Liqun Kuang
YOU?
Author Swipe
View article: Spatiotemporal Contextual 3D Semantic Segmentation for Intelligent Outdoor Mining
Spatiotemporal Contextual 3D Semantic Segmentation for Intelligent Outdoor Mining Open
Three-dimensional semantic segmentation plays a crucial role in accurately identifying terrain features and objects by effectively extracting 3D spatial information from the environment. However, the inherent sparsity of point clouds and u…
View article: ACT-Agent: Affinity-Cross Transformer for Point Cloud Registration via Reinforcement Learning
ACT-Agent: Affinity-Cross Transformer for Point Cloud Registration via Reinforcement Learning Open
Point cloud registration aims to align two sets of point cloud data by determining the geometric transformation between them, specifically rotation and translation. As a fundamental task in 3D computer vision, point cloud registration play…
View article: Act-Agent: Affinity-Cross Transformer for Point Cloud Registration Via Reinforcement Learning
Act-Agent: Affinity-Cross Transformer for Point Cloud Registration Via Reinforcement Learning Open
View article: Small-Sample Target Detection Across Domains Based on Supervision and Distillation
Small-Sample Target Detection Across Domains Based on Supervision and Distillation Open
To address the issues of significant object discrepancies, low similarity, and image noise interference between source and target domains in object detection, we propose a supervised learning approach combined with knowledge distillation. …
View article: MSANet: LiDAR-Camera Online Calibration with Multi-Scale Fusion and Attention Mechanisms
MSANet: LiDAR-Camera Online Calibration with Multi-Scale Fusion and Attention Mechanisms Open
Sensor data fusion is increasingly crucial in the field of autonomous driving. In sensor fusion research, LiDAR and camera have become prevalent topics. However, accurate data calibration from different modalities is essential for effectiv…
View article: A human activity recognition method based on Vision Transformer
A human activity recognition method based on Vision Transformer Open
Human activity recognition has a wide range of applications in various fields, such as video surveillance, virtual reality and human–computer intelligent interaction. It has emerged as a significant research area in computer vision. GCN (G…
View article: Global semantics correlation transmitting and learning for sketch-based cross-domain visual retrieval
Global semantics correlation transmitting and learning for sketch-based cross-domain visual retrieval Open
Sketch-based cross-domain visual data retrieval is the process of searching for images or 3D models using sketches as input. Achieving feature alignment is a significantly challenging task due to the high heterogeneity of cross-domain data…
View article: A multi-scale covariance matrix descriptor and an accurate transformation estimation for robust point cloud registration
A multi-scale covariance matrix descriptor and an accurate transformation estimation for robust point cloud registration Open
This paper presents a robust point cloud registration method based on a multi-scale covariance matrix descriptor and an accurate transformation estimation. Comparing with state-of-the-art feature descriptor such as FPH, 3DSC, Spin Image, e…
View article: Spatial deformable transformer for 3D point cloud registration
Spatial deformable transformer for 3D point cloud registration Open
View article: HAR-ViT:A human activity recognition method based on ViT
HAR-ViT:A human activity recognition method based on ViT Open
Human activity recognition has a wide range of applications in various fields, such as video surveillance, virtual reality, and human-computer intelligent interaction. It has emerged as a significant research area in computer vision. Key a…
View article: Deeppat: Deep Position-Aware Transformer with Mixed Dataset for Robust Point Cloud Registration
Deeppat: Deep Position-Aware Transformer with Mixed Dataset for Robust Point Cloud Registration Open
View article: Improved Robot Path Planning Method Based on Deep Reinforcement Learning
Improved Robot Path Planning Method Based on Deep Reinforcement Learning Open
With the advancement of robotics, the field of path planning is currently experiencing a period of prosperity. Researchers strive to address this nonlinear problem and have achieved remarkable results through the implementation of the Deep…
View article: Influenza trend prediction method combining Baidu index and support vector regression based on an improved particle swarm optimization algorithm
Influenza trend prediction method combining Baidu index and support vector regression based on an improved particle swarm optimization algorithm Open
Web-based search query data have been recognized as valuable data sources for discovering new influenza epidemics. However, selecting search and query keywords and adopting prediction methods pose key challenges to improving the effective…
View article: A Spatiotemporal Brain Network Analysis of Alzheimer’s Disease Based on Persistent Homology
A Spatiotemporal Brain Network Analysis of Alzheimer’s Disease Based on Persistent Homology Open
Current brain network studies based on persistent homology mainly focus on the spatial evolution over multiple spatial scales, and there is little research on the evolution of a spatiotemporal brain network of Alzheimer’s disease (AD). Thi…
View article: Default Mode Network Analysis of APOE Genotype in Cognitively Unimpaired Subjects Based on Persistent Homology
Default Mode Network Analysis of APOE Genotype in Cognitively Unimpaired Subjects Based on Persistent Homology Open
Current researches on default mode network (DMN) in normal elderly have mainly focused on finding some dysfunctional areas with decreased or increased connectivity. The global network dynamics of apolipoprotein E (APOE) e4 allele group is …
View article: White Matter Brain Network Research in Alzheimer’s Disease Using Persistent Features
White Matter Brain Network Research in Alzheimer’s Disease Using Persistent Features Open
Despite the severe social burden caused by Alzheimer’s disease (AD), no drug than can change the disease progression has been identified yet. The structural brain network research provides an opportunity to understand physiological deterio…
View article: Cross-Domain Correspondence for Sketch-Based 3D Model Retrieval Using Convolutional Neural Network and Manifold Ranking
Cross-Domain Correspondence for Sketch-Based 3D Model Retrieval Using Convolutional Neural Network and Manifold Ranking Open
Due to the huge difference in the representation of sketches and 3D models, sketch-based 3D model retrieval is a challenging problem in the areas of graphics and computer vision. Some state-of-the-art approaches usually extract features fr…
View article: Developing a Parametric 3D Face Model Editing Algorithm
Developing a Parametric 3D Face Model Editing Algorithm Open
In the fields of computer graphics and computer vision, a great amount of research and analysis has been conducted on expression-carrying face models. How to construct more realistic and effective 3D face models has become an immense chall…
View article: A Local Feature Descriptor Based on Rotational Volume for Pairwise Registration of Point Clouds
A Local Feature Descriptor Based on Rotational Volume for Pairwise Registration of Point Clouds Open
Aiming to problems in the pairwise registration of point clouds, such as keypoints are difficult to describe accurately, corresponding points are difficult to match accurately and convergence speed is slow due to uncertainty of initial tra…
View article: Metabolic Brain Network Analysis of FDG-PET in Alzheimer’s Disease Using Kernel-Based Persistent Features
Metabolic Brain Network Analysis of FDG-PET in Alzheimer’s Disease Using Kernel-Based Persistent Features Open
Recent research of persistent homology in algebraic topology has shown that the altered network organization of human brain provides a promising indicator of many neuropsychiatric disorders and neurodegenerative diseases. However, the curr…
View article: Efficient numerical schemes for two-dimensional Ginzburg-Landau equation in superconductivity
Efficient numerical schemes for two-dimensional Ginzburg-Landau equation in superconductivity Open
The objective of this paper is to propose some high-order compact schemes for two-dimensional Ginzburg-Landau equation. The space is approximated by high-order compact methods to improve the computational efficiency. Based on Crank-Nicolso…
View article: A concise and persistent feature to study brain resting‐state network dynamics: Findings from the Alzheimer's Disease Neuroimaging Initiative
A concise and persistent feature to study brain resting‐state network dynamics: Findings from the Alzheimer's Disease Neuroimaging Initiative Open
Alzheimer's disease (AD) is the most common type of dementia in the elderly with no effective treatment currently. Recent studies of noninvasive neuroimaging, resting‐state functional magnetic resonance imaging (rs‐fMRI) with graph theoret…