![AI4Media Methodology in a nutshell](/sites/default/files/styles/16_9_100/public/2024-05/AI4Media_Methodology-dark_vf.png?itok=W_Z40z4h)
![AIIA LABORATORY](/sites/default/files/2024-05/aiia-logo_0.png)
AI Science and Engineering: Societal and Environmental Impact
Is “AI Science and Engineering” an un upcoming scientific discipline that can fuse AI, brain and mind studies and social engineering?
A Centre of Excellence delivering next generation AI Research and Training at the service of Media, Society and Democracy.
Motivated by the challenges, risks and opportunities that the wide use of AI brings to media, society and politics, AI4Media aspires to become a centre of excellence and a wide network of researchers across Europe and beyond, with a focus on delivering the next generation of core AI advances to serve the key sector of Media, to make sure that the European values of ethical and trustworthy AI are embedded in future AI deployments, and to reimagine AI as a crucial beneficial enabling technology in the service of Society and Media.
The AI4Media consortium, comprising 30 leading partners in the areas of AI and media (9 universities, 9 research centres, and 12 industrial partners) and 35 associate members, will establish the networking infrastructure to bring together the currently fragmented European AI landscape in the field of media, and foster deeper and long-running interactions between academia and industry, including Digital Innovation Hubs. It will also shape a research agenda for media AI research, and implement research and innovation both with respect to cutting-edge technologies at the core of AI research, and within specific fields of media-related AI. AI4Media will provide a targeted funding framework through open calls, to speed up the uptake of innovations developed within the network. A PhD programme will further enhance links to the industry and the fostering and exchange of talent, while providing motivation to prevent brain drain, and a set of use cases will be developed by the network to demonstrate the impact of the achieved advances in the media sector. The Excellence Centre that is established during the AI4Media project, and the ecosystem that will grow around it, will provide a long-term basis for the support of AI excellence in Europe, long after the project ends, with the aim of ensuring that Ethical AI guided by European values assumes a global leading role in the field of Media.
Is “AI Science and Engineering” an un upcoming scientific discipline that can fuse AI, brain and mind studies and social engineering?
This lecture overviews the relation between AI and medical imaging and diagnosis.
An experimentation framework that assesses how well graph neural networks (GNN) can minimize various attributed graph functions on the node domain.
MAD-TSC is a multilingual aligned dataset for target-dependent sentiment classification (TSC) on the news domain.
Transfer-learning-based method addressing exemplar-free class-incremental learning
FaVCI2D is a face verification dataset including demographically-diversified faces and challenging negative faces.
The dataset enables the open evaluation of photographic profile rating and ranking algorithms that can provide users with privacy-related feedback.
Implementation of different class-incremental methods
AdvisIL recommends appropriate algorithm-backbone architecture combinations for a user-provided class-incremental learning scenario.
Method that provides privacy-related feedback for photographic user profiles
AI Consultant and Researcher Bobby Bahov
The repository contains the python code for the manifold mixing model soup algorithm as proposed in the paper at https://arxiv.org/abs/2309.08610.
This is a component which is able to detect shot boundaries, the sampling structure and dynamic keyframes in a videos at a speed of four times faster than real-time.
MIDI-to-Audio piano synthesizer based on DDSP.
This model detects upscaled 4k videos and identifies the upscaling model used.
The dataset contains 200 4K video sequences for each one of six deep-learning-based super-resolution methods. They correspond to the original 200 videos in BVI-DVC (https://fan-aaron-zhang.github.io/BVI-DVC/). The 1080p versions of these videos have been ...
Image Auto Tagging technology enables automatic assignment of relevant tags or keywords to vast collections of images and videos.
Bernhard C. Geiger (Key Researcher at Know-Center GmbH, Austria)
A framework for evaluating LLM on iterative game content refinement
Dataset of 4D dynamic sequences of 3D faces with varying facial expressions
d-Simplex classifiers achieve stationary, compatible features, enabling seamless model updates in retrieval systems.
A novel dataset of dynamic sequences of 3D face models, where a combination of synthetic and real identities exhibit an unprecedented variety of 4D facial expressions, with variations that include the classical neutral-apex transition, but generalize to e...
Using stationary representations, CoReS trains models to obtain compatible representations, eliminating costly re-indexing in retrieval systems during upgrades.
Mitigating forgetting in continual representation learning using contrastive supervised distillation.
Using fixed classifiers derived from regular polytopes to enhance neural network efficiency and accuracy by generating stationary, maximally-separated feature representations.
NEFER is composed of paired RGB and event videos representing human faces labeled with the respective emotions and also annotated with face bounding boxes and facial landmarks.
We propose a two-stage learning baseline with a learnable weight scaling layer for reducing the bias caused by long-tailed distribution in LT-CIL and which in turn also improves the performance of conventional CIL due to the limited exemplars.
We propose a more realistic, physics-based color data augmentation - which we call Planckian Jitter.
Elastic Feature Consolidation (EFC), exploits a tractable second-order approximation of feature drift based on an Empirical Feature Matrix (EFM).
Synthetic Social Agents (SSA) is intended to be an oversimplification of real social behaviors, yet offers a challenging shift of attention from individual motion to social forces.
Neural network based on an end-to-end trainable working memory, which acts as an external storage where information about each agent can be continuously written, updated and recalled
Architecture and GAN-based training procedure for obtaining a fast neural network which enable better bitrate performances respect to the H.265 codec for the same quality, or better quality at the same bitrate.
Nicola Messina, Giovanni Puccetti (CNR) Roberto Gallotta (University of Malta)
Mathias Felipe de Lima Santos (Ph.D.), Macquarie University, Sydney
AI4Media is excited to announce the release of a series of booklets featuring the key technological and research highlights from the AI4Media project. These four comprehensive booklets aim to advance the next generation of core AI research for the media i...
AI4Media has recently launched a series of seven demo videos that showcase the groundbreaking achievements of AI4Media’s use cases. These videos highlight the strong collaboration between AI researchers and media industry professionals across Europe, addr...