arXiv research

Paper develops a new method to analyze 3D tree-like objects.

This research detects and identifies human-made objects in 3D point clouds using novel methods.

New approach handles stochastic and partially-observable environments using discrete autoencoders and Monte Carlo tree search.

Python tools for 3D shape analysis on Kendall's space.

3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches learn such features either using structured data representations (voxel grids and o…

We develop three efficient approaches for generating visual explanations from 3D convolutional neural networks (3D-CNNs) for Alzheimer's disease classification. One approach conducts sensitivity analysis on hierarchical 3D image segmentation, and the other two visualize network activations on a spatial map. Visual chec…

Improved 3D LiDAR data classification using product coefficients.

Graph refinement, or the task of obtaining subgraphs of interest from over-complete graphs, can have many varied applications. In this work, we extract trees or collection of sub-trees from image data by, first deriving a graph-based representation of the volumetric data and then, posing the tree extraction as a graph …

Equivariant diffusion model generates 3D molecules efficiently.

The polynomial affine model of gravity is explored in 3D, focusing on cosmological solutions.

This paper finds efficient algorithms for approximating Markov networks with k-tree topologies.

3D Convolutional Neural Networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. However, interpreting the decision making process of these 3D-CNNs is still an infeasible task. In this paper, we present a unique 3D-CNN based Gradient-weighted Class Activation Mapping method (3D…

Generative modeling of 3D shapes has become an important problem due to its relevance to many applications across Computer Vision, Graphics, and VR. In this paper we build upon recently introduced 3D mesh-convolutional Variational AutoEncoders which have shown great promise for learning rich representations of deformab…

Optimal Survival Trees improve accuracy in medical data analysis.

New 3D protein analysis methods improve accuracy.

Existing networks directly learn feature representations on 3D point clouds for shape analysis. We argue that 3D point clouds are highly redundant and hold irregular (permutation-invariant) structure, which makes it difficult to achieve inter-class discrimination efficiently. In this paper, we propose a two-faceted sol…

Random forests are a learning algorithm proposed by Breiman [Mach. Learn. 45 (2001) 5--32] that combines several randomized decision trees and aggregates their predictions by averaging. Despite its wide usage and outstanding practical performance, little is known about the mathematical properties of the procedure. This…

Understanding the three-dimensional (3D) structure of the genome is essential for elucidating vital biological processes and their links to human disease. To determine how the genome folds within the nucleus, chromosome conformation capture methods such as HiC have recently been employed. However, computational methods…

Enhanced 3D shape analysis using information geometry.

A novel 3D shape registration method using spectral graph embedding and probabilistic matching.

New framework segments 3D scenes using neural algorithms and sub-Riemannian geometry.

3D convolutional neural networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. In this paper, we present a 3D-CNN based method to learn distinct local geometric features of interest within an object. In this context, the voxelized representation may not be sufficient to captu…

Discover gaps in q-series exponents for 3d N=2 theories.

New tree splitting criteria improve probabilistic predictions.

New benchmark for non-rigid 3D human shape retrieval.

Paper proposes Roweisposes for 3D action recognition using generalized eigenvalue problem.

3D models vulnerable to adversarial attacks, new method improves success rate and naturalness.

Study 3d N=1 vacua from M-theory compactification on Spin(7) space.

Constructing of molecular structural models from Cryo-Electron Microscopy (Cryo-EM) density volumes is the critical last step of structure determination by Cryo-EM technologies. Methods have evolved from manual construction by structural biologists to perform 6D translation-rotation searching, which is extremely comput…

Regression Trees analyze stock returns, revealing market excess return as the most informative factor.

Paper predicts TUG score from gait characteristics using machine learning.

The paper certifies decision trees against evasion attacks using program analysis.

Improved 3D ECG feature attributions for clinical interpretation.

3D U-Net improves kidney and tumor segmentation from CT scans.

Study of asymptotics of meromorphic 3D-index as q approaches 1.

Large prospective epidemiological studies acquire cardiovascular magnetic resonance (CMR) images for pre-symptomatic populations and follow these over time. To support this approach, fully automatic large-scale 3D analysis is essential. In this work, we propose a novel deep neural network using both CMR images and pati…

This paper considers object detection and 3D estimation using an FMCW radar. The state-of-the-art deep learning framework is employed instead of using traditional signal processing. In preparing the radar training data, the ground truth of an object orientation in 3D space is provided by conducting image analysis, of w…

In this paper, we have proposed a brain signal classification method, which uses eigenvalues of the covariance matrix as features to classify images (topomaps) created from the brain signals. The signals are recorded during the answering of 2D and 3D questions. The system is used to classify the correct and incorrect a…

This work analyzes tree-based methods from a ranking perspective, providing insights and new statistics.

Decision tree learning heuristics fail even in smoothed analysis for complex targets.

Proposes a new method for subgroup analysis using optimal trees with parameter fusion.

Paper uses RL for high-level character control in 3D environments.

When using Convolutional Neural Networks (CNNs) for segmentation of organs and lesions in medical images, the conventional approach is to work with inputs and outputs either as single slice (2D) or whole volumes (3D). One common alternative, in this study denoted as pseudo-3D, is to use a stack of adjacent slices as in…

Decision tree classifiers are a widely used tool in data stream mining. The use of confidence intervals to estimate the gain associated with each split leads to very effective methods, like the popular Hoeffding tree algorithm. From a statistical viewpoint, the analysis of decision tree classifiers in a streaming setti…

Regression trees learn gradients of differentiable functions.

Advanced 3D metrology technologies such as Coordinate Measuring Machine (CMM) and laser 3D scanners have facilitated the collection of massive point cloud data, beneficial for process monitoring, control and optimization. However, due to their high dimensionality and structure complexity, modeling and analysis of point…

In this paper we study supersymmetric co-dimension 2 and 4 defects in the compactification of the 6d $(2,0)$ theory of type $A_{N-1}$ on a 3-manifold $M$. The so-called 3d-3d correspondence is a relation between complexified Chern-Simons theory (with gauge group $SL(N, \mathbb{C})$) on $M$ and a 3d $\mathcal{N}=2$ theo…

We consider the problem of estimating the evolutionary history of a set of species (phylogeny or species tree) from several genes. It is known that the evolutionary history of individual genes (gene trees) might be topologically distinct from each other and from the underlying species tree, possibly confounding phyloge…