no code implementations • 26 Jul 2023 • Gabriel Bertocco, Fernanda Andaló, Terrance E. Boult, Anderson Rocha
Fully-unsupervised Person and Vehicle Re-Identification have received increasing attention due to their broad applicability in surveillance, forensics, event understanding, and smart cities, without requiring any manual annotation.
no code implementations • 11 Feb 2023 • Wes Robbins, Gabriel Bertocco, Terrance E. Boult
In unconstrained scenarios, face recognition and person re-identification are subject to distortions such as motion blur, atmospheric turbulence, or upsampling artifacts.
1 code implementation • 7 Feb 2022 • Gabriel Bertocco, Antônio Theophilo, Fernanda Andaló, Anderson Rocha
We propose a strategy to tackle Person Re-Identification and Text Authorship Attribution by enabling learning from unlabeled data even when samples from different classes are not prominently diverse.
1 code implementation • IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2021 • Gabriel Bertocco, Fernanda Andaló, Anderson Rocha
Person Re-Identification (ReID) across non-overlapping cameras is a challenging task and, for this reason, most works in the prior art rely on supervised feature learning from a labeled dataset to match the same person in different views.
Ranked #1 on Unsupervised Domain Adaptation on Market to MSMT