Search
Search Results
-
Context feature fusion and enhanced non-maximum suppression for pedestrian detection in crowded scenes
Pedestrian detection has a wide range of applications in the field of multimedia, and significant progress has been made. However, in densely...
-
An improved iterative closest point algorithm based on the particle filter and K-means clustering for fine model matching
The rigid matching of two geometric clouds is vital in the computer vision and its intelligent applications, such as computational geometry,...
-
An Improved Non-Rigid Point Set Registration Algorithm by Preserving Local Topology
AbstractThe previous works on point registration based on graph model formulate registration as a graph matching problem. The key step is to keep...
-
Towards Fine-Grained Optimal 3D Face Dense Registration: An Iterative Dividing and Diffusing Method
Dense vertex-to-vertex correspondence (i.e. registration) between 3D faces is a fundamental and challenging issue for 3D &2D face analysis. While the...
-
SARNet: Semantic Augmented Registration of Large-Scale Urban Point Clouds
Registering urban point clouds is a pretty challenging task due to the large-scale, noise and data incompleteness of LiDAR scanning data. In this... -
Gaussian Mixture Model-Based Registration Network for Point Clouds with Partial Overlap
Mainstream methods of point cloud registration can be divided into two categories: strict point-level correspondence, which is commonly used but... -
Rotation robust non-rigid point set registration with Bayesian student’s t mixture model
Aiming to improve the performance of non-rigid point set registration, this paper proposes a probabilistic method with student’s t mixture model...
-
Joint maximization of accuracy and information for learning the structure of a Bayesian network classifier
Although recent studies have shown that a Bayesian network classifier (BNC) that maximizes the classification accuracy (i.e., minimizes the 0/1 loss...
-
Big topic modeling based on a two-level hierarchical latent Beta-Liouville allocation for large-scale data and parameter streaming
As an extension to the standard symmetric latent Dirichlet allocation topic model, we implement asymmetric Beta-Liouville as a conjugate prior to the...
-
Relative Norm Alignment for Tackling Domain Shift in Deep Multi-modal Classification
Multi-modal learning has gained significant attention due to its ability to enhance machine learning algorithms. However, it brings challenges...
-
Spatiotemporal Cardiac Statistical Shape Modeling: A Data-Driven Approach
Clinical investigations of anatomy’s structural changes over time could greatly benefit from population-level quantification of shape, or... -
Unsupervised Deformable Image Registration with Absent Correspondences in Pre-operative and Post-recurrence Brain Tumor MRI Scans
Registration of pre-operative and post-recurrence brain images is often needed to evaluate the effectiveness of brain gliomas treatment. While recent... -
Magnetic Resonance Image of Breast Segmentation by Multi-Level Thresholding Using Moth-Flame Optimization and Whale Optimization Algorithms
AbstractIn this paper, we propose two breast lesion segmentation methods in dynamic contrast enhanced magnetic resonance image (DCE-MRI) using...
-
Quantile hidden semi-Markov models for multivariate time series
This paper develops a quantile hidden semi-Markov regression to jointly estimate multiple quantiles for the analysis of multivariate time series. The...
-
Gradient-Based Uncertainty for Monocular Depth Estimation
In monocular depth estimation, disturbances in the image context, like moving objects or reflecting materials, can easily lead to erroneous... -
Learning Similarity for Discovering Inspirations of Western Arts in Japanese Culture
Several paintings by Japanese artists in the beginning of 20th century were largely inspired by works of western artists. Finding correspondences... -
2D MRI registration using glowworm swarm optimization with partial opposition-based learning for brain tumor progression
Magnetic resonance imaging (MRI) registration is important in detection, diagnosis, treatment planning, determining radiographic progression,...
-
A Consumer-Theoretic Characterization of Fisher Market Equilibria
In this paper, we bring consumer theory to bear in the analysis of Fisher markets whose buyers have arbitrary continuous, concave, homogeneous (CCH)... -
Towards Understanding Time Varying Triangle Meshes
Time varying meshes are more popular than ever as a representation of deforming shapes, in particular for their versatility and inherent ability to... -
Similar image matching via global topology consensus
Recovering three-dimensional structure from images is one of the important researches in computer vision. The quality of feature matching is one of...