Product Reviews Dataset
This data set comprises a labelled training set used in the experimentation of the paper "Binary Quantification and Dataset Shift: An Experimental Investigation".
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.
This data set comprises a labelled training set used in the experimentation of the paper "Binary Quantification and Dataset Shift: An Experimental Investigation".
Word-Class Embeddings (WCEs) are a form of supervised embeddings specially suited for multiclass text classification. WCEs are meant to be used as extensions (i.e., by concatenation) to pre-trained embeddings (e.g., GloVe or word2vec) embeddings in order ...
This data set comprises a labeled training set, validation samples, and testing samples for ordinal quantification. It appears in our research paper "Ordinal Quantification Through Regularization", which we have published at ECML-PKDD 2022.
The aim of the LeQua 2022 dataset is to allow the comparative evaluation of methods for “learning to quantify” in textual datasets, i.e., methods for training predictors of the relative frequencies of the classes of interest in sets of unlabelled textual ...
ql4facct is a software for replicating experiments concerning the evaluation of estimators of classifier "fairness".
Datasets of the LeQua 2024 Learning to Quantify Data Challenge
An open-source LLaMa2 language model of 7b parameters fine-tuned (using as base model NousResearch/Nous-Hermes-llama-2-7b) to follow instructions in italian.
This model analyses the input text and provides an answer whether in the text there is a change of topic or not (resp. TOPPICCHANGE, SAMETOPIC).
To boost interpretability with concept vectors, a reverse engineering approach automates concept identification by analyzing the latent space of deep neural networks using Singular Value Decomposition. This framework combines factorization, latent space c...
This lecture explores various transformer-based approaches that have emerged as powerful alternatives of Convolutional Neural Networks (CNNs) in Computer Vision.
AI is a rapidly emerging field that has opened up new vistas of innovation and creativity. From intelligent systems to self-driving cars, AI has transformed the way we live and work. While AI is often studied as a subfield of computer science, it has grow...
This short course on Cloud/Edge Computing for Deep Learning and Big Data Analytics provides a comprehensive overview and detailed presentation of advanced technologies utilized in distributed computational systems. Distributed computing plays a critical r...
This short course on Cloud/Edge Computing for Deep Learning and Big Data Analytics provides a comprehensive overview and detailed presentation of advanced technologies utilized in distributed computational systems. Distributed computing plays a critical r...
This short course on Cloud/Edge Computing for Deep Learning and Big Data Analytics provides a comprehensive overview and detailed presentation of advanced technologies utilized in distributed computational systems. Distributed computing plays a critical r...
This short course on Cloud/Edge Computing for Deep Learning and Big Data Analytics provides a comprehensive overview and detailed presentation of advanced technologies utilized in distributed computational systems. Distributed computing plays a critical r...
This short course on Cloud/Edge Computing for Deep Learning and Big Data Analytics provides a comprehensive overview and detailed presentation of advanced technologies utilized in distributed computational systems. Distributed computing plays a critical r...
This short course on Cloud/Edge Computing for Deep Learning and Big Data Analytics provides a comprehensive overview and detailed presentation of advanced technologies utilized in distributed computational systems. Distributed computing plays a critical r...
JECT-CLONE is an AI-powered service that generates personalized morning news briefings for journalists and editors. It applies computational creativity algorithms to JECT.AI's semantic news index of over 25 million articles to recommend novel and relevant...
Provides a framework for learning text-driven generative paths in pre-trained GANs.
Provides a framework for anonymizing faces in public datasets using pre-trained GANs.
Provides a framework for discovering non-linear interpretable paths in pre-trained GAN latent spaces.
Provides a Neural Face Reenactment framework by leveraging the expressiveness of the StyleGAN2’s style space.
Provides a framework for the problem of Neural Face Reenactment using Generative Adversarial Networks (GANs).
Provides a video similarity learning approach using self-supervision.
Provides a framework for addressing the problem of computationally efficient content-based video retrieval in large-scale datasets.
Provides a framework for finding interpretable directions in the latent space of convolutional GANs.
A framework aiming to improve generalization performance and mitigate overfitting in deep learning methodologies in automated human affect and mental state estimation by introducing a novel relational loss for multilabel regression and ordinal problems, a...
A robust and efficient training framework tackling with dataset with noisy labels.
A self-supervised learning method aiming to alleviate the inherent false-negative problem in contrastive learning framework.
A masked contrastive learning framework for learning meaningful fine-grained representations with coarse-labeled dataset.
A method for controlling diversity between clusterings in deep clustering frameworks.
To celebrate four years of building excellence of AI research and foresighting the impact of the European Networks of Excellence Centres in AI and Robotics (AI NoEs), the Fourth Community Workshop 2024 aims to provide a forum for sharing ideas and best pr...
Speakers are AI4Media researchers Anna Schjøtt Hansen, Noémie Krack, and Lidia Dutkiewicz. Anna Schjøtt Hansen is a technological anthropologist and PhD Candidate at the Media Studies Department at the University of Amsterdam. Noémie Krack is a researcher...