David Menotti
YOU?
Author Swipe
View article: PD-Loss: Proxy-Decidability for Efficient Metric Learning
PD-Loss: Proxy-Decidability for Efficient Metric Learning Open
Deep Metric Learning (DML) aims to learn embedding functions that map semantically similar inputs to proximate points in a metric space while separating dissimilar ones. Existing methods, such as pairwise losses, are hindered by complex sa…
View article: Exploring Light-Weight Object Recognition for Real-Time Document Detection
Exploring Light-Weight Object Recognition for Real-Time Document Detection Open
Object Recognition and Document Skew Estimation have come a long way in terms of performance and efficiency. New models follow one of two directions: improving performance using larger models, and improving efficiency using smaller models.…
View article: Toward Advancing License Plate Super-Resolution in Real-World Scenarios: A Dataset and Benchmark
Toward Advancing License Plate Super-Resolution in Real-World Scenarios: A Dataset and Benchmark Open
Recent advancements in super-resolution for License Plate Recognition (LPR) have sought to address challenges posed by low-resolution (LR) and degraded images in surveillance, traffic monitoring, and forensic applications. However, existin…
View article: Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Data
Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Data Open
Synthetic data is gaining increasing popularity for face recognition technologies, mainly due to the privacy concerns and challenges associated with obtaining real data, including diverse scenarios, quality, and demographic groups, among o…
View article: A Comparative Study on Synthetic Facial Data Generation Techniques for Face Recognition
A Comparative Study on Synthetic Facial Data Generation Techniques for Face Recognition Open
Face recognition has become a widely adopted method for user authentication and identification, with applications in various domains such as secure access, law enforcement, and locating missing persons. The success of this technology is la…
View article: Watchlist Challenge: 3<sup>rd</sup> Open-set Face Detection and Identification
Watchlist Challenge: 3<sup>rd</sup> Open-set Face Detection and Identification Open
In the current landscape of biometrics and surveillance, the ability to accurately recognize faces in uncontrolled settings is paramount. The Watchlist Challenge addresses this critical need by focusing on face detection and open-set ident…
View article: Watchlist Challenge: 3rd Open-set Face Detection and Identification
Watchlist Challenge: 3rd Open-set Face Detection and Identification Open
In the current landscape of biometrics and surveillance, the ability to accurately recognize faces in uncontrolled settings is paramount. The Watchlist Challenge addresses this critical need by focusing on face detection and open-set ident…
View article: TCDiff: Triple Condition Diffusion Model with 3D Constraints for Stylizing Synthetic Faces
TCDiff: Triple Condition Diffusion Model with 3D Constraints for Stylizing Synthetic Faces Open
A robust face recognition model must be trained using datasets that include a large number of subjects and numerous samples per subject under varying conditions (such as pose, expression, age, noise, and occlusion). Due to ethical and priv…
View article: Less is more: concatenating videos for Sign Language Translation from a small set of signs
Less is more: concatenating videos for Sign Language Translation from a small set of signs Open
The limited amount of labeled data for training the Brazilian Sign Language (Libras) to Portuguese Translation models is a challenging problem due to video collection and annotation costs. This paper proposes generating sign language conte…
View article: Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach
Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach Open
Despite significant advancements in License Plate Recognition (LPR) through deep learning, most improvements rely on high-resolution images with clear characters. This scenario does not reflect real-world conditions where traffic surveilla…
View article: Multi-Feature Aggregation in Diffusion Models for Enhanced Face Super-Resolution
Multi-Feature Aggregation in Diffusion Models for Enhanced Face Super-Resolution Open
Super-resolution algorithms often struggle with images from surveillance environments due to adverse conditions such as unknown degradation, variations in pose, irregular illumination, and occlusions. However, acquiring multiple images, ev…
View article: Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data
Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data Open
Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra-class variability, time and errors produced in manual labeling, an…
View article: Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data
Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data Open
Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra-class variability, time and errors produced in manual labeling, an…
View article: SDFR: Synthetic Data for Face Recognition Competition
SDFR: Synthetic Data for Face Recognition Competition Open
Large-scale face recognition datasets are collected by crawling the Internet and without individuals' consent, raising legal, ethical, and privacy concerns. With the recent advances in generative models, recently several works proposed gen…
View article: A Multilevel Strategy to Improve People Tracking in a Real-World Scenario
A Multilevel Strategy to Improve People Tracking in a Real-World Scenario Open
The Pal\'acio do Planalto, office of the President of Brazil, was invaded by protesters on January 8, 2023. Surveillance videos taken from inside the building were subsequently released by the Brazilian Supreme Court for public scrutiny. W…
View article: FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data
FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data Open
Despite the widespread adoption of face recognition technology around the world, and its remarkable performance on current benchmarks, there are still several challenges that must be covered in more detail. This paper offers an overview of…
View article: Bubble Detection with Semantic Segmentation for Multiphase Flow Particle Image Velocimetry
Bubble Detection with Semantic Segmentation for Multiphase Flow Particle Image Velocimetry Open
In this paper, we present an evaluation of semantic segmentation for bubble detection in multiphase flow particle image velocimetry (PIV), from which a lot of applications in oil, gas, and chemical industries, for instance, can benefit. Th…
View article: FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data
FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data Open
Despite the widespread adoption of face recognition technology around the world, and its remarkable performance on current benchmarks, there are still several challenges that must be covered in more detail. This paper offers an overview of…
View article: Multi-challenge database for active liveness
Multi-challenge database for active liveness Open
Facial authentication on mobile devices has been widely applied in various scenarios. The field of Face Liveness (or Face Anti-Spoofing, FAS) focuses on methods and tools for detecting attacks (spoofs) where a malicious user tries to imper…
View article: People Tracking Methods Applied to Planalto Palace Security Videos
People Tracking Methods Applied to Planalto Palace Security Videos Open
This paper presents a work in progress with comparative results for five state-of-the-art approaches for pedestrian tracking (Deep OC-SORT, OC-SORT, StrongSORT, BotSORT and ByteTrack) applied to a preliminary version of the UFPRPlanalto801…
View article: Super-Resolution Towards License Plate Recognition
Super-Resolution Towards License Plate Recognition Open
Recent years have seen significant developments in license plate recognition through the integration of deep learning techniques and the increasing availability of training data. Nevertheless, reconstructing license plates from low-resolut…
View article: Leveraging Model Fusion for Improved License Plate Recognition
Leveraging Model Fusion for Improved License Plate Recognition Open
License Plate Recognition (LPR) plays a critical role in various applications, such as toll collection, parking management, and traffic law enforcement. Although LPR has witnessed significant advancements through the development of deep le…
View article: Do We Train on Test Data? The Impact of Near-Duplicates on License Plate Recognition
Do We Train on Test Data? The Impact of Near-Duplicates on License Plate Recognition Open
This work draws attention to the large fraction of near-duplicates in the training and test sets of datasets widely adopted in License Plate Recognition (LPR) research. These duplicates refer to images that, although different, show the sa…