INVITED TALK 1

TITLE:

Read and reason: the role of text in semantic image interpretation.

SPEAKER:

Prof. Ernest Valveny
Dept. Ciències Computació - Computer Vision Center
Universitat Autònoma de Barcelona

ABSTRACT:

Textual content in human environments conveys important high-level semantic information that is not available in any other form in the scene. Interpreting written information in human environments is necessary for performing most everyday tasks like making a purchase, using public transportation, finding a place in the city, etc. Therefore, being able to recognize textual information in images is essential for many high-level reasoning tasks on images. With recent advances in machine learning using deep neural networks, text detection and recognition methods have reached appealing results in complex real life scenarios. In this talk we will review these recent developments in text detection and recognition and we will explore how recognized scene text can be leveraged and combined with visual information in order to address several image semantic interpretation tasks, such as classification, retrieval, captioning or question answering.

INVITED TALK 2

TITLE:

Competency model: from research to innovation.

SPEAKER:

Prof. Virginia Larraz and Prof. Cèlia Baró
Grup de recerca interdisciplinari en educació
Universitat d’Andorra

ABSTRACT:

From the University of Andorra, we will show how we designed our education model. We started rethinking the current study programmes inspired by the European directives in higher education, but also by the Council of Europe in the fields of language teaching and democratic culture. Then, we moved on to the design phase and redefined competences, defined new learning outcomes, and built a new methodology fully based on competences. It’s important to note that the research groups on education and languages have been leading the design of this new and fully competency-based methodology. Finally, we implemented the new model with a process of continuous improvement.