Cookies
Usamos cookies para melhorar nosso site e a sua experiência. Ao continuar a navegar no site, você aceita a nossa política de cookies. Ver mais
Aceitar Rejeitar
  • Menu
Sobre
Download foto HD

Sobre

Ana Rebelo está envolvida em atividades de investigação e desenvolvimento no Grupo Visual Computing and Machine Intelligence (VCMI) no Centro de Telecomunicações e Multimédia (CTM) do INESC TEC. Rebelo tem desenvolvido e implementado algoritmos de Computer Vision e Machine Learning para aplicações biométricas. É responsável pela submissão e coordenação de projetos de investigação e coordenação científica, trabalhando em colaboração com várias empresas. Ela é co-fundadora e co-líder da Escola de Verão VISUM, uma escola de verão sem fins lucrativos que visa reunir Ph.D. candidatos, académicos e investigadores da academia e da indústria com interesses em visão por computador e inteligência artificial. Ana Rebelo tem um doutoramento em Engenharia Electrotécnica e de Computadores pela Universidade do Porto-Portugal.

Tópicos
de interesse
Detalhes

Detalhes

004
Publicações

2020

Learning signer-invariant representations with adversarial training

Autores
Ferreira, PM; Pernes, D; Rebelo, A; Cardoso, JS;

Publicação
Twelfth International Conference on Machine Vision (ICMV 2019)

Abstract

2019

On the role of multimodal learning in the recognition of sign language

Autores
Ferreira, PM; Cardoso, JS; Rebelo, A;

Publicação
Multimedia Tools and Applications

Abstract
Sign Language Recognition (SLR) has become one of the most important research areas in the field of human computer interaction. SLR systems are meant to automatically translate sign language into text or speech, in order to reduce the communicational gap between deaf and hearing people. The aim of this paper is to exploit multimodal learning techniques for an accurate SLR, making use of data provided by Kinect and Leap Motion. In this regard, single-modality approaches as well as different multimodal methods, mainly based on convolutional neural networks, are proposed. Our main contribution is a novel multimodal end-to-end neural network that explicitly models private feature representations that are specific to each modality and shared feature representations that are similar between modalities. By imposing such regularization in the learning process, the underlying idea is to increase the discriminative ability of the learned features and, hence, improve the generalization capability of the model. Experimental results demonstrate that multimodal learning yields an overall improvement in the sign recognition performance. In particular, the novel neural network architecture outperforms the current state-of-the-art methods for the SLR task. © 2018, Springer Science+Business Media, LLC, part of Springer Nature.

2019

DeSIRe: Deep Signer-Invariant Representations for Sign Language Recognition

Autores
Ferreira, PM; Pernes, D; Rebelo, A; Cardoso, JS;

Publicação
IEEE Transactions on Systems, Man, and Cybernetics: Systems

Abstract

2018

Physiological Inspired Deep Neural Networks for Emotion Recognition

Autores
Ferreira, PM; Marques, F; Cardoso, JS; Rebelo, A;

Publicação
IEEE ACCESS

Abstract
Facial expression recognition (FER) is currently one of the most active research topics due to its wide range of applications in the human-computer interaction field. An important part of the recent success of automatic FER was achieved thanks to the emergence of deep learning approaches. However, training deep networks for FER is still a very challenging task, since most of the available FER data sets are relatively small. Although transfer learning can partially alleviate the issue, the performance of deep models is still below of its full potential as deep features may contain redundant information from the pre-trained domain. Instead, we propose a novel end-to-end neural network architecture along with a well-designed loss function based on the strong prior knowledge that facial expressions are the result of the motions of some facial muscles and components. The loss function is defined to regularize the entire learning process so that the proposed neural network is able to explicitly learn expression-specific features. Experimental results demonstrate the effectiveness of the proposed model in both lab-controlled and wild environments. In particular, the proposed neural network provides quite promising results, outperforming in most cases the current state-of-the-art methods.

2018

Are Deep Learning Methods Ready for Prime Time in Fingerprints Minutiae Extraction?

Autores
Rebelo, A; Oliveira, T; Correia, ME; Cardoso, JS;

Publicação
Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications - Lecture Notes in Computer Science

Abstract

Teses
supervisionadas

2019

Face recognition for forensic applications - Methods for matching facial sketches to mugshot pictures

Autor
Leonardo Gomes Capozzi

Instituição
UP-FEUP

2019

Automation of Waste Sorting with Deep Learning

Autor
João Soares Sousa

Instituição
UP-FEUP

2019

Sign Language Recognition: Integrating Prior Domain Knowledge into Deep Neural Networks

Autor
Pedro Miguel Martins Ferreira

Instituição
UP-FEUP

2018

Portuguese Sign Language Recognition

Autor
Pedro Miguel Martins Ferreira

Instituição
IES_Outra

2015

Smart Image Retargeting Techniques

Autor
Laura Figueiredo Ângelo

Instituição
UP-FEUP