113 citations · 328 across the 16 of their papers we have counts for
20 papers
Spatiotemporally adaptive compression for scientific dataset with feature preservation -- a case study on simulation data with extreme climate events analysis
Qian Gong, Chengzhu Zhang, Xin Liang +10
Scientific discoveries are increasingly constrained by limited storage space and I/O capacities. For time-series simulations and experiments, their data often need to be decimated…
Intelligent Intersection: Two-Stream Convolutional Networks for Real-time Near Accident Detection in Traffic Video
Xiaohui Huang, Pan He, Anand Rangarajan +1
In Intelligent Transportation System, real-time systems that monitor and analyze road users become increasingly critical as we march toward the smart city era. Vision-based framewo…
Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer's Disease Classification
Chengliang Yang, Anand Rangarajan, Sanjay Ranka
We develop three efficient approaches for generating visual explanations from 3D convolutional neural networks (3D-CNNs) for Alzheimer's disease classification. One approach conduc…
Global Model Interpretation via Recursive Partitioning
Chengliang Yang, Anand Rangarajan, Sanjay Ranka
In this work, we propose a simple but effective method to interpret black-box machine learning models globally. That is, we use a compact binary tree, the interpretation tree, to e…
A Gaussian mixture model representation of endmember variability in hyperspectral unmixing
Yuan Zhou, Anand Rangarajan, Paul D. Gader
Hyperspectral unmixing while considering endmember variability is usually performed by the normal compositional model (NCM), where the endmembers for each pixel are assumed to be s…
A Category Space Approach to Supervised Dimensionality Reduction
Anthony O. Smith, Anand Rangarajan
Supervised dimensionality reduction has emerged as an important theme in the last decade. Despite the plethora of models and formulations, there is a lack of a simple model which a…
A Compositional Approach to Language Modeling
Kushal Arora, Anand Rangarajan
Traditional language models treat language as a finite state automaton on a probability space over words. This is a very strong assumption when modeling something inherently comple…
Disaggregation of SMAP L3 Brightness Temperatures to 9km using Kernel Machines
Subit Chakrabarti, Tara Bongiovanni, Jasmeet Judge +2
In this study, a machine learning algorithm is used for disaggregation of SMAP brightness temperatures (T) from 36km to 9km. It uses image segmentation to cluster th…
A Grassmannian Graph Approach to Affine Invariant Feature Matching
Mark Moyou, John Corring, Adrian Peter +1
In this work, we present a novel and practical approach to address one of the longstanding problems in computer vision: 2D and 3D affine invariant feature matching. Our Grassmannia…
Spatial Scaling of Satellite Soil Moisture using Temporal Correlations and Ensemble Learning
Subit Chakrabarti, Jasmeet Judge, Tara Bongiovanni +2
A novel algorithm is developed to downscale soil moisture (SM), obtained at satellite scales of 10-40 km by utilizing its temporal correlations to historical auxiliary data at fine…
Contrastive Entropy: A new evaluation metric for unnormalized language models
Kushal Arora, Anand Rangarajan
Perplexity (per word) is the most widely used metric for evaluating language models. Despite this, there has been no dearth of criticism for this metric. Most of these criticisms c…
A spatial compositional model (SCM) for linear unmixing and endmember uncertainty estimation
Yuan Zhou, Anand Rangarajan, Paul Gader
The normal compositional model (NCM) has been extensively used in hyperspectral unmixing. However, most of the previous research has focused on estimation of endmembers and/or thei…
Randomized Block Subgradient Methods for Convex Nonsmooth and Stochastic Optimization
Qi Deng, Guanghui Lan, Anand Rangarajan
Block coordinate descent methods and stochastic subgradient methods have been extensively studied in optimization and machine learning. By combining randomized block sampling with…
Downscaling Microwave Brightness Temperatures Using Self Regularized Regressive Models
Subit Chakrabarti, Jasmeet Judge, Anand Rangarajan +1
A novel algorithm is proposed to downscale microwave brightness temperatures (), at scales of 10-40 km such as those from the Soil Moisture Active Passive mission to…
Error bounds for gradient density estimation computed from a finite sample set using the method of stationary phase
Karthik S. Gurumoorthy, Anand Rangarajan
For a twice continuously differentiable function , we define the density function of its gradient (derivative in one dimension) as a random variable transformat…
A fast eikonal equation solver using the Schrodinger wave equation
Karthik S. Gurumoorthy, Adrian M. Peter, Birmingham Hang Guan +1
We use a Schrödinger wave equation formalism to solve the eikonal equation. In our framework, a solution to the eikonal equation is obtained in the limit as Planck's constant $\hba…
Gradient density estimation in arbitrary finite dimensions using the method of stationary phase
Karthik S. Gurumoorthy, Anand Rangarajan, John Corring
We prove that the density function of the gradient of a sufficiently smooth function , obtained via a random variable transformati…
A new variational principle for the Euclidean distance function: Linear approach to the non-linear eikonal problem
Karthik S. Gurumoorthy, Anand Rangarajan
We present a fast convolution-based technique for computing an approximate, signed Euclidean distance function on a set of 2D and 3D grid locations. Instead of solving the non-…
An application of the stationary phase method for estimating probability densities of function derivatives
Karthik S. Gurumoorthy, Anand Rangarajan, Arunava Banerjee
We prove a novel result wherein the density function of the gradients---corresponding to density function of the derivatives in one dimension---of a thrice differentiable function…
Distance Transform Gradient Density Estimation using the Stationary Phase Approximation
Karthik S. Gurumoorthy, Anand Rangarajan
The complex wave representation (CWR) converts unsigned 2D distance transforms into their corresponding wave functions. Here, the distance transform S(X) appears as the phase of th…