|
Currently, I am working at University of Rochester advised by Professor Chenliang Xu, where I work on instructional video understanding and vision-language problems. I had nearly 3 wonderful years at VinAI Research where I worked on Scene text spotting problem under the supervision of Professor Nguyen Minh Hoai. I did my bachelor at University of Engineering and Technology - VNU, where I had chances to work with Professor Hoang Van Xiem. |
|
- 03/2024: One paper accepted at NAACL 2024.
- 03/2024: I received research internship offers from Bosch AI Research and Amazon, USA.
- 07/2023: One paper accepted at AV4D Workshop, ICCV 2023.
- 08/2022: I started my journey with the University of Rochester since the Fall 2022.
- 01/2022: I began working as an AI Research Engineer with the applied team at VinAI Research.
- 03/2021: One paper accepted at CVPR 2021.
- 07/2020: I graduated with Distinction from Vietnam National University in 2020.
- 12/2019: I started my journey with VinAI Research as an AI Research Resident in December 2019.
|
I'm interested in computer vision, natural language processing, and machine learning (especially deep learning). Much of my research lies in optical character recognition, focusing on scene text recognition. I am also fond of Vision-Language problems, such as understanding visual content using natural language. |
|
Under review, 2024 github / paper A single multimodal LLM designed for comprehensively solving all tasks related to egocentric video understanding. |
|
Nguyen Nguyen, Jing Bi, Ali Vosoughi, Yapeng Tian, Pooyan Fazli, Chenliang Xu NAACL (Findings), 2024 github / paper A new task of understanding the state of objects and the progression of object state changes. Besides, we trained a Multimodal-LLM that significantly surpasses previous state-of-the-art models. Our model achieved 90% quality of GPT4-V on both GPT4 and human evaluations. |
|
Nguyen Nguyen, Yapeng Tian, Chenliang Xu Under review paper A simple but effective approach to incorporate language knowledge from large text corpus for improving both text detection and recognition. |
|
Jing Bi*, Nguyen Nguyen*, Ali Vosoughi*, Chenliang Xu (* equal contribution) AV4D Workshop, ICCV, 2023 github / paper A comprehensive system designed to guide humans to work more efficiently and accurately. Our system leverages the power of LLMs to interpret and process information from visual, auditory, and contextual dimensions. |
|
Nguyen Nguyen, Thu Nguyen, Vinh Tran, Minh Triet Tran, Thanh Duc Ngo, Thien Huu Nguyen, Minh Hoai Nguyen CVPR, 2021 project page / github / paper A novel approach to incorporate dictionary on both training and testing phases. Additionally, we also introduced a novel Vietnamese scene text dataset (VinText), the largest scene text dataset for Vietnamese. |
|
|
 |
Reviewer
|
 |
Competition jury member (2021)
|
|
Teaching assistant (2018 - 2019)
|
|
|
-
University of Rochester 2022 - presentPh.D. Student
Department of Computer Science -
Bosch Research May. 2024 - August. 2024Research Intern
Audio Group -
VinAI Research Jan. 2022- June. 2022AI Research Engineer
R&D Group -
VinAI Research Dec. 2019- Dec. 2021AI Research Resident
Computer Vision Research Group -
Teko Vietnam April. 2019- Nov. 2019AI Engineer Intern
Data Science Group -
Vietnam National University 2016 - 2020B.S. Student
Information Technology Department
|
This website uses source code from http://jonbarron.info and https://www.yapengtian.com |