Assets

Selection of assets applied in MediaFutures projects

3D Force-Directed Graph

Web component to represent a graph data structure in a 3-dimensional space


A web component to represent a graph data structure in a 3-dimensional space using a force-directed iterative layout. Uses ThreeJS/WebGL for 3D rendering and either d3-force-3d or ngraph for the underlying physics engine.

Applied in: Edit Wars


Agora

Agora Ecosystem is a Data Science Marketplace infrastructure project from DIMA (TU- Berlin) and IAM (DFKI)


A unified data infrastructure for building ecosystems that bring together data, algorithms, models, and computational resources so that users can combine them to ease the development of novel applications.

Applied in: People Supported Intelligence


BERTopic

BERT and c-TF-IDF to create easily interpretable topics


BERTopic is a topic modeling technique that leverages transformers and c-TF-IDF to create dense clusters allowing for easily interpretable topics whilst keeping important words in the topic descriptions.

Applied in: Edit Wars


BERTTweet

Public large-scale pre-trained language model for English tweets


Open source large scale language model trained using the RoBERTa pre-training procedure. The corpus used to pre-train BERTweet consists of 850M English Tweets (16B word tokens ~ 80GB), containing 845M tweets. The code is released under the MIT License.

Applied in: Overtone


Computer-assisted recognition of denial and skepticism (CARDS)

Model for detecting and categorising misinformation about climate change


CARDS is a research project into detecting and categorising misinformation about climate change. CARDS stands for Computer Assisted Recognition of Denial and Skepticism using supervised machine learning to detect claims used to cast doubt on climate science and solutions.

Applied in: Critical Climate Machine


CountVectorizer

Python module to convert a collection of text documents to a matrix of token counts


CountVectorizer is a python module included in scikit-learn, that implements both tokenization and occurrence counting in a single class. This implementation produces a sparse representation of the counts using scipy.sparse.csr_matrix.

Applied in: Edit Wars


D3.js

Interactive visualizations


A JavaScript library for producing dynamic, interactive data visualizations in web browsers. It combines powerful visualization components and a data-driven approach to manipulate documents. It makes use of Web standards, Scalable Vector Graphics, HTML5 and CSS.

Applied in: Trolls vs Elves. I-doc


Data Ethics Canvas

Data Ethics Canvas by ODI


The Data Ethics Canvas is a tool for anyone who collects, shares or uses data. It helps identify and manage ethical issues – at the start of a project that uses data, and throughout.

Applied in: Closing the Gap – the Gokind venture


DeepFace

A Lightweight Face Recognition and Facial Attribute Analysis Library for Python


Deepface is a lightweight face recognition and facial attribute analysis (age, gender, emotion and race) framework for python. It is a hybrid face recognition framework wrapping state-of-the-art models: VGG-Face, Google FaceNet, OpenFace, Facebook DeepFace, DeepID, ArcFace, Dlib and SFace.

Applied in: Ctrl+Alt+Img


DYCI2

Creative dynamics of improvised interaction library


The DYCI2 library contains a collection of generative agents and tools for smart composition and human-machine co-improvisation. It integrates the results of the DYCI2 project and shapes a next-generation software with regard to OMax.

Applied in: Critical Climate Machine


FFmpeg

Cross-platform suite to record, convert and stream audio and video


FFmpeg is a free and open-source software project consisting of a suite of libraries and programs for handling video, audio, and other multimedia files and streams. It is widely used for format transcoding, basic editing (trimming and concatenation), video scaling, video post-production effects and standards compliance (SMPTE, ITU). It includes encoders and decoders for many audio and video file formats.

Applied in: Sock Puppet Theather


Graph Commons

Graph collaborative platform


Graph Commons is a collaborative platform for mapping, analyzing and publishing data-networks. It empowers people and organizations to transform their data into interactive maps and untangle complex relations that impact them and their communities.

Applied in: Biblio-Graph


Hugginface

Platform to share machine learning models and datasets


The Hugging Face Hub is a AI community supported by a platform that allows users to exchange pretrained datasets, models, and machine learning project demos

Applied in: Factiverse


Keras

Deep learning API based on TensorFlow


Keras is a deep learning API written in Python, running on top of the machine learning platform TensorFlow. It was developed with a focus on enabling fast experimentation.

Applied in: Synthetic Identity Speculations


LibROSA

A python package for music and audio analysis


Librosa is powerful Python library built to work with audio and perform analysis on it. It provides the building blocks necessary to create music information retrieval systems, and it is the starting point towards working with audio data at scale for a wide range of applications such as detecting voice from a person to finding personal characteristics from an audio.

Applied in: Claypot


Lightship

Software development kit for augmented reality based on Unity


Lightship is a proprietary software from Niantic that consists of a suite of tools to create innovative, real-world AR experiences that inspire movement and encourage exploration. What they call "real-world metaverse".

Applied in: OCHI


Proprietary Software

Open source alternative: Mozilla Hubs

Matplotlib

Data visualization


Comprehensive library for creating static, animated, and interactive visualizations in Python. Matplotlib is widely used for quick visualizations and to get an understanding of a dataset.

Applied in: Synthetic Identity Speculations; Sock Puppet Theather


Meta Graph API

API for reading and writing to the Meta social graph


The Graph API is the primary way for apps to read and write to the Meta social graph. All of Meta SDKs and products interact with the Graph API, which is an HTTP-based API that apps can use to programmatically query data, post new stories, manage ads, upload photos, and perform a wide variety of other tasks.

Applied in: Synthetic Identity Speculations


Mozilla Hubs

An open source platform to meet, share and collaborate together in private 3D virtual spaces


Mozilla Hubs is a virtual collaboration platform that runs in a browser. Mozilla Hubs allows to create 3D spaces and to invite others to join using a URL to bring communities together in a shared virtual space (e.g, hosting conferences, teaching a class, showcasing art, etc.)

Applied in: Time-Lapse Migration


NLTK

Natural Language Processing


NLTK is a natural language processing toolkit widely used to process text data with python programming language. With NLTK it is possible to compute text similarity, lemmatization, to remove stop words, sentiment analysis, etc. The NLTK website offers a suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing.

Applied in: People Supported Intelligence


Open Refine

Cleaning and transforming data


Free, open source power tool for working with messy data and improving it. It allows for cleaning data, transforming it from one format into another, reconciling and matching data, and extending it with web services and external data.

Applied in: Biblio-Graph


OpenCV

Open Source Computer Vision Library


OpenCV (Open Source Computer Vision Library) is an open source computer vision and machine learning software library. OpenCV was built to provide a common infrastructure for computer vision applications. OpenCV is open source and released under the Apache 2 License. It is free for commercial use.

Applied in: Doppelganger; Sock Puppet Theather


OpenLayers

A high-performance, feature-packed library for all your mapping needs


OpenLayers is a high-performance, feature-packed library for creating interactive maps on the web. It can display map tiles, vector data and markers loaded from any source on any web page. OpenLayers has been developed to further the use of geographic information of all kinds. It is completely free, Open Source JavaScript, released under the BSD 2-Clause License.

Applied in: HYPERViz


OpenPose

Real-time multi-person keypoint detection library for body, face, hands, and foot estimation


OpenPose is a real-time multi-person system to jointly detect human body, hand, facial, and foot keypoints (in total 135 keypoints) on single images. The repository comes with OpenPose training code, OpenPose foot dataset and OpenPose Unity Plugin, plus papers published in IEEE TPAMI and CVPR that help you to understand the functionalities.

Applied in: Synthetic Identity Speculations


Prodigy

An annotation tool powered by active learning


Prodigy is a scriptable annotation tool so efficient that data scientists can do the annotation themselves, enabling a new level of rapid iteration.

Applied in: Biblio-Graph


Python OSC

Python library for implementing OSC (Open Sound Control)


Python-osc implements a server and client for Open Sound Control. It allows a python access to a versatile protocol used in many musical instruments, controller hardware and control applications.

Applied in: Critical Climate Machine


PyTorch

An open source machine learning framework that accelerates the path from research prototyping to production deployment.


PyTorch is a Python package that provides two high-level features. Tensor computation (like NumPy) with strong GPU acceleration and deep neural networks built on a tape-based autograd system.

Applied in: Critical Climate Machine; Factiverse


scikit-learn

Python module for machine learning built on top of SciPy


Scikit-learn is a useful package for building machine learning models like clustering, classification, and regression models. It also provides a variety of packages for data transformation such as feature extraction, encoding, normalization etc.

Applied in: Critical Climate Machine; Sock Puppet Theather


SenseMaker®

SenseMaker® by The Cynefin Company (formerly known as Cognitive Edge)


SenseMaker® allows for large-scale capture of data into a quantitative framework where the ‘subject’ becomes their own ethnographer. SenseMaker® combines the scale of numbers with the explanatory power of narrative.

Applied in: PONTE


Proprietary Software

SimSwap

Framework for high fidelity face swapping


Open source framework for generalized and high fidelity face swapping, capable of transferring the identity of an arbitrary source face into an arbitrary target face while preserving the attributes of the target face. The tool run on Pytorch, the code is available on GitHub.

Applied in: Doppelganger


Spacy

Industrial-strength Natural Language Processing in Python


spaCy is a library for advanced Natural Language Processing in Python and Cython. spaCy comes with pretrained pipelines and supports tokenization and training for 70+ languages. It features neural network models for tagging, parsing, named entity recognition, text classification and more.

Applied in: Edit Wars; Factiverse; Overtone


StyleGAN2

Style-based GAN architecture (StyleGAN) for data-driven unconditional generative image modeling


StyleGAN2 is an improvement over StyleGAN which is based on Progressive GAN. The library and the research associated, have been developed by researchers from NVIDIA AI so the library is licensed under Nvidia Source Code License-NC.

Applied in: Doppelganger


Tableau

Visual analytics platform


A propetary analytics platform focused on business intelligence that facilitates to explore and manage data, and share insights.

Applied in: BKYNDR


Proprietary software

Open source alternative: Apache Superset; Grafana.

TensorFlow

An open source machine learning framework


TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries, and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML-powered applications.

Applied in: MUMIDIS; Synthetic Identity Speculations


Triply

Linked-data knowledge graphs


Triply aims to simplify the use of linked-data knowledge graphs in practical and large-scale applications. We focus on improving the experience of both the developer and the user for working with knowledge graphs and believe in the benefits of following open standards.

Applied in: Biblio-Graph


Tweepy

Python wrapper for the Twitter API


Python library to access the Twitter API. It accesses the Twitter REST (including Search) and Stream APIs.

Applied in: Sock Puppet Theather


Twitter API

Twitter API official documentation


Through the Twitter API it is possible to retrieve public tweets about specific topics or query terms, and to monitor the debate in real time. The documentation includes tools and libraries for dealing with the API in different programming languages, and step by step tutorials.

Applied in: Critical Climate Machine; 730 hours of violence; Trolls vs Elves. I-doc


UMAP

Uniform Manifold Approximation and Projection for Dimension Reduction


Uniform Manifold Approximation and Projection (UMAP) is a general purpose dimension reduction technique for machine learning. It can be used for visualisation similarly to t-SNE, but also for general non-linear dimension reduction.

Applied in: Edit Wars


VertexAI

Managed machine learning platform providing Google’s cloud services to deploy and maintain AI models


Vertex AI is a machine learning platform that allows one to train and deploy ML models and AI applications, and customize large language models (LLMs) for use in AI-powered applications. Vertex AI combines data engineering, data science, and ML engineering workflows, enabling teams to collaborate using a common toolset and scale applications with Google Cloud.

Applied in: Overtone


VGGFace2-HQ

Open source high resolution dataset for face swapping


VGGFace2 is a large-scale face recognition dataset. Images are downloaded from Google Image Search and have large variations in pose, age, illumination, ethnicity and profession. The dataset includes loosely-cropped faces for each identity, and meta information for each identity and each face image in the dataset. For each image, face detection and 5 estimated keypoints are provided.

Applied in: Doppelganger


vvvv

Real time video synthesis


Hybrid visual/textual live-programming environment for easy prototyping and development. It facilitates real-time video synthesis and the handling of large media environments with physical interfaces, real-time motion graphics, audio and video that can interact with many users simultaneously.

Applied in: JECT-SENSE


Contact us!

   

MediaFutures is funded by the European Union's Horizon 2020 Programme, under grant agreement number 951962. MediaFutures is a Europe-wide consortium. This website is managed on behalf of the consortium by Eurecat, whose main address is Carrer de Bilbao, 72, 08013 Barcelona (Spain).