Search Results for author:
Found 55 papers, 23 papers with code
One-to-many Reconstruction of 3D Geometry of cultural Artifacts using a synthetically trained Generative Model
Estimating the 3D shape of an object using a single image is a difficult problem.
Extending 6D Object Pose Estimators for Stereo Vision
Estimating the 6D pose of objects accurately, quickly, and robustly remains a difficult task.
An Empirical Study of Uncertainty Estimation Techniques for Detecting Drift in Data Streams
In safety-critical domains such as autonomous driving and medical diagnosis, the reliability of machine learning models is crucial.
Generalization of Fitness Exercise Recognition from Doppler Measurements by Domain-adaption and Few-Shot Learning
In previous works, a mobile application was developed using an unmodified commercial off-the-shelf smartphone to recognize whole-body exercises.
Bias and Diversity in Synthetic-based Face Recognition
In this work, we investigate how the diversity of synthetic face recognition datasets compares to authentic datasets, and how the distribution of the training data of the generative models affects the distribution of the synthetic data.
IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models
The availability of large-scale authentic face databases has been crucial to the significant advances made in face recognition research over the past decade.
Ranked #2 on
Synthetic Face Recognition
on AgeDB-30
(Accuracy metric)
ExFaceGAN: Exploring Identity Directions in GAN's Learned Latent Space for Synthetic Identity Generation
To generate multiple samples of a certain synthetic identity, previous works proposed to disentangle the latent space of GANs by incorporating additional supervision or regularization, enabling the manipulation of certain attributes.
Identity-driven Three-Player Generative Adversarial Network for Synthetic-based Face Recognition
We empirically proved that our IDnet synthetic images are of higher identity discrimination in comparison to the conventional two-player GAN, while maintaining a realistic intra-identity variation.
Extension of Dictionary-Based Compression Algorithms for the Quantitative Visualization of Patterns from Log Files
This work presents an approach to detect frequent patterns in textual data that can be simultaneously registered during the file compression process with low consumption of resources.
IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Model
The availability of large-scale authentic face databases has been crucial to the significant advances made in face recognition research over the past decade.
Unsupervised Face Recognition using Unlabeled Synthetic Data
In this paper, we propose an unsupervised face recognition model based on unlabeled synthetic data (USynthFace).
Ranked #1 on
Unsupervised face recognition
on LFW
Stating Comparison Score Uncertainty and Verification Decision Confidence Towards Transparent Face Recognition
The confidence of a decision is often based on the overall performance of the model or on the image quality.
Fairness in Face Presentation Attack Detection
Face recognition (FR) algorithms have been proven to exhibit discriminatory behaviors against certain demographic and non-demographic groups, raising ethical and legal concerns regarding their deployment in real-world scenarios.
QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization
Deep learning-based face recognition models follow the common trend in deep neural networks by utilizing full-precision floating-point networks with high computational costs.
Ranked #1 on
Quantization
on LFW
On the (Limited) Generalization of MasterFace Attacks and Its Relation to the Capacity of Face Representations
However, previous works followed evaluation settings consisting of older recognition models, limited cross-dataset and cross-model evaluations, and the use of low-scale testing data.
QMagFace: Simple and Accurate Quality-Aware Face Recognition
These variabilities can be measured in terms of face image quality which is defined over the utility of a sample for recognition.
Ranked #1 on
Face Verification
on IJB-B
Partial Attack Supervision and Regional Weighted Inference for Masked Face Presentation Attack Detection
Our proposed method outperforms established PAD methods in the CRMA database by reducing the mentioned shortcomings when facing masked faces.
Pixel-Level Face Image Quality Assessment for Explainable Face Recognition
To achieve this, a model-specific quality value of the input image is estimated and used to build a sample-specific quality regression model.
ElasticFace: Elastic Margin Loss for Deep Face Recognition
The recent state-of-the-art face recognition solutions proposed to incorporate a fixed penalty margin on commonly used classification loss function, softmax loss, in the normalized hypersphere to increase the discriminative power of face recognition models, by minimizing the intra-class variation and maximizing the inter-class variation.
Ranked #1 on
Face Recognition
on IJB-B
(TAR @ FAR=0.0001 metric)
Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detection
With the increased deployment of face recognition systems in our daily lives, face presentation attack detection (PAD) is attracting much attention and playing a key role in securing face recognition systems.
PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation
However, this limits the deployment of such models that contain an extremely large number of parameters to embedded and low-end devices.
Ranked #2 on
Lightweight Face Recognition
on CALFW
PW-MAD: Pixel-wise Supervision for Generalized Face Morphing Attack Detection
A face morphing attack image can be verified to multiple identities, making this attack a major vulnerability to processes based on identity verification, such as border checks.
ReGenMorph: Visibly Realistic GAN Generated Face Morphing Attacks by Attack Re-generation
Face morphing attacks aim at creating face images that are verifiable to be the face of multiple identities, which can lead to building faulty identity links in operations like border checks.
MixFaceNets: Extremely Efficient Face Recognition Networks
In this paper, we present a set of extremely efficient and high throughput models for accurate face verification, MixFaceNets which are inspired by Mixed Depthwise Convolutional Kernels.
Ranked #3 on
Lightweight Face Recognition
on IJB-C
MFR 2021: Masked Face Recognition Competition
These teams successfully submitted 18 valid solutions.
Iris Presentation Attack Detection by Attention-based and Deep Pixel-wise Binary Supervision Network
Iris presentation attack detection (PAD) plays a vital role in iris recognition systems.
MiDeCon: Unsupervised and Accurate Fingerprint and Minutia Quality Assessment based on Minutia Detection Confidence
The implementation is publicly available.
Masked Face Recognition: Human vs. Machine
This work provides a joint evaluation and in-depth analyses of the face verification performance of human experts in comparison to state-of-the-art automatic FR solutions.
Real Masks and Spoof Faces: On the Masked Face Presentation Attack Detection
Face masks have become one of the main methods for reducing the transmission of COVID-19.
A Comprehensive Study on Face Recognition Biases Beyond Demographics
However, to enable a trustworthy FR technology, it is essential to know the influence of an extended range of facial attributes on FR beyond demographics.
Self-restrained Triplet Loss for Accurate Masked Face Recognition
Using the face as a biometric identity trait is motivated by the contactless nature of the capture process and the high accuracy of the recognition algorithms.
Understanding Interpretability by generalized distillation in Supervised Classification
The ability to interpret decisions taken by Machine Learning (ML) models is fundamental to encourage trust and reliability in different practical applications.
MAAD-Face: A Massively Annotated Attribute Dataset for Face Images
In this work, we propose MAADFace, a new face annotations database that is characterized by the large number of its high-quality attribute annotations.
Micro Stripes Analyses for Iris Presentation Attack Detection
In this paper, we propose a lightweight framework to detect iris presentation attacks by extracting multiple micro-stripes of expanded normalized iris textures.
On Benchmarking Iris Recognition within a Head-mounted Display for AR/VR Application
Motivated by the performance of iris recognition, we also propose the continuous authentication of users in a non-collaborative capture setting in HMD.
Beyond Identity: What Information Is Stored in Biometric Face Templates?
For evaluating the predictability of the attributes, we trained a massive attribute classifier that is additionally able to accurately state its prediction confidence.
Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification
Most existing person re-identification methods compute pairwise similarity by extracting robust visual features and learning the discriminative metric.
Iris Liveness Detection Competition (LivDet-Iris) -- The 2020 Edition
Launched in 2013, LivDet-Iris is an international competition series open to academia and industry with the aim to assess and report advances in iris Presentation Attack Detection (PAD).
The Effect of Wearing a Mask on Face Recognition Performance: an Exploratory Study
The recent COVID-19 pandemic have increased the value of hygienic and contactless identity verification.
AutoSNAP: Automatically Learning Neural Architectures for Instrument Pose Estimation
Despite recent successes, the advances in Deep Learning have not yet been fully translated to Computer Assisted Intervention (CAI) problems such as pose estimation of surgical instruments.
Style-transfer GANs for bridging the domain gap in synthetic pose estimator training
Given the dependency of current CNN architectures on a large training set, the possibility of using synthetic data is alluring as it allows generating a virtually infinite amount of labeled training data.
Face Quality Estimation and Its Correlation to Demographic and Non-Demographic Bias in Face Recognition
Face quality assessment aims at estimating the utility of a face image for the purpose of recognition.
SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness
Face image quality is an important factor to enable high performance face recognition systems.
Ranked #1 on
Face Quality Assessement
on LFW
Demographic Bias in Presentation Attack Detection of Iris Recognition Systems
With the widespread use of biometric systems, the demographic bias problem raises more attention.
Unsupervised Enhancement of Soft-biometric Privacy with Negative Face Recognition
Current research on soft-biometrics showed that privacy-sensitive information can be deduced from biometric templates of an individual.
Post-Comparison Mitigation of Demographic Bias in Face Recognition Using Fair Score Normalization
In contrast to previous works, our fair normalization approach enhances the overall performance by up to 53. 2% at false match rate of 0. 001 and up to 82. 9% at a false match rate of 0. 00001.
Real-time texturing for 6D object instance detection from RGB Images
For objected detection, the availability of color cues strongly influences detection rates and is even a prerequisite for many methods.
Cascaded Generation of High-quality Color Visible Face Images from Thermal Captures
Generating visible-like face images from thermal images is essential to perform manual and automatic cross-spectrum face recognition.
Efficient Pose Selection for Interactive Camera Calibration
This work presents a pose selection method that finds a compact and robust set of calibration poses and is suitable for interactive calibration.
Background Subtraction with Real-time Semantic Segmentation
Our proposed framework consists of two components, a traditional BGS segmenter $\mathcal{B}$ and a real-time semantic segmenter $\mathcal{S}$.
GANs for Medical Image Analysis
Generative Adversarial Networks (GANs) and their extensions have carved open many exciting ways to tackle well known and challenging medical image analysis problems such as medical image de-noising, reconstruction, segmentation, data simulation, detection or classification.
Combining Background Subtraction Algorithms with Convolutional Neural Network
Accurate and fast extraction of foreground object is a key prerequisite for a wide range of computer vision applications such as object tracking and recognition.
Exploring Adversarial Examples: Patterns of One-Pixel Attacks
Failure cases of black-box deep learning, e. g. adversarial examples, might have severe consequences in healthcare.
Histograms of Gaussian normal distribution for feature matching in clutter scenes
Especially in cluttered scenes there are many feature mismatches between scenes and models.
A Graphical Social Topology Model for Multi-Object Tracking
Inspired with the social affinity property of moving objects, we propose a Graphical Social Topology (GST) model, which estimates the group dynamics by jointly modeling the group structure and the states of objects using a topological representation.
