Set-Type Belief Propagation with Applications to Poisson Multi-Bernoulli
SLAM
May 5, 2023
| | | | |
Computer Science
Electrical Engineering and Systems Science
Artificial Intelligence
Signal Processing
Belief propagation (BP) is a useful probabilistic inference algorithm for
efficiently computing approximate marginal probability densities of random
variables. However, in its standard form, BP is only applicable to the
vector-type random v...
Supervised Training of Neural-Network Quantum States for the Next
Nearest Neighbor Ising model
May 5, 2023
| | | |
Physics
Statistical Mechanics
Quantum Gases
Quantum Physics
Different neural network architectures can be unsupervisedly or supervisedly
trained to represent quantum states. We explore and compare different
strategies for the supervised training of feed forward neural network quantum
states. We empi...
Listen to Look into the Future: Audio-Visual Egocentric Gaze
Anticipation
May 5, 2023
| | | |
Computer Science
Computer Vision and Pattern Recognition
Egocentric gaze anticipation serves as a key building block for the emerging
capability of Augmented Reality. Notably, gaze behavior is driven by both
visual cues and audio signals during daily activities. Motivated by this
observation, we ...
Data-inspired modeling of accidents in traffic flow networks
May 5, 2023
|
Mathematics
Computer Science
Numerical Analysis
Numerical Analysis
We consider hyperbolic partial differential equations (PDEs) for a dynamic
description of the traffic behavior in road networks. These equations are
coupled to a Hawkes process that models traffic accidents taking into account
their self-ex...
Set-Valued Analysis of Generalized Barycentric Coordinates and Their
Geometric Properties
May 5, 2023
Mathematics
Metric Geometry
Letting P be a convex polytope in Rd with n>d vertices, we
study geometric and analytical properties of the set of generalized barycentric
coordinates relative to any point p∈P. We prove that such sets are
polytopes in ...
DBAT: Dynamic Backward Attention Transformer for Material Segmentation
with Cross-Resolution Patches
May 5, 2023
| |
Computer Science
Computer Vision and Pattern Recognition
The objective of dense material segmentation is to identify the material
categories for every image pixel. Recent studies adopt image patches to extract
material features. Although the trained networks can improve the segmentation
performan...
Modeling Model Predictive Control: A Category Theoretic Framework for
Multistage Control Problems
May 5, 2023
| | | | |
Mathematics
Optimization and Control
Category Theory
Model predictive control (MPC) is an optimal control technique which involves
solving a sequence of constrained optimization problems across a given time
horizon. In this paper, we introduce a category theoretic framework for
constructing c...
The Generalized Makeev Problem Revisited
May 5, 2023
| |
Mathematics
Combinatorics
Metric Geometry
Based on a result of Makeev, in 2012 Blagojevi\'c and Karasev proposed the
following problem: given any positive integers m and 1≤ℓ≤k, find
the minimum dimension d=Δ(m;ℓ/k) such that for any m mass
distributions o...
Efficient Treatment of Relativistic Effects with Periodic Density
Functional Methods: Energies, Gradients, and Stress Tensors
May 5, 2023
| |
Physics
Chemical Physics
Mesoscale and Nanoscale Physics
Materials Science
Computational Physics
The implementation of an efficient self-consistent field (SCF) method
including both scalar relativistic effects and spin-orbit interaction in
density functional theory (DFT) is presented. We make use of Gaussian-type
orbitals (GTOs) and al...
3D Small Object Detection with Dynamic Spatial Pruning
May 5, 2023
| | | | |
Computer Science
Computer Vision and Pattern Recognition
In this paper, we propose an efficient feature pruning strategy for 3D small
object detection. Conventional 3D object detection methods struggle on small
objects due to the weak geometric information from a small number of points.
Although ...