Search Results for author:
Found 40 papers, 8 papers with code
Attention Based Machine Learning Methods for Data Reduction with Guaranteed Error Bounds
To address this challenge, data compression or reduction techniques are crucial.
Video-based Pedestrian and Vehicle Traffic Analysis During Football Games
This paper utilizes video analytics to study pedestrian and vehicle traffic behavior, focusing on analyzing traffic patterns during football gamedays.
MTDT: A Multi-Task Deep Learning Digital Twin
MTDT enables accurate, fine-grained estimation of loop detector waveform time series for each lane of movement, alongside successful estimation of several MOEs for each lane group associated with a traffic phase concurrently and for all approaches of an arbitrary urban intersection.
Machine Learning Techniques for Data Reduction of Climate Applications
Scientists conduct large-scale simulations to compute derived quantities-of-interest (QoI) from primary data.
Machine Learning Techniques for Data Reduction of CFD Applications
We present an approach called guaranteed block autoencoder that leverages Tensor Correlations (GBATC) for reducing the spatiotemporal data generated by computational fluid dynamics (CFD) and other scientific applications.
Graph Attention Network for Lane-Wise and Topology-Invariant Intersection Traffic Simulation
Traffic congestion has significant economic, environmental, and social ramifications.
MGARD: A multigrid framework for high-performance, error-controlled data compression and refactoring
We describe MGARD, a software providing MultiGrid Adaptive Reduction for floating-point scientific data on structured and unstructured grids.
Spatiotemporally adaptive compression for scientific dataset with feature preservation -- a case study on simulation data with extreme climate events analysis
Additionally, we integrate spatiotemporal feature detection with data compression and demonstrate that performing adaptive error-bounded compression in higher dimensional space enables greater compression ratios, leveraging the error propagation theory of a transformation-based compressor.
A Spatiotemporal Correspondence Approach to Unsupervised LiDAR Segmentation with Traffic Applications
We address the problem of unsupervised semantic segmentation of outdoor LiDAR point clouds in diverse traffic scenarios.
An Efficient Semi-Automated Scheme for Infrastructure LiDAR Annotation
Specifically, we introduce a human-in-the-loop schema in which annotators recursively fix and refine annotations imperfectly predicted by our tool and incrementally add them to the training dataset to obtain better SOT and MOT models.
Scalable Hybrid Learning Techniques for Scientific Data Compression
Data compression is becoming critical for storing scientific data because many scientific applications need to store large amounts of data and post process this data for scientific discovery.
Expressing linear equality constraints in feedforward neural networks
Elimination of the auxiliary variables leads to a dual minimization problem on the Lagrange multipliers introduced to satisfy the linear constraints.
Learning Canonical Embeddings for Unsupervised Shape Correspondence with Locally Linear Transformations
We present a new approach to unsupervised shape correspondence learning between pairs of point clouds.
Towards Improving the Generation Quality of Autoregressive Slot VAEs
We propose two improvements that strengthen object correlation learning.
Self-Supervised Robust Scene Flow Estimation via the Alignment of Probability Density Functions
Scene flow estimation is therefore converted into the problem of recovering motion from the alignment of probability density functions, which we achieve using a closed-form expression of the classic Cauchy-Schwarz divergence.
Self-Supervised Learning
Self-supervised Scene Flow Estimation
Learning Scene Dynamics from Point Cloud Sequences
Our experimental evaluation confirms that recurrent processing of point cloud sequences results in significantly better SSFE compared to using only two frames.
Generating Scenes with Latent Object Models
We introduce a structured latent variable model that learns the underlying data-generating process for a dataset of scenes.
Domain-guided Machine Learning for Remotely Sensed In-Season Crop Growth Estimation
Results from this study exhibit both the viability of NNs in crop growth stage estimation (CGSE) and the benefits of using domain knowledge.
Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations
Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize.
Hybrid Generative Models for Two-Dimensional Datasets
Two-dimensional array-based datasets are pervasive in a variety of domains.
Neural data compression for physics plasma simulation
We present a VAE-based data compression method, called VAe Physics Optimized Reduction (VAPOR), to compress scientific data while preserving physics constraints.
SparsePipe: Parallel Deep Learning for 3D Point Clouds
Besides, it suitably partitions the model when the GPUs are heterogeneous such that the computing is load-balanced with reduced communication overhead.
A Unified Framework for Multiclass and Multilabel Support Vector Machines
We propose a straightforward extension to the SVM to cope with multiclass and multilabel classification problems within a unified framework.
Intelligent Intersection: Two-Stream Convolutional Networks for Real-time Near Accident Detection in Traffic Video
In this paper, we propose a two-stream Convolutional Network architecture that performs real-time detection, tracking, and near accident detection of road users in traffic video data.
Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer's Disease Classification
Comparative analysis show that the sensitivity analysis based approach has difficulty handling loosely distributed cerebral cortex, and approaches based on visualization of activations are constrained by the resolution of the convolutional layer.
Global Model Interpretation via Recursive Partitioning
To generate the interpretation tree, a unified process recursively partitions the input variable space by maximizing the difference in the average contribution of the split variable between the divided spaces.
A Gaussian mixture model representation of endmember variability in hyperspectral unmixing
We show, given the GMM starting premise, that the distribution of the mixed pixel (under the linear mixing model) is also a GMM (and this is shown from two perspectives).
A Category Space Approach to Supervised Dimensionality Reduction
To this end, we set up a model in which each class is represented as a 1D subspace of the vector space formed by the features.
A Compositional Approach to Language Modeling
Traditional language models treat language as a finite state automaton on a probability space over words.
A Grassmannian Graph Approach to Affine Invariant Feature Matching
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.
Spatial Scaling of Satellite Soil Moisture using Temporal Correlations and Ensemble Learning
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 finer scales.
Disaggregation of SMAP L3 Brightness Temperatures to 9km using Kernel Machines
In this study, a machine learning algorithm is used for disaggregation of SMAP brightness temperatures (T$_{\textrm{B}}$) from 36km to 9km.
Contrastive Entropy: A new evaluation metric for unnormalized language models
In this paper, we address the last problem and propose a new discriminative entropy based intrinsic metric that works for both traditional word level models and unnormalized language models like sentence level models.
A spatial compositional model (SCM) for linear unmixing and endmember uncertainty estimation
In this paper, we show that NCM can be used for calculating the uncertainty of the estimated endmembers with spatial priors incorporated for better unmixing.
Disaggregation of Remotely Sensed Soil Moisture in Heterogeneous Landscapes using Holistic Structure based Models
The KLD of the disaggregated estimates generated by the SRRM is at least four orders of magnitude lower than those for the PRI disaggregated estimates, while the computational time needed was reduced by three times.
Downscaling Microwave Brightness Temperatures Using Self Regularized Regressive Models
A novel algorithm is proposed to downscale microwave brightness temperatures ($\mathrm{T_B}$), at scales of 10-40 km such as those from the Soil Moisture Active Passive mission to a resolution meaningful for hydrological and agricultural applications.
A Riemannian Framework for Matching Point Clouds Represented by the Schrodinger Distance Transform
In this paper, we use the well known Riemannian framework never before used for point cloud matching, and present a novel matching algorithm.
A fast eikonal equation solver using the Schrodinger wave equation
In our framework, a solution to the eikonal equation is obtained in the limit as Planck's constant $\hbar$ (treated as a free parameter) tends to zero of the solution to the corresponding linear Schr\"odinger equation.
Gradient density estimation in arbitrary finite dimensions using the method of stationary phase
We prove that the density function of the gradient of a sufficiently smooth function $S : \Omega \subset \mathbb{R}^d \rightarrow \mathbb{R}$, obtained via a random variable transformation of a uniformly distributed random variable, is increasingly closely approximated by the normalized power spectrum of $\phi=\exp\left(\frac{iS}{\tau}\right)$ as the free parameter $\tau \rightarrow 0$.
A new variational principle for the Euclidean distance function: Linear approach to the non-linear eikonal problem
In other words, when $S$ and $\phi$ are related by $\phi = \exp \left(-\frac{S}{\tau} \right)$ and $\phi$ satisfies a specific linear differential equation corresponding to the extremum of a variational problem, we obtain the approximate Euclidean distance function $S = -\tau \log(\phi)$ which converges to the true solution in the limit as $\tau \rightarrow 0$.
