close

In the media

In the mediaNews

Los probadores del futuro en los medios de comunicación

JELO

Los probadores del futuro, el último trabajo del Dr. Sergio Escalera, líder del grupo de investigación Human Pose Recovery and Behavior Analysis del Centro de Visión por Computador (CVC) – Universidad de Barcelona (UB), sigue de actualidad. En las últimas semanas ha suscitado el interés de medios de comunicación tales cómo la Agencia SINC, Onda Cero, Atresmedia, El Periódico o el Heraldo de Aragón, entre otros. Puedes consultarlos todos en la siguiente lista:

 

read more
In the mediaNews

El Centre de Visió per Computador s’uneix a la carta oberta de l’ACER “Ara més que mai: cal impulsar la ciència i la innovació”

ExKZRL-XIAE8LGY

El Dr. Josep Llados, Director del Centre de Visió per Computador (CVC) i membre de la junta de l’Associació Catalana d’Entitats de Recerca (ACER), ha signat la carta oberta “Ara més que mai: cal impulsar la ciència i la innovació” on l’ACER demana al futur nou govern català aprofitar els fons de recuperació de la Comissió Europea i fer que la ciència i la innovació donin un salt endevant, cobrint tota la cadena de valor, des de l’impuls de la recerca mes bàsica fins als mecanismes per millorar la transferència de coneixement al mercat.

L’ACER demana, a més a més, que aquesta estratègia sigui implementada de forma transversal en tots els Departaments, amb una coordinació des d’un Departament on Recerca i Innovació siguin centrals.

Els altres signants de la carta són Josep Samitier, director de l’Institut de Bioenginyeria de Catalunya (IBEC); Joan Comella, director del Vall d’Hebron Research Institute (VHIR); Francesc Posas, director de l’Institut de Recerca Biomèdica (IRB) i Ramon Miquel, director de l’Institut de Física d’Altes Energies (IFAE).

En els mitjans:

Diari Ara: https://www.ara.cat/societat/centres-recerca-reclamen-nou-govern-prioritzi-ciencia-innovacio_1_3910497.html

 

read more
In the mediaNewsPress Release

The fitting rooms of the future

Researchers from the Computer Vision Center (CVC) and the University of Barcelona (UB) have developed, using deep learning, CLOTH3D, the first 3D big scale synthetic dataset for simulating clothes on top of different body shapes. This dataset is the first step to allow virtual enhanced try-ons experience.

Every day, more and more people buy their clothes using virtual platforms, and the current pandemic situation is even speeding up this trend. The advantages of this new way of shopping are evident, but it has some shortcomings too. One of the most important is that people cannot try on the clothes before receiving it at their place. To solve this problem, Artificial Intelligence and deep learning are playing a key role, since they are allowing modelling, recovery and generation of 3D model clothes. These models will mean a breakthrough for enhanced virtual try-ons experience, reducing designers and animator’s workload.

Nowadays, it exits models for simulating clothes on top of body shapes, but they are almost focused on 2D. This is because 3D models need an enormous amount of data, and available 3D cloth data are very scarce. There are three main strategies in order to produce data of 3D dressed humans: 3D scans, 3D from conventional images, and synthetic generation. In the case of 3D scans, they are costly, and at most they can produce a single mesh (human + garments). Alternatively, datasets that infer 3D geometry of clothes from conventional images are inaccurate and cannot properly model cloth dynamics. Finally, synthetic data is easy to generate and is ground truth error free.

Researchers from the Human Pose Recovery and Behavior Analysis Group at the Computer Vision Center (CVC) – University of Barcelona (UB) chose this last path and developed CLOTH3D, the first big scale synthetic dataset of 3D clothed human sequences, which was recently published in the Computer Vision – ECCV 2020 journal.  “As a lot of data is needed for developing 3D models, we decided to generate our own data. We have designed and release the biggest dataset of this kind with a strong outfit variability and rich cloth dynamics”, explained Hugo Bertiche (UB – CVC).

CLOTH3D contains a large variability on garment type, topology, shape, size, tightness and fabric. Clothes are simulated on top of thousands of different pose sequences and body shapes, generating realistic cloth dynamics. CLOTH3D is unique in terms of garment, shape, and pose variability, including more than 2 million 3D samples. “We developed a generation pipeline that creates a unique out fit for each sequence in terms of garment type, topology, shape, size, tightness and fabric. While other datasets contain just a few different garments, ours is the biggest data set in this field nowadays, with thousands of different garments. But we did not focus only in its development, we also published it in open access, so it is available for all types of audiences”, Dr. Sergio Escalera (CVC-UB) pointed out.

But cloth manufacturing industry is not the only ones who could take advantage of this dataset, “the entertainment industry could also benefit, since computer generated image movies and videogames could be even more realistic”, argue Dr. Meysam Madadi (CVC). But there is still plenty of work to do, “understanding of 3D garments through deep learning is still in early stages. On one hand, while our dataset covers most day-to-day garment variability, outfit styles are only limited by imagination. Faster, automatic and smart garment design could lead to many very interesting applications. On the other hand, cloth dynamics are extremely complex and challenging, and they have been barely tackled in very naive ways. Further exploring is a must for this community. Finally, real fabrics are much more than what simulators usually provide, deep learning has yet to find the proper way to model extremely fine and chaotic details such as wrinkles and also objects of arbitrary geometry related to outfits, such as hats, glasses, gloves, shoes, trinkets and more”, concluded H. Bertiche.

Reference:

Bertiche H., Madadi M., Escalera S. (2020) CLOTH3D: Clothed 3D Humans. Computer Vision – ECCV 2020. Lecture Notes in Computer Science, vol 12540. Springer, Cham. DOI: 10.1007/978-3-030-58565-5_21

read more
ConferencesIn the mediaNewsPress Release

New advances in the detection of bias in face recognition algorithms

FairFace Challenge at ECCV 2020(1)

A team from the Computer Vision Center (CVC) and the University of Barcelona has published the results of a study that evaluates the accuracy and bias in gender and skin colour of automatic face recognition algorithms tested with real world data. Although the top solutions exceed the 99.9% of accuracy, researchers have detected some groups that show higher false positive or false negative rates.

Face recognition has been routinely utilized by both private and governmental organizations around the world. Automatic face recognition can be used for legitimate and beneficial purposes (e.g. to improve security) but at the same time its power and ubiquity heightens a potential negative impact unfair methods can have for the society (e.g. discrimination against ethnic minorities). Although not sufficient, a necessary condition for a legitimate deployment of face recognition algorithms is equal accuracy for all demographic groups.

With this purpose in mind, researchers from the Human Pose Recovery and Behavior Analysis Group at the Computer Vision Center (CVC) – University of Barcelona, led by Dr. Sergio Escalera, organized a challenge within the European Conference of Computer Vision (ECCV) 2020. The results, recently published in Computer Vision – ECCV 2020 Workshops, evaluated the accuracy and bias in gender and skin colour of the submitted algorithms by the participants on the task of face verification in the presence of other confounding attributes.

The challenge was a success since “it attracted 151 participants, who made more than 1.800 submissions in total, exceeding our expectations regarding the number of participants and submissions” explained Dr. Sergio Escalera (CVC-UB).

The participants used an image dataset not balanced, which simulates a real world scenario where AI-based models supposed to be trained and evaluated on imbalanced data (considerably more white males that dark females). In total, they worked with 152,917 images from 6,139 identities.

The images were annotated for two protected attributes: gender and skin colour; and five legitimate attributes: age group (0-34, 35-64, 65+), head pose (frontal, other), image source (still image, video frame), wearing glasses and a bounding box size.

The obtained results were very promising. Top winning solutions exceeded 99.9% of accuracy while achieving very low scores in the proposed bias metrics, “which can be considered a step toward the development of fairer face recognition methods” expounded Julio C. S. Jacques Jr., researcher at the CVC and at the Universitat Oberta de Catalunya. The analysis of top-10 teams showed higher false positive rates for females with dark skin tone and for samples where both individuals wear glasses. In contrast there were higher false negative rates for males with light skin tone and for samples where both individuals are younger than 35 years. Also, it was found that in the dataset individuals younger than 35 years wear glasses less often than older individuals, resulting in a combination of effects of these attributes. “This was not a surprise as the adopted dataset was not balanced with respect to different demographic attributes. However, it shows that overall accuracy is not enough when the goal is to build fair face recognition methods, and that future works on the topic must take into account accuracy and bias mitigation together”, concluded Julio C. S. Jacques Jr.

Reference:

Sixta T., Jacques Junior J.C.S., Buch-Cardona P., Vazquez E., Escalera S. (2020) FairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognition. Computer Vision – ECCV 2020 Workshops. ECCV 2020. Lecture Notes in Computer Science, vol 12540. Springer, Cham. DOI: 10.1007/978-3-030-65414-6_32

In the media

Diario Libre: Detectan algoritmos más precisos de reconocimiento facial según tono de piel

El Desconcierto: Inteligencia artificial: Detectan algoritmos más precisos de reconocimiento facial según tono de piel

Ámbito: Detectan algoritmos que diferencian el tono de piel en el reconocimiento facial

Diario San Rafael: Detectan algoritmos que diferencian el tono de piel en el reconocimiento facial

Mirage news: New advances in detection of bias in face recognition algorithms

Marktechpost: Researchers From Computer Vision Center (CVC) And The University Of Barcelona Conducted A Study That Results In Improved Accuracy On Face Verification Tasks In The Presence Of Other Confounding Attributes

read more
In the media

The role of the CVC in the fight against Covid-19 and lung cancer

Foto IAM4B

La Vanguardia -in its printed edition- and Univadis Spain, featured the CVC research aimed to develop a digital biopsia that may be used in the diagnosis of Covid-19 and lung cancer.

Members of the Interactive Augmented Modelling for Biomedicine (IAM4B) led by Dr. Dèbora Gil and Dr. Carles Sánchez, in collaboration with researchers from the Germans Trias i Pujol Research Institute (IGTP) led by the Dr. Antoni Rosell, Thorax Area Clinical Director, were using a technique called radiomics for the diagnosis of lung cancer combining PET and TAC scanners.

IAM4B researchers (CVC). From left to right and from top to bottom: Dr. Carles Sánchez, Guillermo Torres, Dr. Thomas Batard, Dr. Aura Hernández, Roger Domingo Espinós, Esmitt Ramírez, Dr. Dèbora Gil (IAM4B Director) and José Elías Yauri.

 

Hospital Germans Trias i Pujol researchers. From left to right and from top to the bottom: Dr. Jordi Deportos, Dr. Antoni Rosell (Thorax Area Clinical Director), Dr. Sonia Baeza, Dr. Gloria Moragas and Dr. Maite Salcedo

However, with the Covid-19 pandemic emergence, they tried to transfer all the knowledge they accumulated during their studies in cancer lung to Covid-19, concretely to the early detection of microstrokes provoked by bilateral pneumonia asociated to Covid-19 infection. For achieving this purpose they used again radiomics with TAC and SPECT (instead PET) scanners.

The system has been retrospectively tested with 63 Covid-19 patients for the first pandemic wave and 70 non-Covid-19 patients, including healthy controls and non-Covid-19 pneumonia (bacterial pneumonia), reaching a 93% accuracy in the detection of Covid-19 microinfarcts. The results are therefore very encouraging.

You can read the full articles here (in Spanish): Digital biopsia (La Vanguardia) and Univadis España

 

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 712949 (TECNIOspring PLUS) and from the Agency for Business Competitiveness of the Government of Catalonia.

read more
1 2 3 4 5 15
Page 3 of 15