
PseudoBayesian Learning with Kernel Fourier Transform as Prior
We revisit Rahimi and Recht (2007)'s kernel random Fourier features (RFF...
read it

Fast SpatiallyVarying Indoor Lighting Estimation
We propose a realtime method to estimate spatiallyvarying indoor lighti...
read it

AllWeather Deep Outdoor Lighting Estimation
We present a neural network that predicts HDR outdoor illumination from ...
read it

Developing and Deploying Machine Learning Pipelines against RealTime Image Streams from the PACS
Executing machine learning (ML) pipelines on radiology images is hard du...
read it

Dichotomize and Generalize: PACBayesian Binary Activated Deep Neural Networks
We present a comprehensive study of multilayer neural networks with bina...
read it

Unsupervised Automatic Building Extraction Using Active Contour Model on Unregistered Optical Imagery and Airborne LiDAR Data
Automatic extraction of buildings in urban scenes has become a subject o...
read it

A Perceptual Measure for Deep Single Image Camera Calibration
Most current single image camera calibration methods rely on specific im...
read it

Robustness to Adversarial Examples through an Ensemble of Specialists
We are proposing to use an ensemble of diverse specialists, where specia...
read it

MultiTask Learning by Deep Collaboration and Application in Facial Landmark Detection
Convolutional neural networks (CNN) have become the most successful and ...
read it

Alternating Direction Method of Multipliers for Sparse Convolutional Neural Networks
The storage and computation requirements of Convolutional Neural Network...
read it

An adaptive thresholding approach for automatic optic disk segmentation
Optic disk segmentation is a prerequisite step in automatic retinal scre...
read it

Parametric Exponential Linear Unit for Deep Convolutional Neural Networks
The activation function is an important component in Convolutional Neura...
read it

Streaming kernel regression with provably adaptive mean, variance, and regularization
We consider the problem of streaming kernel regression, when the observa...
read it

Learning to Predict Indoor Illumination from a Single Image
We propose an automatic method to infer high dynamic range illumination ...
read it

Estimating Quality in MultiObjective Bandits Optimization
Many realworld applications are characterized by a number of conflictin...
read it

Learning High Dynamic Range from Outdoor Panoramas
Outdoor lighting has extremely high dynamic range. This makes the proces...
read it

Deep 6DOF Tracking
We present a temporal 6DOF tracking method which leverages deep learnin...
read it

Deep Outdoor Illumination Estimation
We present a CNNbased technique to estimate highdynamic range outdoor ...
read it

Dictionary Learning for Robotic Grasp Recognition and Detection
The ability to grasp ordinary and potentially neverseen objects is an i...
read it

Risk Bounds for the Majority Vote: From a PACBayesian Analysis to a Learning Algorithm
We propose an extensive analysis of the behavior of majority votes in bi...
read it

An Improvement to the Domain Adaptation Bound in a PACBayesian context
This paper provides a theoretical analysis of domain adaptation based on...
read it

On Generalizing the CBound to the Multiclass and Multilabel Settings
The Cbound, introduced in Lacasse et al., gives a tight upper bound on ...
read it

Learning interpretable models of phenotypes from whole genome sequences with the Set Covering Machine
The increased affordability of whole genome sequencing has motivated its...
read it

The AllDifferent Constraint with Precedences
We propose AllDiffPrecedence, a new global constraint that combines toge...
read it

Sign Language Fingerspelling Classification from Depth and Color Images using a Deep Belief Network
Automatic sign language recognition is an open problem that has received...
read it

PACBayesian Learning and Domain Adaptation
In machine learning, Domain Adaptation (DA) arises when the distribution...
read it

Learning a peptideprotein binding affinity predictor with kernel ridge regression
We propose a specialized string kernel for small biomolecules, peptides...
read it

PACBayesian Analysis of Martingales and Multiarmed Bandits
We present two alternative ways to apply PACBayesian analysis to sequen...
read it

Towards an interdisciplinary, sociotechnical analysis of software ecosystem health
This extended abstract presents the research goals and preliminary resea...
read it

Coqatoo: Generating Natural Language Versions of Coq Proofs
Due to their numerous advantages, formal proofs and proof assistants, su...
read it

Query Completion Using Bandits for Engines Aggregation
Assisting users by suggesting completed queries as they type is a common...
read it

Fusion of ANN and SVM Classifiers for Network Attack Detection
With the progressive increase of network application and electronic devi...
read it

From Superpixel to Human Shape Modelling for Carried Object Detection
Detecting carried objects is one of the requirements for developing syst...
read it

Secrecy by WitnessFunctions on Increasing Protocols
In this paper, we present a new formal method to analyze cryptographic p...
read it

Learning a Bias Correction for Lidaronly Motion Estimation
This paper presents a novel technique to correct for bias in a classical...
read it

Deep Learning for Electromyographic Hand Gesture Signal Classification by Leveraging Transfer Learning
In recent years, the use of deep learning algorithms has become increasi...
read it

Relaxed Conditions for Secrecy in a RoleBased Specification
In this paper, we look at the property of secrecy through the growth of ...
read it

Outdistribution training confers robustness to deep neural networks
The easiness at which adversarial instances can be generated in deep neu...
read it

Diversity regularization in deep ensembles
Calibrating the confidence of supervised learning models is important fo...
read it

A Theorem for Secrecy in Tagged Protocols Using the Theory of WitnessFunctions
In this paper, we enunciate the theorem of secrecy in tagged protocols u...
read it

A Framework for Evaluating 6DOF Object Trackers
We present a challenging and realistic novel dataset for evaluating 6DO...
read it

Learning to Estimate Indoor Lighting from 3D Objects
In this work, we propose a step towards a more accurate prediction of th...
read it

On the universality of the stochastic block model
Mesoscopic pattern extraction (MPE) is the problem of finding a partitio...
read it

Evaluating and Characterizing Incremental Learning from NonStationary Data
Incremental learning from nonstationary data poses special challenges t...
read it

Learning Object Localization and 6D Pose Estimation from Simulation and Weakly Labeled Real Images
This work proposes a process for efficiently training a pointwise objec...
read it

Controlling Overgeneralization and its Effect on Adversarial Examples Generation and Detection
Convolutional Neural Networks (CNNs) allowed improving the stateofthe...
read it

Geometry Preserving Sampling Method based on Spectral Decomposition for 3D Registration
In the context of 3D mapping, larger and larger point clouds are acquire...
read it

Lidar Measurement Bias Estimation via Return Waveform Modelling in a Context of 3D Mapping
In a context of 3D mapping, it is very important to get accurate measure...
read it

CELLO3D: Estimating the Covariance of ICP in the Real World
The fusion of Iterative Closest Point (ICP) reg istrations in existing ...
read it

A New Loss Function for Temperature Scaling to have Better Calibrated Deep Networks
However Deep neural networks recently have achieved impressive results f...
read it
Université Laval
Université Laval (UL) is the first Frenchspeaking university in America. It is located in Quebec City, Canada. The UL offers nearly 400 curricula for all three cycles. She is internationally recognized for excellence in her education and scientific research.