Clip retrieval works by converting the text query to a CLIP embedding , then using that embedding to query a knn index of clip image embedddings
The Digital Curator application allows you to explore the art collections of Central European museums and search for artworks based on specific motifs.
Users of the application can build their combination of objects and reveal how often the subject has occurred across the centuries, view graphics, drawings, or paintings that represent it in different epochs, and compare data with other themes.
The Digital Curator offers a quantitative view of cultural history based on the frequency of symbols and iconographic themes in many artifacts, not on a detailed observation of individual items. This distant viewing can be especially useful if our interest is aimed at exploring a genre, rather than a specific work, to understand the overall social conditions, rather than the life of a particular artist, or to interpret the overall political situation, rather than the views of the selected author. Exploring big cultural-historical data may bring new insights into abstract social phenomena such as cultural and economic influence, canon issues, the relationship between the center and the periphery, or the functioning of the art market. It can also help us better observe the migration of motifs and their takeover across centuries and distant regions.
The Digital Curator database now contains 196 116 works from the collections of 91 museums from Austria, Bavaria, the Czech Republic, and Slovakia. 71 410 of these works are available under an open license, so it is possible to view them online. Other works are used only as a basis for statistics, presenting the frequency of occurrence of motifs. The AI library for machine learning TensorFlow and the computer service Google Cloud including the tool Google Cloud Vision were used for the automatic detection of the depicted motifs. Data search and storage is performed using the ElasticSearch database and the operation of the application is provided by the Google App Engine service.
Implementation was carried out with the kind support of the UMPRUM, Academy of Arts, Architecture and Design in Prague , the Ministry of Education of the Czech Republic the Slovak National Gallery, and the BlueGhost digital agency. Thanks also go to many museums that made it possible to use their digitized collections, and to Richard Prajer, Radim Hašek, and Eva Škvárová who helped with the development of the application and the preparation of the database.
The project was designed by Lukas Pilka in 2019-22.
All The Tropes is a community-edited wiki website dedicated to discussing Creators, Works, and Tropes -- the people, projects and patterns of creative writing in all kinds of entertainment: television, literature, movies, video games, and more.
The Collections database consists of entries for more than 480,000 works in the Musée du Louvre and Musée National Eugène-Delacroix. Updated on a daily basis, it is the result of the continuous research and documentation efforts carried out by teams of experts from both museums.
This database* is an ongoing project to aggregate tools and resources for artists, engineers, curators & researchers interested in incorporating machine learning (ML) and other forms of artificial intelligence (AI) into their practice. Resources in the database come from our partners and network; tools cover a broad spectrum of possibilities presented by the current advances in ML like enabling users to generate images from their own data, create interactive artworks, draft texts or recognise objects. Most of the tools require some coding skills, however, we’ve noted ones that don’t. Beginners are encouraged to turn to RunwayML or entries tagged as courses.
*This database isn’t comprehensive—it's a growing collection of research commissioned & collected by the Creative AI Lab. The latest tools were selected by Luba Elliott. Check back for new entries.
Via : https://docs.google.com/document/d/1TkusCE5mS4tuTYoBwaTV4aJKdSVsf9jFKsGJCx8M05c/edit
The new Collection online
From Dürer to the Rosetta Stone, explore 4.5 million objects.
The database is based on the British Museum's collection management tool, where we record what we know about our collection. It was created for the Museum to store information for its own use, and is therefore full of specialised terms, abbreviations and shorthand.
The Museum has been working on the database for more than 40 years and, even with more than two million records, we've only catalogued about half of the collection. We're adding and improving records every day but, even so, an object record may not have been checked. In many cases, the most recent research has not yet been added. There will be mistakes and omissions, but the Museum chooses to publish the data, rather than hold it until it is 'finished', as there will always be new information about an object. Only personal and sensitive information has been withheld.
An anatomical case study of the Amazon echo as a artificial intelligence system made of human labor
It took 200,000 years for our human population to reach 1 billion—and only 200 years to reach 7 billion. But growth has begun slowing, as women have fewer babies on average. When will our global population peak? And how can we minimize our impact on Earth’s resources, even as we approach 11 billion?
Visualization of the market place, by size and colors
Almost 216 million people, or 3.15% of the world population, live outside their countries.
Sharing Architectural Knowledge
A massive central data source and a handy way to graphically compare nations.
When you enter phrases into the Google Books Ngram Viewer, it displays a graph showing how those phrases have occurred in a corpus of books.
The Freesound Project is a collaborative database of Creative Commons licensed sounds. Freesound focusses only on sound, not songs.
Jinni is a Taste Engine. We look at film through the lens of what makes you love or hate anything you watch. With a Taste Engine, you don't search by what you're looking for, you search by what you like.
Publish your Open Call for participants to Wooloo's growing network of more than 13.000 art professionals in 140 countries.
All the blogs with cool data visualization eye candy
MACE is a pan-european initiative to interconnect and disseminate digital information about architecture.
Personas shows you how the Internet sees you. An installation by Aaron Zinman.
Below are 50 of the best data visualizations and tools for creating your own visualizations out there, covering everything from Digg activity to network connectivity to what s currently happening on Twitter.
Contemporary art and culture
The international artist database
ANOPTIQUE developpe et accompagne la mise en contexte cooperative de logiciels libres favorisant les pratiques de l' Intelligence Collective, en particulier dans le domaine de la visualisation d'information.
The 0xdb is a rather unique kind of movie database. It uses a variety of publicly accessible resources, like search engines and file-sharing networks, to automatically collect information about, and actual images and sounds.
unreal visualisation is used for real world interference. the telezone project combines physical world behaviour with internet coordination and visualisation. going beyond this means to create an xperience, where visual information transfer was. what else
This site is designed to find objects, patches, applications, etc... from Max universe (Max/MSP, Jitter,...). Just as an indication, some objects are listed to be available on Pure Data as well.
Created in 1975, Heure Exquise ! is a non-profit association specialized in the promotion of video art and video creation.
An on line gallery and database of video art
Works using digital pictures and technologies
Bienvenue dans la Banque Digitale. Cette banque de donnees a ete concue et enrichie par Valerie Morignat afin de constituer une base de ressources libre d'acces pour les chercheurs, les createurs, etudiants et publics concernes par la creation
Database of film and cinema
Collaborative music database