Minh Tran

I am a Ph.D. student in Computer Science at the University of Arkansas, advised by Ngan Le. Before starting my Ph.D., I was a research assistant at AIOZ AI, advised by Tuong Do and Anh Nguyen.

Email / CV / Google Scholar / Github / Linkedin

Research

My research interests are algorithms for visual generative tasks (amodal completion, image inpainting, virtual try-on, etc.); visual perception tasks (object detection, segmentation, and tracking); and vision and language interaction (VLMs, text-guided generation).

2025

A2VIS: Amodal-aware Approach to Video Instance Segmentation

Minh Tran*, Thang Pham*, Winston Bounsavy, Tri Nguyen, Ngan Le

Image and Vision Computing Journal 2025

arXiv / project page

S3Former: Self-supervised High-resolution Transformer for Solar PV Profiling

Minh Tran, Adrian De Luis, Haitao Liao, Ying Huang, Roy McCann, Alan Mantooth, Jack Cothren, Ngan Le

IEEE Transactions on Smart Grid 2025

arXiv / paper

2024

Text-Guided Video Amodal Completion

Minh Tran, Winston Bounsavy, Taisei Hanyu, Thang Pham, Khoa Vo, Tri Nguyen, Ngan Le

Preprint 2024

paper / project page

HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model

Khoa Vo, Thinh Phan, Kashu Yamazaki, Minh Tran, Ngan Le

Neurips 2024

arXiv / code / project page

Amodal Instance Segmentation with Diffusion Shape Prior Estimation

Minh Tran, Khoa Vo, Tri Nguyen, Ngan Le

ACCV 2024

arXiv / project page

ShapeFormer: Shape Prior Visible-to-Amodal Transformer-based Amodal Instance Segmentation

Minh Tran, Winston Bounsavy, Khoa Vo, Anh Nguyen, Tri Nguyen, Ngan Le

IJCNN 2024

arXiv / code

Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation

Kashu Yamazaki, Taisei Hanyu, Khoa Vo, Thang Pham, Minh Tran, Gianfranco Doretto, Anh Nguyen, Ngan Le

ICRA 2024

arXiv / code / project page

2023

aistron: Amodal Instance Segmentation Toolbox and Benchmark

Minh Tran, Ngan Le

code

2022

AISFormer: Amodal Instance Segmentation with Transformer

Minh Tran, Khoa Vo, Kashu Yamazaki, Arthur Fernandes, Michael Kidd, Ngan Le

BMVC 2022

arXiv / code / project page

3DConvCaps: 3DUnet with Convolutional Capsule Encoder for Medical Image Segmentation

Minh Tran, Viet-Khoa Vo-Ho, Ngan T.H. Le

International Conference on Pattern Recognition 2022

arXiv / code

Light-weight deformable registration using adversarial learning with distilling knowledge

Minh Tran*, Tuong Do*, Huy Tran, Erman Tjiputra, Quang D Tran, Anh Nguyen, * indicates equal contribution

IEEE Transactions on Medical Imaging 2022

paper / code

Deep Federated Learning for Autonomous Driving

Anh Nguyen, Tuong Do, Minh Tran, Binh X Nguyen, Chien Duong, Tu Phan, Erman Tjiputra, Quang D Tran

IEEE Intelligent Vehicles Symposium, 2022

arXiv / code

SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data

Minh Tran, Loi Ly, Binh-Son Hua, Ngan Le

IEEE International Symposium on Biomedical Imaging 2022 (Oral Presentation)

arXiv

2021

Multiple meta-model quantifying for medical visual question answering

Tuong Do, Binh X Nguyen, Erman Tjiputra, Minh Tran, Quang D Tran, Anh Nguyen

MICCAI 2021

paper / code

2020

BEETLEBOT: Indoor Self-Driving Delivery Robot

AIOZ AI

project page

Mobile Robot Planner with Low-cost Cameras Using Deep Reinforcement Learning

Minh Tran, Ngoc Q Ly

IEEE NICS 2020

paper / code / B.Sc. Dissertation

Activities