Online Course on “Literate Models for Vision: Combining vision, language and reading”

The Computer Vision Center (CVC) organizes a short course on “Literate Models for Vision” offered through the International Artificial Intelligence Doctoral Academy (AIDA).

Written information in the world around us is a fundamental cue for a multitude of everyday tasks. From shopping at the supermarket to finding our destination in an unknown urban space, written text helps us perform many tasks that would otherwise be much more complex.

Computer vision systems on the other hand, have been practically illiterate for the first half century of their lifetime. Specific research on reading systems has been going on for decades, but the semantic information that image text conveys was not incorporated to higher-level computer vision tasks until very recently. This is gradually changing, afforded by the great success achieved in the field of scene text recognition in recent years.

Through this short interactive course, doctoral students will have a chance to reconcile with the state of the art in reading systems, especially scene text recognition, and explore how image text enables us to tackle new and exciting computer vision tasks such as fine-grained image classification, cross-modal retrieval, captioning and visual question answering.

WHEN: Monday 20 December 2021 from 10:00 to 17.00 CET

WHERE: Online

HOW TO REGISTER: https://www.i-aida.org/course/vision-and-language-reading-systems-and-multi-modal-representations/

Schedule (all times are CET):

10:00 – 11:00 Introduction and Scene Text Understanding Overview

11:00 – 12:00 Common blocks for multi-modal systems

12:00 – 13:00 Scene text for Fine Grained Image Classification and Cross-modal retrieval

13:00 – 15:00 Break

15:00 – 16:00 Scene text for Captioning and VQA

16:00 – 17:00 Demo session