About Me
Hi there! I'm Le-Anh Tran, a Computer Vision and Machine Learning researcher. I completed my PhD under the guidance of Prof. Dong-Chul Park, an expert in Artificial Neural Networks. I'm also a writer for various popular Medium publications such as Towards Data Science, Level Up Coding, etc.
Back in 2014, I enrolled at Ho Chi Minh City University of Technology and Education (HCMUTE). Three years later, I joined Intelligent Systems Lab (ISLab) and became a Teaching Assistant at HCMUTE. In 2018, I obtained my BEng Degree and published my first research paper. During that time, my team (ISLab) participated in the Digital Race Contest organized by FPT Corporation, where afterward I worked as an AI Engineer for one year before moving to South Korea in early 2019 to pursue postgraduate education. In 2019, I had the opportunity to intern at OCST Co., Ltd. in Seoul. Since 2020, I've been working as a Research Intern at MindinTech, Inc. in Seoul. In 2021, right after obtaining MSc Degree, I started my PhD journey. My research interests include Neural Network Architectures, Image Enhancement, Object Detection, and Cluster Analysis.
Apart from my passion for research, I also have a love for sports, singing, and drawing. Taking care of my research is always a top priority for me.
Email: tranleanh.nt@gmail.com
Profiles: ResearchGate |
GoogleScholar |
MyCV
Projects | Blogs: Github |
Medium
Education
3/2021 – 2/2024
Myongji University (Natural Science Campus), South Korea
3/2019 – 2/2021
Myongji University (Natural Science Campus), South Korea
9/2014 – 8/2018
HCMC University of Technology and Education (HCMUTE), Vietnam
Experience
4/2020 – 2/2024
MindinTech, Inc., Seoul, South Korea
3/2021 – 2/2024
Intelligent Computing Research Lab (ICRL), Myongji University, South Korea
7/2019 – 9/2019
OCST Co., Ltd., Seoul, South Korea
3/2018 – 2/2019
FPT Software, Ho Chi Minh City, Vietnam
2/2017 – 1/2018
Faculty of Electrical and Electronics Engineering, HCMUTE, Vietnam
Publications
LA Tran, DC Park
(under review) Preprint available on arXiv, 2024 [Code]
LA Tran, DC Park
(under review) Preprint available on TechRxiv, 2024 [Code]
LA Tran, DC Park
The Visual Computer, Springer (SCIE), 2024 [Code]
LA Tran, D Kwon, HM Deberneh, DC Park
Intelligent Data Analysis, IOS Press (SCIE), 2024 [PDF | Code]
LA Tran, NC Tran, DC Park, J Carrabina, D Castells-Rufas
GECOST 2024, IEEE [PDF | Code]
LA Tran, D Kwon, DC Park
(in press) Procedia Computer Science, Elsevier, 2024 [PDF | Code]
LA Tran, TD Nguyen, TD Do, NC Tran, D Kwon, DC Park
ICSSE 2023, IEEE [PDF]
NN Truong, MH Le, TD Do, LA Tran, TD Nguyen, HH Trinh
ICSSE 2023, IEEE [PDF]
LA Tran, DC Park
ASPAI 2022, IFSA [PDF]
LA Tran, DC Park
ISI 2022, Springer [PDF]
LA Tran, HM Deberneh, TD Do, TD Nguyen, MH Le, DC Park
IWIS 2022, IEEE [PDF | Code]
LA Tran, S Moon, DC Park
Procedia Computer Science, Vol. 204, Elsevier, 2022 [PDF | Code]
LA Tran, TD Do, DC Park, MH Le
ICSSE 2021, IEEE [PDF | Code]
LA Tran
Technical Report, OCST Co., Ltd., 2020 [PDF | Code]
LA Tran, MH Le
ICSSE 2019, IEEE [PDF]
LA Tran, NP Le, TD Do, MH Le
GTSD 2018, IEEE [PDF]
Projects
Project 2: Hazy/Dusty Image Synthesis for Driving Scenarios
Project 3: POCS-based Clustering Algorithm
Project 4: Object Detection Streaming and Data Management on Web Browser
Project 5: Enhancement of Robustness in Object Detection Module for ADAS
Project 6: Single Image Dehazing via Regional Saturation-Value Translation
Project 7: Data Augmentation Compilation with Python and OpenCV
Project 8: Darkeras: Run YOLO on Keras using Darknet Weights
More projects from me can be found at my Github page.
Blog
POCS-based Clustering Algorithm Explained
Each data has different importance.
EDN-GTM: Encoder-decoder Network with Guided Transmission Map
When traditional computer vision and deep learning conjugate.
MetaFormer: De facto need for Vision?
What is the key to the success of Vision Transformers?
Data Distillation for Object Detection
Learn from different perspectives.
Data Augmentation Compilation with Python and OpenCV
Prevent your model from overfitting.
Darkeras: Execute YOLOv3/YOLOv4 Object Detection on Keras with Darknet Pre-trained Weights
Everything in the universe is connected.
Synthesize Hazy/Foggy Images using Monodepth and Atmospheric Scattering Models
When fog is beneficial.
A Gentle Introduction to Hint Learning & Knowledge Distillation
Guide a student to learn a teacher’s behavior.
More posts from me can be found at my Medium page.