
-
Recovering Trajectories of Unmarked Joints in 3D Human Actions Using Latent Space Optimization
Motion capture (mocap) and time-of-flight based sensing of human actions...
read it
-
Generative Patch Priors for Practical Compressive Image Recovery
In this paper, we propose the generative patch prior (GPP) that defines ...
read it
-
Designing Accurate Emulators for Scientific Processes using Calibration-Driven Deep Models
Predictive models that accurately emulate complex scientific processes c...
read it
-
Improved Surrogates in Inertial Confinement Fusion with Manifold and Cycle Consistencies
Neural networks have become very popular in surrogate modeling because o...
read it
-
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking
In the past few years, generative models like Generative Adversarial Net...
read it
-
Merlin: Enabling Machine Learning-Ready HPC Ensembles
With the growing complexity of computational and experimental facilities...
read it
-
Extreme Few-view CT Reconstruction using Deep Inference
Reconstruction of few-view x-ray Computed Tomography (CT) data is a high...
read it
-
Parallelizing Training of Deep Generative Models on Massive Scientific Datasets
Training deep neural networks on large scientific data is a challenging ...
read it
-
Exploring Generative Physics Models with Scientific Priors in Inertial Confinement Fusion
There is significant interest in using modern neural networks for scient...
read it
-
Improving Limited Angle CT Reconstruction with a Robust GAN Prior
Limited angle CT reconstruction is an under-determined linear inverse pr...
read it
-
Function Preserving Projection for Scalable Exploration of High-Dimensional Data
We present function preserving projections (FPP), a scalable linear proj...
read it
-
Scalable Topological Data Analysis and Visualization for Evaluating Data-Driven Models in Scientific Applications
With the rapid adoption of machine learning techniques for large-scale a...
read it
-
SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
Unsupervised domain adaptation aims to transfer and adapt knowledge lear...
read it
-
MR-GAN: Manifold Regularized Generative Adversarial Networks
Despite the growing interest in generative adversarial networks (GANs), ...
read it
-
MimicGAN: Corruption-Mimicking for Blind Image Recovery & Adversarial Defense
Solving inverse problems continues to be a central challenge in computer...
read it
-
Multiple Subspace Alignment Improves Domain Adaptation
We present a novel unsupervised domain adaptation (DA) method for cross-...
read it
-
Unsupervised Dimension Selection using a Blue Noise Spectrum
Unsupervised dimension selection is an important problem that seeks to r...
read it
-
Understanding Deep Neural Networks through Input Uncertainties
Techniques for understanding the functioning of complex machine learning...
read it
-
An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks
Solving inverse problems continues to be a challenge in a wide array of ...
read it
-
Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion
Computed Tomography (CT) reconstruction is a fundamental component to a ...
read it
-
Influential Sample Selection: A Graph Signal Processing Approach
With the growing complexity of machine learning techniques, understandin...
read it
-
Bootstrapping Graph Convolutional Neural Networks for Autism Spectrum Disorder Classification
Using predictive models to identify patterns that can act as biomarkers ...
read it
-
Diversity Promoting Online Sampling for Streaming Video Summarization
Many applications benefit from sampling algorithms where a small number ...
read it
-
A Riemannian Framework for Statistical Analysis of Topological Persistence Diagrams
Topological data analysis is becoming a popular way to study high dimens...
read it
-
Elastic Functional Coding of Riemannian Trajectories
Visual observations of dynamic phenomena, such as human actions, are oft...
read it
-
Interactively Test Driving an Object Detector: Estimating Performance on Unlabeled Data
In this paper, we study the problem of `test-driving' a detector, i.e. a...
read it