
Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classification
Standard deep learning models that employ the categorical crossentropy ...
read it

Generative Patch Priors for Practical Compressive Image Recovery
In this paper, we propose the generative patch prior (GPP) that defines ...
read it

GraCIAS: Grassmannian of Corrupted Images for Adversarial Security
Input transformation based defense strategies fall short in defending ag...
read it

Unsupervised Pretrained Models from Healthy ADLs Improve Parkinson's Disease Classification of Gait Patterns
Application and use of deep learning algorithms for different healthcare...
read it

AMCLoss: Angular Margin Contrastive Loss for Improved Explainability in Image Classification
Deeplearning architectures for classification problems involve the cros...
read it

HalluciNet: Scene Completion by Exploiting Object Cooccurrence Relationships
We address the new problem of complex scene completion from sparse label...
read it

Topological Descriptors for Parkinson's Disease Classification and Regression Analysis
At present, the vast majority of human subjects with neurological diseas...
read it

Invenio: Discovering Hidden Relationships Between Tasks/Domains Using Structured Meta Learning
Exploiting known semantic relationships between finegrained tasks is cr...
read it

Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning
Learning representations that can disentangle explanatory attributes und...
read it

Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping
Many timeseries classification problems involve developing metrics that...
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

PINet: A Deep Learning Approach to Extract Topological Persistence Images
Topological features such as persistence diagrams and their functional a...
read it

NonParametric Priors For Generative Adversarial Networks
The advent of generative adversarial networks (GAN) has enabled new capa...
read it

Geometry of Deep Generative Models for Disentangled Representations
Deep generative models like variational autoencoders approximate the int...
read it

An Optical FlowBased Approach for MinimallyDivergent Velocimetry Data Interpolation
Threedimensional (3D) biomedical image sets are often acquired with in...
read it

Multiple Subspace Alignment Improves Domain Adaptation
We present a novel unsupervised domain adaptation (DA) method for cross...
read it

RateAdaptive Neural Networks for Spatial Multiplexers
In resourceconstrained environments, one can employ spatial multiplexin...
read it

Perturbation Robust Representations of Topological Persistence Diagrams
Topological methods for data analysis present opportunities for enforcin...
read it

CSVQA: Visual Question Answering with Compressively Sensed Images
Visual Question Answering (VQA) is a complex semantic task requiring bot...
read it

Compressive Light Field Reconstructions using Deep Learning
Light field imaging is limited in its computational processing demands o...
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

Persistent Homology of Attractors For Action Recognition
In this paper, we propose a novel framework for dynamical analysis of hu...
read it

Elastic Functional Coding of Riemannian Trajectories
Visual observations of dynamic phenomena, such as human actions, are oft...
read it

Shape Distributions of Nonlinear Dynamical Systems for Videobased Inference
This paper presents a shapetheoretic framework for dynamical analysis o...
read it

Fast Integral Image Estimation at 1
We propose a framework called ReFInE to directly obtain integral image e...
read it

ReconNet: NonIterative Reconstruction of Images from Compressively Sensed Random Measurements
The goal of this paper is to present a noniterative and more importantl...
read it

Reconstructionfree action inference from compressive imagers
Persistent surveillance from camera networks, such as at parking lots, U...
read it

Interactively Test Driving an Object Detector: Estimating Performance on Unlabeled Data
In this paper, we study the problem of `testdriving' a detector, i.e. a...
read it
Pavan Turaga
is this you? claim profile