Abstract: Continual Learning (CL) is a paradigm where an agent learns over time from a stream of data. In this talk, we will discuss how to exploit pretrained models in CL. First, we will talk about “continual pretraining”, a scenario where a large pretrained model is updated over time. The results show that continual pretraining … Read more
The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022, took place on 19-24 June in New Orleans and online. The Computer Vision Center contributed with the following papers: CVPR Oral. An important milestone for CVC’s history! LaTr: Layout-Aware Transformer for Scene-Text VQA, by Ali Furkan Biten, Ron Litman, Yusheng Xie, Srikar Appalaraju, and … Read more
El Centre de Visió per Computador (CVC) i Intel Intelligent Systems Lab han estat guardonats amb el Premi Nacional al Partenariat Publicoprivat en R+I pel desenvolupament conjunt del simulador de codi obert sense ànim de lucre CARLA, per entrenar i validar sistemes de conducció autònoma. El premi s’ha lliurat el 7 de juny de 2022 … Read more
The 15th IAPR International Workshop on Document Analysis Systems, DAS 2022, took place on 22-25 May in La Rochelle, France and online. CVC contributed with the papers: A Multilingual Approach to Scene Text Visual Question Answering, by Josep Brugués i Pujolràs, Lluís Gómez i Bigordà, and Dimosthenis Karatzas Read while you drive – multilingual text tracking on the road, by … Read more
The Winter Conference on Applications of Computer Vision, WACV 2022, took place on 4-8 January. CVC contributed with several papers: Class-Balanced Active Learning for Image Classification (Javad Zolfaghari Bengar, Joost van de Weijer, Laura Lopez Fuentes, Bogdan Raducanu) One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition (Mohamed Ali Souibgui, Ali Furkan Biten, Sounak … Read more
CVC is participating in the 3rd Deep Learning Barcelona Symposium (DLBCN) as a key sponsor and is contributing with several CVC researchers. CVC is present on the organizing committee as well as on talks and posters. This DLBCN edition expands its categories by adding a life sciences area as it is key in the current artificial intelligence … Read more
Researchers From The Eurecat Technology Centre, The CVC And The University Of Barcelona Have Developed An Automated System That Taps Into Deep Learning Technology To Detect Lesions Caused By Covid-19 By Reading Computed Tomography (CT) Chest Images. The study, conducted by researchers Giuseppe Pezzano, Vicent Ribas, Petia Radeva and Oliver Díaz, was recently published in the … Read more
The Computer Vision Center (CVC) Is One Of The Research & Industry Members Of The Recently Launched International AI Doctoral Academy (AIDA) Which Is Aimed To Attract PhD And Postdoc Talents In Europe Through Educational And Training Activities In The Field Of Artificial Intelligence. AIDA is the first academy of its kind in Europe and internationally. Coordinated by … Read more
Researchers From The Computer Vision Center And The Landscape Archaeology Research Group (GIAP) Of The Catalan Institute Of Classical Archaeology (ICAC) Have Developed A Hybrid Algorithm That Combines Deep Learning And Machine Learning To Improve The Automatic Detection Of Archaeological Tumuli Avoiding The Inclusion Of Most False Positives. Archaeological tumuli are one of the most common types of archaeological … Read more
Source: Department Of The Vice-Presidency, Digital Policies And Territory – Generalitat de Catalunya The CVC researcher, Dr. Alicia Fornés received the Dona TIC award in the Academic/Researcher category. The awards ceremony, which is celebrated annually in commemoration of the Ada Lovelace Day, was held on October 13th at CosmoCaixa Barcelona and broadcasted on Youtube. The Dona … Read more
