Tin Nguyen (Kevin)

I'm Tin Nguyen, currently pursuing my PhD in Explainable AI at Auburn University, AL, US under the mentorship of Professor Anh Totti Nguyen. I received Master degree at Sejong University, Seoul, Korea under the supervision of Professor Yong-Guk Kim. I did my Bachelor at the University of Science, Ho Chi Minh City, Viet Nam with guidance from Professor Ly Quoc Ngoc.

I'm keen on collaborating and sharing ideas to advance our understanding and application of AI 😄. If you're interested in working together or just want to chat about AI, feel free to get in touch

CV  /  Google Scholar  /  ResearchGate  /  Twitter  /  Github

Latest News  /  Feature Projects

profile photo
Research

I am deeply committed to developing interpretable, editable, and robust machine learning approaches, though my interests extend beyond these core areas. Representative papers are highlighted.

Conference
[Accepted] PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck
Thang Pham, Peijie Chen, Tin Nguyen, Seunghyun Yoon, Trung Bui, Anh Nguyen
NAACL, 2024 Findings
Code / Paper / Demo / Video

We proposed a part-based bird classifier that makes predictions based on part-wise descriptions. Our method directly utilizes human-provided descriptions (in this work, from GPT4). It outperforms CLIP and M&V by 10 points in CUB and 28 points in NABirds.

Journal
[Accepted] Meme Analysis using LLM-based Contextual Information and U-net Encapsulated Transformer
Thanh Tin Nguyen, Marvin John, Hulin Jin, Yong-Guk Kim

IEEE Access, Jul, 4, 2024
Project Page / Code / Paper

This study proposes an attention-based module for analyzing the sentiment and emotion of memes.

[Accepted] Coarse-To-Fine Fusion for Language Grounding in 3D Navigation
Thanh Tin Nguyen, Anh H. Vo, Soo-Mi Choi, Yong-Guk Kim

Knowledge-based Systems (KBS), Jul 4, 2023
Video / Code / Paper

This study proposes a coarse-to-fine fusion module between vision and language. This will help an agent learn a joint representation while navigating in a virtual environment.

[Accepted] Fruit-CoV: An Efficient Vision-based Framework for Speedy Detection and Diagnosis of SARS-CoV-2 Infections Through Recorded Cough Sounds
Long H. Nguyen, Nhat Truong Pham, Van Huong Do, Liu Tai Nguyen, Thanh Tin Nguyen, Van Dung Do, Hai Nguyen, Ngoc Duy Nguyen

(Challenge 1st) Expert System with Applications (ESWA), 1, November, 2022
Link Challenge / Paper

Introducing Fruit-CoV, a two-stage vision framework, which is capable of detecting SARS-CoV-2 infections through recorded cough sounds. In this challenge, we won 100mil VND (~ $4275) for the 1st place.

A New Framework of Moving Object Tracking Based on Object Detection-Tracking with Removal of Moving Features using Stereo Camera and IMU
Nguyen Thanh Tin, Ly Quoc Ngoc, Le Bao Tuan

International Journal of Advanced Computer Science and Applications (SAI), 14, April, 2020
Video 1 / Video 2 / Video 3 / Paper

Applying Yolo3 to Particle Filter to enhance its speed and accuracy, furthermore, an end-to-end localization framework using a stereo camera and IMU in the unknown environment.

Workshop / Challenge
HCILab at Memotion 2.0 2022: Analysis of sentiment, emotion, and intensity of emotion classes from meme images using single and multi modalities
Nguyen Thanh Tin, Nhat Truong Pham, Yong-Guk Kim, et. al,.
(Workshop) First Workshop on ​Multimodal Fact-Checking and Hate Speech Detection AAAI 2022, 2021  
Paper / Link Challenge / Project Page / Code

Achieved 1st on the public leaderboard, applying SAN, multihop, CNNRoBerta as multimodalities, and Only Text and Image as Single modalities.

Image Captioning Using Swin Transformer Encoder and LSTM Attention Decoder
Nguyen Thanh Tin
(Workshop 3rd and) VLSP - vieCap4H Challenge: Automatic image caption generation for healthcare domains in Vietnamese (Oral presentation), 25, October, 2021  

(VNU Journal of Science (JCSCE)) vieCap4H - VLSP 2021: Vietnamese Image Captioning for Healthcare Domain using Swin Transformer and Attention-based LSTM, 5, May, 2022  
Paper / Link Challenge / Project Page / Code

[Most interesting discussed idea award] Achieved 3rd on the private leaderboard, applying Swin Transformer as the Encoder (and other types), and LSTM Attention as the Decoder.

Choosen to be in the Special Issue of VNU Journal of Science (JCSCE)

Reviewer
Academic Service