
ACDC: Weight Sharing in AtomCoefficient Decomposed Convolution
Convolutional Neural Networks (CNNs) are known to be significantly over...
read it

Nested Learning For MultiGranular Tasks
Standard deep neural networks (DNNs) are commonly trained in an endtoe...
read it

Differential 3D Facial Recognition: Adding 3D to Your StateoftheArt 2D Method
Active illumination is a prominent complement to enhance 2D face recogni...
read it

Fairness With Minimal Harm: A ParetoOptimal Approach For Healthcare
Common fairness definitions in machine learning focus on balancing notio...
read it

SalGaze: Personalizing Gaze Estimation Using Visual Saliency
Traditional gaze estimation methods typically require explicit user cali...
read it

Range Adaptation for 3D Object Detection in LiDAR
LiDARbased 3D object detection plays a crucial role in modern autonomou...
read it

Stochastic Conditional Generative Networks with Basis Decomposition
While generative adversarial networks (GANs) have revolutionized machine...
read it

Domaininvariant Learning using Adaptive Filter Decomposition
Domain shifts are frequently encountered in realworld scenarios. In thi...
read it

ScaleEquivariant Neural Networks with Decomposed Convolutional Filters
Encoding the input scale information explicitly into the representation ...
read it

Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors
Deep neural networks (DNNs) are notorious for their vulnerability to adv...
read it

Continuous Dice Coefficient: a Method for Evaluating Probabilistic Segmentations
Objective: Overlapping measures are often utilized to quantify the simil...
read it

Noncontact photoplethysmogram and instantaneous heart rate estimation from infrared face video
Extracting the instantaneous heart rate (iHR) from face videos has been ...
read it

Learning to Collaborate for UserControlled Privacy
It is becoming increasingly clear that users should own and control thei...
read it

Stop memorizing: A datadependent regularization framework for intrinsic pattern learning
Deep neural networks (DNNs) typically have enough capacity to fit random...
read it

RotDCF: Decomposition of Convolutional Filters for RotationEquivariant Deep Networks
Explicit encoding of group actions in deep features makes it possible fo...
read it

DNN or kNN: That is the Generalize vs. Memorize Question
This paper studies the relationship between the classification performed...
read it

Liveness Detection Using Implicit 3D Features
Spoofing attacks are a threat to modern face recognition systems. In thi...
read it

Virtual CNN Branching: Efficient Feature Ensemble for Person ReIdentification
In this paper we introduce an ensemble method for convolutional neural n...
read it

DCFNet: Deep Neural Network with Decomposed Convolutional Filters
Filters in a Convolutional Neural Network (CNN) contain model parameters...
read it

OLÉ: Orthogonal Lowrank Embedding, A Plug and Play Geometric Loss for Deep Learning
Deep neural networks trained using a softmax layer at the top and the cr...
read it

ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks
Hash codes are efficient data representations for coping with the ever g...
read it

LDMNet: Low Dimensional Manifold Regularized Neural Networks
Deep neural networks have proved very successful on archetypal tasks for...
read it

Learning to Succeed while Teaching to Fail: Privacy in Closed Machine Learning Systems
Security, privacy, and fairness have become critical in the era of data ...
read it

Deep Video Deblurring
Motion blur from camera shake is a major problem in videos captured by h...
read it

Selflearning Scenespecific Pedestrian Detectors using a Progressive Latent Model
In this paper, a selflearning approach is proposed towards solving scen...
read it

Not Afraid of the Dark: NIRVIS Face Recognition via Crossspectral Hallucination and Lowrank Embedding
Surveillance cameras today often capture NIR (near infrared) images in l...
read it

Probabilistic FluorescenceBased Synapse Detection
Brain function results from communication between neurons connected by c...
read it

Nonnegative Matrix Underapproximation for Robust Multiple Model Fitting
In this work, we introduce a highly efficient algorithm to address the n...
read it

Fast L1NMF for Multiple Parametric Model Estimation
In this work we introduce a comprehensive algorithmic pipeline for multi...
read it

Generalization Error of Invariant Classifiers
This paper studies the generalization error of invariant classifiers. In...
read it

Tradeoffs between Convergence Speed and Reconstruction Accuracy in Inverse Problems
Solving inverse problems with iterative algorithms is popular, especiall...
read it

Robust Large Margin Deep Neural Networks
The generalization error of deep neural networks via their classificatio...
read it

Fundamental Limits in Multiimage Alignment
The performance of multiimage alignment, bringing different images into...
read it

GraphConnect: A Regularization Framework for Neural Networks
Deep neural networks have proved very successful in domains where large ...
read it

Compressed Nonnegative Matrix Factorization is Fast and Accurate
Nonnegative matrix factorization (NMF) has an established reputation as ...
read it

Removing Camera Shake via Weighted Fourier Burst Accumulation
Numerous recent approaches attempt to remove image blur due to camera sh...
read it

Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
Three important properties of a classification machinery are: (i) the sy...
read it

Data Representation using the Weyl Transform
The Weyl transform is introduced as a rich framework for data representa...
read it

On the Stability of Deep Networks
In this work we study the properties of deep neural networks (DNN) with ...
read it

Random Forests Can Hash
Hash codes are a very efficient data representation needed to be able to...
read it

Dissimilaritybased Sparse Subset Selection
Finding an informative subset of a large collection of data points or mo...
read it

Graph Matching: Relax at Your Own Risk
Graph matchingaligning a pair of graphs to minimize their edge disagr...
read it

A Biclustering Framework for Consensus Problems
We consider grouping as a general characterization for problems such as ...
read it

Learning Transformations for Classification Forests
This work introduces a transformationbased learner model for classifica...
read it

Sparse similaritypreserving hashing
In recent years, a lot of attention has been devoted to efficient neares...
read it

Robust Multimodal Graph Matching: Sparse Coding Meets Graph Matching
Graph matching is a challenging problem with very important applications...
read it

Learning Transformations for Clustering and Classification
A lowrank transformation learning framework for subspace clustering and...
read it

Domaininvariant Face Recognition using Learned Lowrank Transformation
We present a lowrank transformation approach to compensate for face var...
read it

Learning Robust Subspace Clustering
We propose a lowrank transformationlearning framework to robustify sub...
read it

Video Human Segmentation using Fuzzy Object Models and its Application to Body Pose Estimation of Toddlers for Behavior Studies
Video object segmentation is a challenging problem due to the presence o...
read it
Guillermo Sapiro
is this you? claim profile
Guillermo Sapiro is an informatics, electrical engineering and professor who has made a significant contribution to the processing of images. He worked for 15 years at the University of Minnesota before joining Duke University as a Professor. He has also researched image processing in Hewlett Packard Labs and is known for being one of the people who originally developed the LOCOI Compression Algorithm for image lossless compression. It also contributed significantly to the development of the Adobe After Effects rotobrush tool that has been included in the After Effects version since CS5. Adobe uses his research in a variety of projects such as Photoshop and hires his students often. He also teaches a massive open online course on image and video processing through Coursera. The title of the course is “Image and video processing: from Mars to Hollywood with a hospital stop.” He lives with his wife, the two sons and the golden Hummus recorder.