no code implementations • 11 Mar 2024 • Henrique Jesus, Hugo Proença
However, three weaknesses are commonly reported for such kind of approaches: 1) their extreme demands in terms of learning data; 2) the difficulties in generalising between different domains; and 3) the lack of interpretability/explainability, with biometrics being of particular interest, as it is important to provide evidence able to be used for forensics/legal purposes (e. g., in courts).
1 code implementation • Image and Vision Computing 2024 • Kailash Hambarde, Hugo Proença
Human re-identification (re-ID) is nowadays among the most popular topics in computer vision, due to the increasing importance given to safety/security in modern societies.
Action Recognition Image-To-Video Person Re-Identification +4
1 code implementation • IEEE Access 2023 • Kailash Hambarde, Hugo Proença
This paper provides an extensive and thorough overview of the models and techniques utilized in the first and second stages of the typical information retrieval processing chain.
no code implementations • 18 May 2023 • Joana C. Costa, Tiago Roxo, Hugo Proença, Pedro R. M. Inácio
Deep Learning is currently used to perform multiple tasks, such as object recognition, face recognition, and natural language processing.
1 code implementation • 9 Mar 2023 • Tiago Roxo, Joana C. Costa, Pedro R. M. Inácio, Hugo Proença
The results show that: 1) AVA trained models maintain a state-of-the-art performance in WASD Easy group, while underperforming in the Hard one, showing the 2) similarity between AVA and Easy data; and 3) training in WASD does not improve models performance to AVA levels, particularly for audio impairment and surveillance settings.
no code implementations • 28 Dec 2022 • Fernando Alonso-Fernandez, Josef Bigun, Julian Fierrez, Naser Damer, Hugo Proença, Arun Ross
Periocular refers to the externally visible region of the face that surrounds the eye socket.
no code implementations • 12 Oct 2022 • Kien Nguyen, Hugo Proença, Fernando Alonso-Fernandez
In this survey, we provide a comprehensive review of more than 200 papers, technical reports, and GitHub repositories published over the last 10 years on the recent developments of deep learning techniques for iris recognition, covering broad topics on algorithm designs, open-source tools, open challenges, and emerging research.
1 code implementation • 24 Sep 2022 • Marcelo dos Santos, Rayson Laroca, Rafael O. Ribeiro, João Neves, Hugo Proença, David Menotti
To the best of our knowledge, this is the first time SDEs have been used for such an application.
1 code implementation • 21 Oct 2021 • Bruno Degardin, João Neves, Vasco Lopes, João Brito, Ehsan Yaghoubi, Hugo Proença
Synthesising the spatial and temporal dynamics of the human body skeleton remains a challenging task, not only in terms of the quality of the generated shapes, but also of their diversity, particularly to synthesise realistic body movements of a specific action (action conditioning).
Ranked #1 on Human action generation on Human3.6M
2 code implementations • 14 Jul 2021 • Tiago Roxo, Hugo Proença
To overcome these limitations, we: 1) present frontal and wild face versions of three well-known surveillance datasets; and 2) propose YinYang-Net (YY-Net), a model that effectively and dynamically complements facial and body information, which makes it suitable for gender recognition in wild conditions.
no code implementations • 14 May 2021 • Bruno Degardin, Vasco Lopes, Hugo Proença
It is known that the kinematics of the human body skeleton reveals valuable information in action recognition.
2 code implementations • 12 May 2021 • Tiago Roxo, Hugo Proença
Soft biometrics analysis is seen as an important research topic, given its relevance to various applications.
1 code implementation • 3 Jan 2021 • Bruno Degardin, Hugo Proença
The detection of abnormal events in surveillance footage remains a challenge and has been the scope of various research works.
Ranked #1 on Semi-supervised Anomaly Detection on UBI-Fights
1 code implementation • 8 Jul 2020 • Hugo Proença
We propose a reversible face de-identification method for low resolution video data, where landmark-based techniques cannot be reliably used.
1 code implementation • 19 Jun 2020 • S. V. Aruna Kumar, Ehsan Yaghoubi, Hugo Proença
In video-based person re-identification, both the spatial and temporal features are known to provide orthogonal cues to effective representations.
1 code implementation • 6 Apr 2020 • S. V. Aruna Kumar, Ehsan Yaghoubi, Abhijit Das, B. S. Harish, Hugo Proença
Over the last decades, the world has been witnessing growing threats to the security in urban spaces, which has augmented the relevance given to visual surveillance solutions able to detect, track and identify persons of interest in crowds.
1 code implementation • 2 Apr 2020 • Ehsan Yaghoubi, Diana Borza, João Neves, Aruna Kumar, Hugo Proença
The automatic characterization of pedestrians in surveillance footage is a tough challenge, particularly when the data is extremely diverse with cluttered backgrounds, and subjects are captured from varying distances, under multiple poses, with partial occlusion.
1 code implementation • 26 Feb 2020 • Hugo Proença, Ehsan Yaghoubi, Pendar Alirezazadeh
This paper describes one objective function for learning semantically coherent feature embeddings in multi-output classification problems, i. e., when the response variables have dimension higher than one.
no code implementations • 10 Feb 2020 • Luiz A. Zanlorensi, Hugo Proença, David Menotti
Ocular biometric systems working in unconstrained environments usually face the problem of small within-class compactness caused by the multiple factors that jointly degrade the quality of the obtained data.
1 code implementation • 30 Jan 2020 • Ehsan Yaghoubi, Diana Borza, Aruna Kumar, Hugo Proença
The \emph{receptive fields} of deep learning classification models determine the regions of the input data that have the most significance for providing correct decisions.
no code implementations • 21 Nov 2019 • Luiz A. Zanlorensi, Diego R. Lucio, Alceu S. Britto Jr., Hugo Proença, David Menotti
One of the major challenges in ocular biometrics is the cross-spectral scenario, i. e., how to match images acquired in different wavelengths (typically visible (VIS) against near-infrared (NIR)).
2 code implementations • 13 Nov 2019 • João C. Neves, Ruben Tolosana, Ruben Vera-Rodriguez, Vasco Lopes, Hugo Proença, Julian Fierrez
The availability of large-scale facial databases, together with the remarkable progresses of deep learning technologies, in particular Generative Adversarial Networks (GANs), have led to the generation of extremely realistic fake facial content, raising obvious concerns about the potential for misuse.
no code implementations • 5 Jan 2019 • Imad Rida, Lunke Fei, Hugo Proença, Amine Nait-ali, Abdenour Hadid
As an advanced research topic in forensics science, automatic shoe-print identification has been extensively studied in the last two decades, since shoe marks are the clues most frequently left in a crime scene.