Jeongmin Park
YOU?
Author Swipe
View article: Two-hand static and dynamic Arabic sign language recognition using keypoints and shape descriptors with attention-driven feature fusion
Two-hand static and dynamic Arabic sign language recognition using keypoints and shape descriptors with attention-driven feature fusion Open
Sign language is a vital communication tool for individuals with hearing and speech impairments, yet Arabic Sign Language (ArSL) recognition remains challenging due to signer variability, occlusions, and limited benchmark datasets. To addr…
View article: Bayesian Bootstrap based Gaussian Copula Model for Mixed Data with High Missing Rates
Bayesian Bootstrap based Gaussian Copula Model for Mixed Data with High Missing Rates Open
Missing data is a common issue in various fields such as medicine, social sciences, and natural sciences, and it poses significant challenges for accurate statistical analysis. Although numerous imputation methods have been proposed to add…
View article: Multimodal scene recognition using semantic segmentation and deep learning integration
Multimodal scene recognition using semantic segmentation and deep learning integration Open
Semantic modeling and recognition of indoor scenes present a significant challenge due to the complex composition of generic scenes, which contain a variety of features including themes and objects, makes semantic modeling and indoor scene…
View article: Real-Time Monitoring of Air Pollution and Detection of Illegal Emissions Using Advanced Scanning LiDAR Technology
Real-Time Monitoring of Air Pollution and Detection of Illegal Emissions Using Advanced Scanning LiDAR Technology Open
Air pollution is a persistent environmental and public health challenge, particularly in industrial areas characterized by diverse and diffuse emission sources. This study demonstrates the application of an advanced scanning LiDAR system f…
View article: Holistic Pose Estimation and Dynamic Motion Analysis for Telerehabilitation of Physically Disabled Individuals
Holistic Pose Estimation and Dynamic Motion Analysis for Telerehabilitation of Physically Disabled Individuals Open
Telerehabilitation systems leveraging depth video analysis provide an effective solution for remote physiotherapy, particularly for individuals with physical disabilities. This study presents an advanced exercise classification framework t…
View article: R-CNN Based Vehicle Object Detection via Segmentation Capabilities in Road Scenes
R-CNN Based Vehicle Object Detection via Segmentation Capabilities in Road Scenes Open
In the realm of intelligent transportation systems, vehicle detection and classification stand as pivotal tasks. An effective traffic monitoring system should be capable of detecting, counting, and categorizing moving vehicles. Vehicle cla…
View article: Auxiliary Task Graph Convolution Network: A Skeleton-Based Action Recognition for Practical Use
Auxiliary Task Graph Convolution Network: A Skeleton-Based Action Recognition for Practical Use Open
Graph convolution networks (GCNs) have been extensively researched for action recognition by estimating human skeletons from video clips. However, their image sampling methods are not practical because they require video-length information…
View article: SSDTrain: An Activation Offloading Framework to SSDs for Faster Large Language Model Training
SSDTrain: An Activation Offloading Framework to SSDs for Faster Large Language Model Training Open
The growth rate of the GPU memory capacity has not been able to keep up with that of the size of large language models (LLMs), hindering the model training process. In particular, activations -- the intermediate tensors produced during for…
View article: LSM-GNN: Large-scale Storage-based Multi-GPU GNN Training by Optimizing Data Transfer Scheme
LSM-GNN: Large-scale Storage-based Multi-GPU GNN Training by Optimizing Data Transfer Scheme Open
Graph Neural Networks (GNNs) are widely used today in recommendation systems, fraud detection, and node/link classification tasks. Real world GNNs continue to scale in size and require a large memory footprint for storing graphs and embedd…
View article: Development of early wildfire detecting system using scanning lidar and image processing
Development of early wildfire detecting system using scanning lidar and image processing Open
Wildfires are increasing globally due to climate change. Wildfires can spread rapidly in a short period of time, early detection is important. A CCTV and thermal imaging camera are used for early detection and prevention of wildfires and i…
View article: Weather and Climate conditions over the Arctic and mid-latitude regions affecting air quality
Weather and Climate conditions over the Arctic and mid-latitude regions affecting air quality Open
Recently, it has been noticed that weather and climate changes over the Arctic and mid-latitude regions may have influenced the particulate matter concentrations and haze over East Asia. Among the various weather and climate conditions and…
View article: Research on monitoring illegal air pollution using Scanning Lidar System
Research on monitoring illegal air pollution using Scanning Lidar System Open
The Scanning Lidar System (SMART MK-II) analyzes light backscattered by particles in the air and calculates information about fine dust mass concentration with distance. fine dust concentration in real time and continuously was observed wi…
View article: Fingertip Video Dataset for Non-Invasive Diagnosis of Anemia Using ResNet-18 Classifier
Fingertip Video Dataset for Non-Invasive Diagnosis of Anemia Using ResNet-18 Classifier Open
Hemoglobin is the iron containing protein in red blood cells which carries oxygen from lungs to rest of the body tissues.Accurate measurement of hemoglobin is essential for diagnosing anemia, a condition characterized by a deficiency of re…
View article: Road Traffic Monitoring from Aerial Images Using Template Matching and Invariant Features
Road Traffic Monitoring from Aerial Images Using Template Matching and Invariant Features Open
Road traffic monitoring is an imperative topic widely discussed among researchers.Systems used to monitor traffic frequently rely on cameras mounted on bridges or roadsides.However, aerial images provide the flexibility to use mobile platf…
View article: UNet Based on Multi-Object Segmentation and Convolution Neural Network for Object Recognition
UNet Based on Multi-Object Segmentation and Convolution Neural Network for Object Recognition Open
The recent advancements in vision technology have had a significant impact on our ability to identify multiple objects and understand complex scenes. Various technologies, such as augmented reality-driven scene integration, robotic navigat…
View article: Corrections to “Efficient Multi-Object Recognition Using GMM Segmentation Feature Fusion Approach”
Corrections to “Efficient Multi-Object Recognition Using GMM Segmentation Feature Fusion Approach” Open
Presents corrections to the paper, (Corrections to “Efficient Multi-Object Recognition Using GMM Segmentation Feature Fusion Approach”).
View article: Efficient Object Segmentation and Recognition Using Multi-Layer Perceptron Networks
Efficient Object Segmentation and Recognition Using Multi-Layer Perceptron Networks Open
Object segmentation and recognition is an imperative area of computer vision and machine learning that identifies and separates individual objects within an image or video and determines classes or categories based on their features.The pr…
View article: Remote Sensing Image Interpretation: Deep Belief Networks for Multi-Object Analysis
Remote Sensing Image Interpretation: Deep Belief Networks for Multi-Object Analysis Open
Object Classification in Remote Sensing Imagery holds paramount importance for extracting meaningful insights from complex aerial scenes. Conventional methods encounter challenges in achieving precision amidst diverse landscape features. T…
View article: Efficient Multi-Object Recognition Using GMM Segmentation Feature Fusion Approach
Efficient Multi-Object Recognition Using GMM Segmentation Feature Fusion Approach Open
Machines need to be able to recognize and understand complex visual surroundings to function at their best in a variety of contexts. Here, we address the difficult problem of multi-object recognition to obtain a sophisticated knowledge of …
View article: Enhanced Object Detection and Classification via Multi-Method Fusion
Enhanced Object Detection and Classification via Multi-Method Fusion Open
Advances in machine vision systems have revolutionized applications such as autonomous driving, robotic navigation, and augmented reality.Despite substantial progress, challenges persist, including dynamic backgrounds, occlusion, and limit…
View article: Empirical Analysis of Honeybees Acoustics as Biosensors Signals for Swarm Prediction in Beehives
Empirical Analysis of Honeybees Acoustics as Biosensors Signals for Swarm Prediction in Beehives Open
Honeybees play a vital role in preservation of an healthy environment. Bees not only provide pollination services but also produce honey, beeswax, and royal jelly. Beekeeping has a rich history and substantial economic potential worldwide,…
View article: Instance-Based Lossless Summarization of Knowledge Graph With Optimized Triples and Corrections (IBA-OTC)
Instance-Based Lossless Summarization of Knowledge Graph With Optimized Triples and Corrections (IBA-OTC) Open
Knowledge graph (KG) summarization facilitates efficient information retrieval for exploring complex structural data. For fast information retrieval, it requires processing on redundant data. However, it necessitates the completion of info…
View article: CODAG: Characterizing and Optimizing Decompression Algorithms for GPUs
CODAG: Characterizing and Optimizing Decompression Algorithms for GPUs Open
Data compression and decompression have become vital components of big-data applications to manage the exponential growth in the amount of data collected and stored. Furthermore, big-data applications have increasingly adopted GPUs due to …
View article: Accelerating Sampling and Aggregation Operations in GNN Frameworks with GPU Initiated Direct Storage Accesses
Accelerating Sampling and Aggregation Operations in GNN Frameworks with GPU Initiated Direct Storage Accesses Open
Graph Neural Networks (GNNs) are emerging as a powerful tool for learning from graph-structured data and performing sophisticated inference tasks in various application domains. Although GNNs have been shown to be effective on modest-sized…
View article: Postures anomaly tracking and prediction learning model over crowd data analytics
Postures anomaly tracking and prediction learning model over crowd data analytics Open
Innovative technology and improvements in intelligent machinery, transportation facilities, emergency systems, and educational services define the modern era. It is difficult to comprehend the scenario, do crowd analysis, and observe perso…
View article: GPU-Initiated On-Demand High-Throughput Storage Access in the BaM System Architecture
GPU-Initiated On-Demand High-Throughput Storage Access in the BaM System Architecture Open
Graphics Processing Units (GPUs) have traditionally relied on the host CPU to initiate access to the data storage. This approach is well-suited for GPU applications with known data access patterns that enable partitioning of their dataset …
View article: Aerial Insights: Deep Learning-Based Human Action Recognition in Drone Imagery
Aerial Insights: Deep Learning-Based Human Action Recognition in Drone Imagery Open
Human action recognition is critical because it allows machines to comprehend and interpret human behavior, which has several real-world applications such as video surveillance, robot-human collaboration, sports analysis, and entertainment…
View article: An Elliptical Modeling Supported System for Human Action Deep Recognition Over Aerial Surveillance
An Elliptical Modeling Supported System for Human Action Deep Recognition Over Aerial Surveillance Open
The advancement of computer vision technology has led to the development of sophisticated algorithms capable of accurately recognizing human actions from red-green-blue videos recorded by drone cameras. Hence, possessing an exceptional pot…