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

Sep 2023 Dimosthenis Karatzas gave an invited talk at the DocILE lab at CLEF 2023

Jul 2023 Our NeurIPS 2023 competition on Privacy Preserving Federated Learning Document VQA is now on!

Jun 2023 A new postdoc joined the group - welcome Lei Kang!

Arp 2023 3 papers accepted to ICDAR 23

Apr 2023 A new postdoc joined the group - welcome Mohamed Souibgui!

Mar 2023 The creation of the ELLIS Unit Barcelona was approved! Dimosthenis Karatzas will co-direct the new unit along Prof Carme Torras

Jan 2022 A new PhD student joined the group - welcome Qi Dong!

Nov 2022 2 papers accepted to AAAI 23

Nov 2020 Andres Mafla successfully defended his PhD thesis. Congratulations!

Nov 2020 Ali Biten successfully defended his PhD thesis. Congratulations!

Nov 2022 Dimosthenis Karatzas was ranked at the top 2% of the world´s most cited AI researchers 2021 based on Scopus standardized citation indicators

Oct 2022 VLR co-organised the "Text in Everything" workshop at ECCV 2022

Sep 2022 VLR participates in the new European Lighthouse on Safe and Secure AI (ELSA)

Sep 2022 Dimosthenis Karatzas was awarded an Amazon Research Award

June 2022 Ali Biten's research was featured in the CVPR Daily magazine

June 2022 Andres Mafla recognised as outstanding reviewer of CVPR 22

Feb 2022 1 paper accepted to CVPR 2022

Oct 2021 4 papers accepted to WACV 22

Oct 2021 Dimosthenis Karatzas was ranked at the top 2% of the world´s most cited AI researchers 2020 based on Scopus standardized citation indicators

Sep 2021 VLR co-organised the "Document Visual Question Answering" workshop at ICDAR 2021

May 2021 2 papers accepted to ICDAR 21

Dec 2020 Anguelos Nicolau successfully defended his PhD thesis. Congratulations!

Oct 2020 3 papers accepted to WACV 21

Oct 2020 Dimosthenis Karatzaswas ranked at the top 2% of the world´s most cited AI researchers 2019 based on Scopus standardized citation indicators

Dec 2020 Raul Gomez successfully defended his PhD thesis. Congratulations!

July 2020 1 paper accepted to ACM MM 20

July 2020 1 paper accepted to ECCV 20

June 2020 VLR co-organised the "Text and Documents in the Deep Learning Era" workshop at CVPR 2020

Jan 2020 1 paper accepted to ICRA 20

Apr 2020 Dimosthenis Karatzas was awarded an AWS Machine Learning Research Award

Oct 2019 2 papers accepted to WACV 20

Sep 2019 VLR co-organised the "Human-Document Interaction" workshop at ICDAR 2019

July 2019 1 paper accepted to ICCV 19

May 2019 7 papers accepted to ICDAR 19

Mar 2019 VLR researchers Lluis Gomez, Marcal Rossinyol and Dimosthenis Karatzas create a new spin-off company, AllRead

Feb 2019 1 paper accepted to CVPR 19

Dec 2018 VLR co-organised the "Int. Workshop on Robust Reading" at ACCV 2018

Nov 2018 Dena Bazazian successfully defended her PhD thesis. Congratulations!

July 2018 1 paper accepted to ECCV 18

Sep 2017 VLR co-organised the "Human-Document Interaction" workshop at ICDAR 2017

Sep 2017 VLR co-organised the "Camera Based Document Analysis and Recognition" workshop at ICDAR 2017

May 2017 4 papers accepted to ICDAR 19

Feb 2017 1 paper accepted to CVPR 17

Feb 2017 Dimosthenis Karatzas and Andy Bagdanov were awarded a Google Faculty Award

Apr 2016 Lluis Gomez successfully defended his PhD thesis. Congratulations!

Sep 2018 VLR co-organised the "Robust Reading" workshop at ECCV 2018

Aug 2013 Dimosthenis Karatzas was awarded the IAPR/ICDAR Young Investigator Award