Vision, Language and Reading

Welcome to the Vision, Language and Reading (VLR) research team at the Computer Vision Center in Barcelona, Spain.

The VLR research team conducts fundamental research and technology transfer at the frontier between vision, language and reading systems. We devise reading systems for text in the wild, and incorporate scene text semantics in a multitude of computer vision tasks such as captioning, visual question answering, cross-modal retrieval, fine-grained classification, etc. In parallel, we advance document understanding with a special interest in end-to-end approaches for Document Visual Question Answering.

News

• Aug 2026  VLR co-organised the workshop "Trustworthy Document Understanding: Privacy, Unlearning, Robustness, and Explainability" for ICPR 2026

• Jun 2026  2 papers accepted at ICPR 2026 “Learning Quantifiable Visual Explanations Without Ground-Truth”   and " Reading In The Dark: Low-Light Scene Text Recognition" 

• May 2026   Artemis Llabrés, Tomás Ockier, and Marc Serra Ortega led  the workshop "HPC@CVC Lessons on Scaling Up: From 1 GPU to 100s"  

• May 2026  Adrià Molina and Artemis Llabrés, with support from ELLIOT, ELLIS BCN, and IARP organized  SSDA 2026 at Vall de Núria 

• Apr 2026  Tomás Ockier, Marc Serra, Aran Oliveras, and Mateo Jure achieved 2nd place at the 11th edition of the HackUPC hackathon

• Mar 2026  Dimosthenis Karatzas, participated in the inauguration of the UniMORE AI Center in Modena, Italy 

• Jan 2026  Start of the DocVQA2026 ICDAR Competition

See more news