Dr. Gemma Rotger winner of Pioner Awards 2021

Dr. Gemma Rotger, CVC Alumni, has been granted the CERCA Pioneer Award 2021 for her doctoral thesis. The prize is a recognition for researchers who have presented a doctoral thesis with results that are clearly aimed at commercial exploitation.

The Pioner Awards aim to recognise those researchers working in one of the CERCA centres who have presented a doctoral thesis through which they propose to initiate or improve the development of a technology or product that may have an industrial or commercial application or might even make a significant specific contribution to the development of public policy.

One of the six winners of this year’s edition has been Dr. Gemma Rotger, former CVC PhD student, for her thesis “Lifelike Humans: Detailed Reconstruction of Expressive Human Faces”, which was developed at CVC – supervised by Dr. Felipe Lumbreras – and the Institute of Robotics and Industrial Informatics (IRI).

The jury considered that her thesis, which develops novel techniques to achieve the automatic generation of detailed and realistic faces of synthetic human characters through low-cost setups, has a direct application in the current and the future of the entertainment industry.

The work incorporates a new method to automatically describe realistic details to the characters, such as wrinkles, facial expressions or micro-expressions, without user interaction or learning data, looking for their robustness and simplicity of configuration. The proposal offers a pioneering approach, which reduces modelling costs and could revolutionize the industry by easily adapting to existing solutions currently on the market.

The Pioner Awards ceremony took place on 20 December in a virtual format on the CERCA YouTube channel.

Congratulations Gemma!

CVC participates in Deep Learning Barcelona as a key sponsor and contributes with several CVC researchers


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 technological revolution. The symposium will feature deep learning world-class leaders in Barcelona on 22 and 23 December.


Barcelona is hosting on 22 and 23 December at UPC Campus Nord the third Deep Learning Barcelona Symposium (DLBCN). Deep learning is one of the engines of the current artificial intelligence technological revolution. This has been implemented in almost all audiovisual fields, such as speech recognition by virtual assistants or photo file organizers. The trend has leaped to the field of life sciences, with applications related to new drugs development or support for medical diagnosis. For this reason, this 2021 symposium is presenting for the first time a session on applications to genomics, nutrition, detection of COVID-19 from cough, or medical imaging.

Deep Learning Barcelona Symposium aims to highlight Barcelona-developed research, bringing together top-notch researchers who are either developing their research in the city right now or had pursued part of their academic career here. The symposium presents 32 talks and 41 posters from international universities such as Stanford, MIT, or Columbia, multinational companies as Meta, Amazon, NVidia and ElementAI, and local research centers like Computer Vision Center (CVC).

CVC is participating in Deep Learning Barcelona Symposium (DLBCN) in diverse ways. It is a sponsor together with Meta AI (Facebook), UOC eHealth Center and UPC School of Telecommunications. CVC researchers Dimosthenis Karatzas (UAB-CVC), Sergio Escalera (UB-CVC) and Petia Radeva (UB-CVC) are part of the Organization Committee along with some other local institutions and companies in the field of artificial intelligence. Various talks and posters are presented by CVC scientists:









New system powered by deep learning makes it possible to detect Covid-19 lesions by analysing CT chest scans

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 journal ‘Computers in Biology and Medicine’.

The research “has enabled us to confirm the system’s efficiency as a decision support tool for healthcare professionals in screening for Covid-19 and to measure the severity, extent and evolution of SARS-CoV-2 pneumonia including over the medium and long term,” says principal investigator Giuseppe Pezzano, a researcher at Eurecat’s Digital Health Unit and the UB.

Specifically, the system works by “first segmenting the lungs from the CT image to narrow down the search area and then using the algorithm to analyse the lung area and detect the presence of Covid-19,” adds Pezzano. “If there is a positive finding, the image is processed to identify the areas affected by the disease.”

The algorithm has been tested on 79 volumes and 110 slices of CT scans in which Covid-19 infection had been detected obtained from three open-access image repositories. Average accuracy for SARS-CoV-2 lesion segmentation was about 99 percent with no false positives observed during identification.

“The accuracy of the tool developed as shown by the results of the study opens up a wide range of other applications in healthcare, a field in which Artificial Intelligence is proving to be increasingly helpful,” points out Vicent Ribas, one of the study researchers and head of the Data Analytics in Medicine research strand at Eurecat’s Digital Health Unit.

The method developed uses an innovative way of calculating the segmentation mask of medical images which has also brought outstanding results in segmenting nodules in CT scans.

Recently “papers have been published showing that Deep Learning algorithms and Computer Vision have achieved greater accuracy than medical experts in detecting cancer in mammograms and predicting strokes and heart attacks,” comments Petia Radeva, CVC researcher and Professor and head of the consolidated Computer Vision and Machine Learning Research Group at the University of Barcelona. “We wanted to be there on the frontline and so we’ve developed this technology to help doctors fight Covid-19 by providing them with high-precision algorithms to analyse medical images objectively, transparently and robustly.”

“This type of automated system is an extremely significant tool for health professionals for more robust and accurate diagnoses,” says UB Assistant Professor Oliver Díaz. “That’s because it can provide information which cannot be measured by a human being.”

Reference: CoLe-CNN+: Context learning – Convolutional neural network for COVID-19-Ground-Glass-Opacities detection and segmentation – ScienceDirect

Related articles: