About Me

Hi ~ I’m Le-Anh Tran, PhD, an AI Research Scientist who enjoys delving into deep neural networks, understanding their inner workings, and enhancing their capabilities to be smarter, faster, and more useful.

My expertise lies in Image Enhancement, Segmentation, and Object Detection, and I’m proficient in Python with hands-on experience in various computer vision projects based on TensorFlow and PyTorch. I love creating innovative AI algorithms, and I stay sharp by reading and publishing research papers, because good science never sleeps.

Recently, I’ve also been exploring language models, curious about how chatbots might one day become my colleagues, or even my competitors.

Outside of work, I enjoy unwinding through art and sports. I sketch and sing on occasion. I am also a big fan of 3-cushion billiards. On the soccer field, I like to think of myself as a cool midfielder.



Email: tranleanh.nt@gmail.com
Profiles: ResearchGate | GoogleScholar | MyCV
Projects | Blogs: Github | Medium


Education

PhD in Computer Vision

3/2021 – 2/2024
Myongji University (Natural Science Campus), South Korea

MSc in Computer Vision

3/2019 – 2/2021
Myongji University (Natural Science Campus), South Korea

BEng in Automation and Control Engineering

9/2014 – 8/2018
HCMC University of Technology and Education (HCMUTE), Vietnam


Experience

Research Staff Member

4/2020 – 5/2025
MindinTech, Inc., Seoul, South Korea

Research Assistant

3/2021 – 2/2024
Intelligent Computing Research Lab (ICRL), Myongji University, South Korea

Software Development Intern

7/2019 – 9/2019
OCST Co., Ltd., Seoul, South Korea

AI Engineer

3/2018 – 2/2019
FPT Software, Ho Chi Minh City, Vietnam

Teaching Assistant

2/2017 – 1/2018
Faculty of Electrical and Electronics Engineering, HCMUTE, Vietnam




Publications

: Equal Contribution Authorship | * : Corresponding Author


Global Saturation-Value Translation Approach for Haze Removal in Urban Aerial Imagery

TD Do, LA Tran, J Lee, SK Hong
IEEE Access (SCIE), 2025

Spatial-Aware Image Denoising through an Encoder-Decoder Framework

TD Nguyen, LA Tran, G Cheol, ES Kim, KC Lee
IEIE 2025, Kangwon National University [PDF]

Low-Light Enhancement via Encoder-Decoder Network with Illumination Guidance

LA Tran, CN Tran, NL Nguyen, NC Dang, J Carrabina, D Castells-Rufas, MS Nguyen
ICCCE 2025, IEEE [Code]

Unpaired Image Dehazing via Kolmogorov-Arnold Transformation of Latent Features

LA Tran
Under Review, 2025

Distilled Pooling Transformer Encoder for Efficient Realistic Image Dehazing

LA Tran, DC Park
Neural Computing and Applications (SCIE), 2024 [Code]

Drone-view Haze Removal via Regional Saturation-Value Translation and Soft Segmentation

TD Do, LA Tran, S Moon, J Chung, NP Nguyen, SK Hong
IEEE Access (SCIE), 2024 [Code]

Clustering Optimization via Centroid Neural Network Ensemble

NC Tran, LA Tran*, NP Le, J Carrabina, D Castells-Rufas, MS Nguyen, NC Dang
FMLDS 2024, IEEE [PDF]

Lightweight Image Dehazing Networks based on Soft Knowledge Distillation

LA Tran, DC Park
The Visual Computer (SCIE), 2024 [Code]

POCS-based Image Compression: An Empirical Examination

TD Do, LA Tran, TD Nguyen, NN Truong, DC Park, MH Le
GTSD 2024, IEEE

Encoder-Decoder Networks with Guided Transmission Map for Effective Image Dehazing

LA Tran, DC Park
The Visual Computer (SCIE), 2024 [Code]

Cluster Analysis via Projection onto Convex Sets

LA Tran, D Kwon, HM Deberneh, DC Park
Intelligent Data Analysis (SCIE), 2024 [PDF | Code]

Toward Improving Robustness of Object Detectors Against Domain Shift

LA Tran, NC Tran, DC Park, J Carrabina, D Castells-Rufas
GECOST 2024, IEEE [PDF | Code]

Single Image Dehazing via Regional Saturation-Value Translation

LA Tran, D Kwon, DC Park
Procedia Computer Science, Vol. 237, Elsevier, 2024 [PDF | Code]

Embedding Clustering via Autoencoder and Projection onto Convex Set

LA Tran, TD Nguyen, TD Do, NC Tran, D Kwon, DC Park
ICSSE 2023, IEEE [PDF]

Efficient Infrared-Thermal Imaging Fusion for Human Detection in Heavy Smoke Scenarios

NN Truong, MH Le, TD Do, LA Tran, TD Nguyen, HH Trinh
ICSSE 2023, IEEE [PDF]

Encoder-Decoder Network with Guided Transmission Map: Architecture

LA Tran, DC Park
ASPAI 2022, IFSA [PDF]

Encoder-Decoder Network with Guided Transmission Map: Robustness and Applicability

LA Tran, DC Park
ISI 2022, Springer [PDF]

POCS-based Clustering Algorithm

LA Tran, HM Deberneh, TD Do, TD Nguyen, MH Le, DC Park
IWIS 2022, IEEE [PDF | Code]

A Novel Encoder-Decoder Network with Guided Transmission Map for Image Dehazing

LA Tran, S Moon, DC Park
Procedia Computer Science, Vol. 204, Elsevier, 2022 [PDF | Code]

Enhancement of Robustness in Object Detection Module for ADAS

LA Tran, TD Do, DC Park, MH Le
ICSSE 2021, IEEE [PDF | Code]

Object Detection Streaming and Data Management on Web Browser

LA Tran
Technical Report, OCST Co., Ltd., 2020 [PDF | Code]

Robust U-Net-based Road Lane Markings Detection for Autonomous Driving

LA Tran, MH Le
ICSSE 2019, IEEE [PDF]

A Vision-based Method for Autonomous Landing on a Target with a Quadcopter

LA Tran, NP Le, TD Do, MH Le
GTSD 2018, IEEE [PDF]







Blog

HTML5 Bootstrap Template by colorlib.com
Towards Data Science | 5 min read

POCS-based Clustering Algorithm Explained

Each data has different importance.

HTML5 Bootstrap Template by colorlib.com
Towards Data Science | 6 min read

EDN-GTM: Encoder-decoder Network with Guided Transmission Map

When traditional computer vision and deep learning conjugate.

HTML5 Bootstrap Template by colorlib.com
Towards Data Science | 4 min read

MetaFormer: De facto need for Vision?

What is the key to the success of Vision Transformers?

HTML5 Bootstrap Template by colorlib.com
Towards Data Science | 5 min read

Data Distillation for Object Detection

Learn from different perspectives.

HTML5 Bootstrap Template by colorlib.com
Towards Data Science | 6 min read

Learning Without Forgetting Simplified

Learn once and forever.

HTML5 Bootstrap Template by colorlib.com
Towards Data Science | 5 min read

Data Augmentation Compilation with Python and OpenCV

Prevent your model from overfitting.

HTML5 Bootstrap Template by colorlib.com
Towards Data Science | 4 min read

Darkeras: Execute YOLOv3/YOLOv4 Object Detection on Keras with Darknet Pre-trained Weights

Everything in the universe is connected.

HTML5 Bootstrap Template by colorlib.com
Towards Data Science | 4 min read

Synthesize Hazy/Foggy Images using Monodepth and Atmospheric Scattering Models

When fog is beneficial.

HTML5 Bootstrap Template by colorlib.com
Towards AI | 5 min read

A Gentle Introduction to Hint Learning & Knowledge Distillation

Guide a student to learn a teacher’s behavior.


*More posts can be found at my Medium page.