Related papers: Target Detection within Nonhomogeneous Clutter via…
LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds of distant and occluded objects. In this paper, we propose a novel two-stage approach, namely…
We consider the initial situation where a dataset has been over-partitioned into $k$ clusters and seek a domain independent way to merge those initial clusters. We identify the total variation distance (TVD) as suitable for this goal. By…
Classification tasks present challenges due to class imbalances and evolving data distributions. Addressing these issues requires a robust method to handle imbalances while effectively detecting out-of-distribution (OOD) samples not…
The rapid growth of high-dimensional datasets across various scientific domains has created a pressing need for new statistical methods to compare distributions supported on their underlying structures. Assessing similarity between datasets…
Recently, there is a growing interest in the study of median-based algorithms for distributed non-convex optimization. Two prominent such algorithms include signSGD with majority vote, an effective approach for communication reduction via…
Providing quantitative interpretation of coherent nonlinear microscopy images, such as third-harmonic generation (THG), is generally hampered by the complex phase-matching conditions, especially in the presence of sample linear…
Deep Nonnegative Matrix Factorization (deep NMF) has recently emerged as a valuable technique for extracting multiple layers of features across different scales. However, all existing deep NMF models and algorithms have primarily centered…
As human-machine interaction continues to evolve, the capacity for environmental perception is becoming increasingly crucial. Integrating the two most common types of sensory data, images, and point clouds, can enhance detection accuracy.…
Most previous works of outdoor instance segmentation for images only use color information. We explore a novel direction of sensor fusion to exploit stereo cameras. Geometric information from disparities helps separate overlapping objects…
The goal of this paper is to further develop an approach to inverse problems with imperfect forward operators that is based on partially ordered spaces. Studying the dual problem yields useful insights into the convergence of the…
Real-world graphs have inherently complex and diverse topological patterns, known as topological heterogeneity. Most existing works learn graph representation in a single constant curvature space that is insufficient to match the complex…
Self-attention modules have demonstrated remarkable capabilities in capturing long-range relationships and improving the performance of point cloud tasks. However, point cloud objects are typically characterized by complex, disordered, and…
We revisit the classical problem of estimating an unknown distribution from its samples by fitting a mixture model that minimizes cross-entropy loss. Framing the task as a stochastic convex optimization problem over the space of $ M…
3D single object tracking with LiDAR points is an important task in the computer vision field. Previous methods usually adopt the matching-based or motion-centric paradigms to estimate the current target status. However, the former is…
We propose a method to address challenges in unconstrained face detection, such as arbitrary pose variations and occlusions. First, a new image feature called Normalized Pixel Difference (NPD) is proposed. NPD feature is computed as the…
Edge detection is a fundamental task in computer vision. It has made great progress under the development of deep convolutional neural networks (DCNNs), some of which have achieved a beyond human-level performance. However, recent…
This article presents a tool for the detection of non-technical losses, which is being developed within the European INTERPRETER project. The tool employs a hybrid method based on feature detection from smart meter data and grid model…
A new system for object detection in cluttered RGB-D images is presented. Our main contribution is a new method called Bingham Procrustean Alignment (BPA) to align models with the scene. BPA uses point correspondences between oriented…
Equivariant neural networks incorporate symmetries into their architecture, achieving higher generalization performance. However, constructing equivariant neural networks typically requires prior knowledge of data types and symmetries,…
Diabetes prediction is an important data science application in the social healthcare domain. There exist two main challenges in the diabetes prediction task: data heterogeneity since demographic and metabolic data are of different types,…