no code implementations • 17 Mar 2024 • Abraham Itzhak Weinberg, Cristiano Premebida, Diego Resende Faria
We study the impact of causality on various fields, its contribution, and its interaction with state-of-the-art approaches.
no code implementations • 9 Sep 2023 • Gledson Melotti, Johann J. S. Bastos, Bruno L. S. da Silva, Tiago Zanotelli, Cristiano Premebida
Object recognition is a crucial step in perception systems for autonomous and intelligent vehicles, as evidenced by the numerous research works in the topic.
1 code implementation • 1 Sep 2023 • Pedro Conde, Rui L. Lopes, Cristiano Premebida
For this reason, this work presents a novel theoretical and practical framework to evaluate object detection systems in the context of uncertainty calibration.
1 code implementation • 31 Jul 2023 • Nuno Cunha, Tiago Barros, Mário Reis, Tiago Marta, Cristiano Premebida, Urbano J. Nunes
Multispectral imagery is frequently incorporated into agricultural tasks, providing valuable support for applications such as image segmentation, crop monitoring, field robotics, and yield estimation.
no code implementations • 29 May 2023 • Tiago Barros, Luís Garrote, Martin Aleksandrov, Cristiano Premebida, Urbano J. Nunes
Autonomous driving systems often require reliable loop closure detection to guarantee reduced localization drift.
1 code implementation • 11 Apr 2023 • Pedro Conde, Tiago Barros, Rui L. Lopes, Cristiano Premebida, Urbano J. Nunes
With the rise of Deep Neural Networks, machine learning systems are nowadays ubiquitous in a number of real-world applications, which bears the need for highly reliable models.
no code implementations • 9 Sep 2022 • Jorge S. S. Júnior, Jérôme Mendes, Francisco Souza, Cristiano Premebida
However, many DL methodologies have complex structures that are not readily transparent to human users.
no code implementations • 18 Jul 2022 • Francisco Souza, Cristiano Premebida, Rui Araújo
The proposed High Order Conditional Mutual Information Maximization (HOCMIM) incorporates high order dependencies into the feature selection procedure and has a straightforward interpretation due to its bottom-up derivation.
no code implementations • 16 Feb 2022 • Gledson Melotti, Cristiano Premebida, Jordan J. Bird, Diego R. Faria, Nuno Gonçalves
In state-of-the-art deep learning for object recognition, SoftMax and Sigmoid functions are most commonly employed as the predictor outputs.
no code implementations • 19 Jun 2021 • Tiago Barros, Ricardo Pereira, Luís Garrote, Cristiano Premebida, Urbano J. Nunes
As part of the localization system, place recognition has benefited from recent developments in other perception tasks such as place categorization or object recognition, namely with the emergence of deep learning (DL) frameworks.
1 code implementation • 17 Jun 2021 • Tiago Barros, Luís Garrote, Ricardo Pereira, Cristiano Premebida, Urbano J. Nunes
LiDAR-based place recognition is one of the key components of SLAM and global localization in autonomous vehicles and robotics applications.
no code implementations • 11 Jul 2020 • Jordan J. Bird, Diego R. Faria, Cristiano Premebida, Anikó Ekárt, George Vogiatzis
The image and the audio datasets are first classified independently, using a fine-tuned VGG16 and an evolutionary optimised deep neural network, with accuracies of 89. 27% and 93. 72%, respectively.
no code implementations • 1 Jul 2020 • Jordan J. Bird, Diego R. Faria, Anikó Ekárt, Cristiano Premebida, Pedro P. S. Ayrosa
In speech recognition problems, data scarcity often poses an issue due to the willingness of humans to provide large amounts of data for learning and classification.