties of channel pruning to both reduce the capacity gap between the models and retain the information geometry.
Category
Multi-modal interaction
Target audience
ADR Experts and Associations, Private Sector, Researchers and Academic
Source
Adra-e
Article/Books/eBooks Article/Books/eBooks

FutureNewsCorp, or how the AI Act changed the future of news

Inspired by scenario writing methods to foster discussion on the societal implications of technology and regulation, the paper develops a ‘legal fiction scenario’ to anticipate the impact of the proposed European 
Category
Legal framework and regulation
Target audience
ADR Experts and Associations, Policy Makers, Private Sector, Public Sector, Researchers and Academic
Source
Adra-e