Toward vehicle occupant-invariant models for activity characterization

L Capozzi, V Barbosa, C Pinto, JR Pinto… - IEEE …, 2022 - ieeexplore.ieee.org
With the advent of self-driving cars and the push by large companies into fully driverless
transportation services, monitoring passenger behaviour in vehicles is becoming …

Adversarial learning for a robust iris presentation attack detection method against unseen attack presentations

PM Ferreira, AF Sequeira, D Pernes… - … Conference of the …, 2019 - ieeexplore.ieee.org
Despite the high performance of current presentation attack detection (PAD) methods, the
robustness to unseen attacks is still an under addressed challenge. This work approaches …

A robust fingerprint presentation attack detection method against unseen attacks through adversarial learning

JA Pereira, AF Sequeira, D Pernes… - … Conference of the …, 2020 - ieeexplore.ieee.org
Fingerprint presentation attack detection (PAD) methods present a stunning performance in
current literature. However, the fingerprint PAD generalisation problem is still an open …

[PDF][PDF] Signer-independent sign language recognition with adversarial neural networks

PM Ferreira, D Pernes, A Rebelo… - International Journal of …, 2021 - researchgate.net
Sign Language Recognition (SLR) has become an appealing topic in modern societies
because such technology can ideally be used to bridge the gap between deaf and hearing …

Condition Invariance for Autonomous Driving by Adversarial Learning

DT e Silva, RPM Cruz - Iberoamerican Congress on Pattern Recognition, 2023 - Springer
Object detection is a crucial task in autonomous driving, where domain shift between the
training and the test set is one of the main reasons behind the poor performance of a …

Genetic improvement of industrial saccharomyces cerevisiae: Consolidated bioprocessing and value-added products for an advanced lignocellulosic biorefinery

JFTP da Cunha - 2021 - search.proquest.com
Nos últimos anos a produção biotecnológica de biocombustíveis e outros químicos a partir
de biomassa renovável apareceu como uma alternativa para a economia baseada em …

Adversarial domain adaptation for sensor networks

FT Andrade - 2020 - search.proquest.com
With the recent surge of big data, manually annotating datasets has become an impossible
task. Asa result, domain adaptation has gained more importance than ever, since it allows …

[PDF][PDF] Fingerprint Anti Spoofing-Domain Adaptation and Adversarial Learning

JAP Pereira - 2020 - repositorio-aberto.up.pt
The fingerprint is the oldest biometric trait used as a form of identification. With the
increasing implementation of biometric sensors in mobile devices, its use is becoming a …

[PDF][PDF] Rethinking a Deep Learning Pipeline for Images

RP de Magalhães Cruz - 2021 - repositorio-aberto.up.pt
P attern recognition methods involve several stages starting from the raw data to the
prediction output. This is known as a pipeline. While deep learning has been hailed as …