This website uses cookies to ensure you get the best experience. By clicking or navigating the site you agree to allow our collection of information through cookies. More info

Day 1: Understanding the past through parallels with the present 

  • 9:00-9:15 : Introduction to the general issue of describing cultural heritage images: what is done, and what is used for?
  • 9:15-10:00: AI-powered semantic labelling of image datasets- formats, target concepts, challenges and description of TimeMatrix and its purpose
  • 10:00-10:30: Training data in image datasets - images and metadata, challenges
  • 10:30-10:40: Break
  • 10:40-11:00: Present state-of-the-art caption generators and their limitations when dealing with anachronic images
  • 11:00-11:30: Transfer learning to describe cultural heritage images as they differ from the present way of life - anachronisms, evolution of concepts through time, minorities, symbols
  • 11:30-12:00:Ethical issues when describing works of art according to their time context

Day 2. Technical implementation of the TimeMatrix

  • 9:00-9:15: Filtering anachronic classes
  • 9:15-9:45: efining new visual classes and visual relations. For  cultural and  iconographic symbols
  • 9:45-10:15: Refining the identification of classes and visual relations according to time context
  • 10:15-10:30: Deep Learning implementation of anachronism correction and class refinement
  • 10:30-10:40: Break
  • 10:40-11:00: Current state of SGoaB
  • 11:00-11:30: Class features and Deep Learning implementation
  • 11:30-12:00: Discussion of anachronic correction and class refinement examples (demo)


The Saint George on a Bike project aims to improve the quality and quantity of open metadata associated with imagery from European cultural heritage. It especially aims to address the challenge of providing Artificial Intelligence with insights into culture, symbols and traditions. 

This webinar is aimed at academic researchers in data mining and data science who are interested in art and culture. It demonstrates results from the project and showcases the potential of adapting automatically produced descriptions of paintings to the time period when they were created. Participants are introduced to what we call the ‘time machine effect’, which consists of the objects of an image being transformed via deep learning methods to similar concepts that are more appropriate to another time period. The technical challenges and current solutions are discussed. At the end of the webinar, a demo shows the correction of anachronisms and class refinement examples.

This webinar took place over two days from 9 - 10 September 2020.


  • Maria Cristina Marinescu (CASE Department, Barcelona Supercomputing Center)

  • Joaquim More Lopez (CASE Department, Barcelona Supercomputing Center)

  • Artem Reshetnikov (CASE Department, Barcelona Supercomputing Center)

  • Albin Larsson (Europeana)