Soon Ki Jung
YOU?
Author Swipe
View article: Analysis of 3D Distribution Maps of Body Composition Using 3D Abdominal Computed Tomography and Its Clinical Applications
Analysis of 3D Distribution Maps of Body Composition Using 3D Abdominal Computed Tomography and Its Clinical Applications Open
Body composition analysis provides essential evidence for evaluating patient health, predicting disease risk, and guiding personalized treatment. Abdominal computed tomography (CT) enables high-resolution visualization of skeletal muscle, …
View article: From Data to Decisions: The Power of Machine Learning in Business Recommendations
From Data to Decisions: The Power of Machine Learning in Business Recommendations Open
This research aims to explore the impact of Machine Learning (ML) on the evolution and efficacy of Recommendation Systems (RS), particularly in the context of their growing significance in commercial business environments. Methodologically…
View article: Edge-Preserving Probabilistic Downsampling for Reliable Medical Segmentation in Resource-Constrained Environments
Edge-Preserving Probabilistic Downsampling for Reliable Medical Segmentation in Resource-Constrained Environments Open
Downsampling, often necessitated due to resource constraints such as limited memory, development timelines, or the need to accelerate learning from large volumes of unlabeled medical data, results in the loss of fine-grained details, inclu…
View article: Mamba in Vision: A Comprehensive Survey of Techniques and Applications
Mamba in Vision: A Comprehensive Survey of Techniques and Applications Open
Mamba is emerging as a novel approach to overcome the challenges faced by Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in computer vision. While CNNs excel at extracting local features, they often struggle to capture…
View article: Toward a Privacy-Preserving Face Recognition System: A Survey of Leakages and Solutions
Toward a Privacy-Preserving Face Recognition System: A Survey of Leakages and Solutions Open
Recent advancements in face recognition (FR) technology in surveillance systems make it possible to monitor a person as they move around. FR gathers a lot of information depending on the quantity and data sources. The most severe privacy c…
View article: Pixel-associated autoencoder for hyperspectral anomaly detection
Pixel-associated autoencoder for hyperspectral anomaly detection Open
Autoencoders (AEs) are central to hyperspectral anomaly detection, given their impressive efficacy. However, the current methodologies often neglect the global pixel similarity of the hyperspectral image (HsI), thereby limiting reconstruct…
View article: Towards Efficient and Accurate CT Segmentation via Edge-Preserving Probabilistic Downsampling
Towards Efficient and Accurate CT Segmentation via Edge-Preserving Probabilistic Downsampling Open
Downsampling images and labels, often necessitated by limited resources or to expedite network training, leads to the loss of small objects and thin boundaries. This undermines the segmentation network's capacity to interpret images accura…
View article: Face De-Identification Using Face Caricature
Face De-Identification Using Face Caricature Open
Face privacy concerns revolve around the ethical, social, and technological implications of collecting, storing, and using facial data. With the advancement of deep learning techniques, realistic face privacy involves techniques that obscu…
View article: A Scene-Specific Object Detection System Utilizing the Advantages of Fixed-Location Cameras
A Scene-Specific Object Detection System Utilizing the Advantages of Fixed-Location Cameras Open
Jin Ho Lee, In Su Kim, Hector Acosta, Hyeong Bok Kim, Seung Won Lee, and Soon Ki Jung. Journal of information and communication convergence engineering 2023;21:329-36. https://doi.org/10.56977/jicce.2023.21.4.329
View article: High-Quality Face Caricature via Style Translation
High-Quality Face Caricature via Style Translation Open
Caricature is an exaggerated form of artistic portraiture that accentuates unique yet subtle characteristics of human faces. Recently, advancements in deep end-to-end techniques have yielded encouraging outcomes in capturing both style and…
View article: HeightNet: Monocular Object Height Estimation
HeightNet: Monocular Object Height Estimation Open
Monocular depth estimation is a traditional computer vision task that predicts the distance of each pixel relative to the camera from one 2D image. Relative height information about objects lying on a ground plane can be calculated through…
View article: High-Quality Face Caricature via Style Translation
High-Quality Face Caricature via Style Translation Open
Caricature is an exaggerated form of artistic portraiture that accentuates unique yet subtle characteristics of human faces. Recently, advancements in deep end-to-end techniques have yielded encouraging outcomes in capturing both style and…
View article: Proceedings of the SIGGRAPH Asia 2022 Real-Time Live!
Proceedings of the SIGGRAPH Asia 2022 Real-Time Live! Open
Shader Park is an open-source JavaScript library and community for creating interactive 2D and 3D shaders. It features a live-coding environment that allows the community to share their creations. The library abstracts signed distance fiel…
View article: Development of STEM-Based AI Education Program for Sustainable Improvement of Elementary Learners
Development of STEM-Based AI Education Program for Sustainable Improvement of Elementary Learners Open
Recent years have seen tremendous technology and research development in the field of artificial intelligence (AI). Initiatives are being made to build or employ AI in various domains of society. The field of education is experiencing the …
View article: Siamese-Based Attention Learning Networks for Robust Visual Object Tracking
Siamese-Based Attention Learning Networks for Robust Visual Object Tracking Open
Tracking with the siamese network has recently gained enormous popularity in visual object tracking by using the template-matching mechanism. However, using only the template-matching process is susceptible to robust target tracking becaus…
View article: Designing Gamified Application: An Effective Integration of Augmented Reality to Support Learning
Designing Gamified Application: An Effective Integration of Augmented Reality to Support Learning Open
Early childhood learning is an important concern for the concept building of children. Students have been taught with traditional methods from the beginning. However, these methods lack kids’ attention. Application of Augmented Reality (AR…
View article: Multi-Modal Data Analysis Based Game Player Experience Modeling Using LSTM-DNN
Multi-Modal Data Analysis Based Game Player Experience Modeling Using LSTM-DNN Open
Game player modeling is a paradigm of computational models to exploit players’ behavior and experience using game and player analytics. Player modeling refers to descriptions of players based on frameworks of data derived from the interact…
View article: Siamese High-Level Feature Refine Network for Visual Object Tracking
Siamese High-Level Feature Refine Network for Visual Object Tracking Open
Siamese network-based trackers are broadly applied to solve visual tracking problems due to its balanced performance in terms of speed and accuracy. Tracking desired objects in challenging scenarios is still one of the fundamental concerns…
View article: Meta-analysis of Prevalence of Depression, Anxiety and Stress Among University Students
Meta-analysis of Prevalence of Depression, Anxiety and Stress Among University Students Open
Background: The global burden on mental disorders have become too advanced with serious consequences on health and society. Over the years, depression, stress, and anxiety have become more common symptoms which affect all over population p…
View article: Learning Soft Mask Based Feature Fusion with Channel and Spatial Attention for Robust Visual Object Tracking
Learning Soft Mask Based Feature Fusion with Channel and Spatial Attention for Robust Visual Object Tracking Open
We propose to improve the visual object tracking by introducing a soft mask based low-level feature fusion technique. The proposed technique is further strengthened by integrating channel and spatial attention mechanisms. The proposed appr…
View article: Improving Object Tracking by Added Noise and Channel Attention
Improving Object Tracking by Added Noise and Channel Attention Open
CNN-based trackers, especially those based on Siamese networks, have recently attracted considerable attention because of their relatively good performance and low computational cost. For many Siamese trackers, learning a generic object mo…
View article: Efficient Visual Tracking With Stacked Channel-Spatial Attention Learning
Efficient Visual Tracking With Stacked Channel-Spatial Attention Learning Open
Template based learning, particularly Siamese networks, has recently become popular due to balancing accuracy and speed. However, preserving tracker robustness against challenging scenarios with real-time speed is a primary concern for vis…
View article: Deep Siamese Networks toward Robust Visual Tracking
Deep Siamese Networks toward Robust Visual Tracking Open
Recently, Siamese neural networks have been widely used in visual object tracking to leverage the template matching mechanism. Siamese network architecture contains two parallel streams to estimate the similarity between two inputs and has…
View article: Brain MRI Segmentation using Rule-Based Hybrid Approach
Brain MRI Segmentation using Rule-Based Hybrid Approach Open
Medical image segmentation being a substantial component of image processing plays a significant role to analyze gross anatomy, to locate an infirmity and to plan the surgical procedures. Segmentation of brain Magnetic Resonance Imaging (M…