Nhat-Tan Bui

Research Associate I, Robotics Institute, Carnegie Mellon University

"True scholar is shown by phronesis, not imagination."

Email: tannhatb@andrew.cmu.edu | tanb@uark.edu

Greetings! My name in Vietnamese is Bùi Nhật Tân (裴日新), which typically means daily renewal 🌕 with brightness 🔆 and hope 🍀. I am currently affiliated with the Human Sensing Lab, working with Prof. Fernando De la Torre, who is truly a mensch and a wonderful advisor!

I was fortunate to receive my M.S. from the University of Arkansas (UARK), advised by Prof. Susan Gauch and Distinguished Prof. Truong Nguyen (UC San Diego), and my B.S. from the University of Science, VNU-HCM (HCMUS) and Auckland University of Technology (AUT), advised by Assoc. Prof. Minh-Triet Tran and Dr. Ngoc-Thao Nguyen.

I have some wonderful friends who always help me in my research journey. All of the people mentioned are those to whom I owe a debt of gratitude.

Research Keywords: Deep Learning 🧠, Computer Vision 👀, and Multimodal Learning 🎏 with applications in 3D and Video Understanding 🔍.

Please feel free to drop me an email if you have any questions about my research, or even me 😁

Publications

"Research is for curiosity and fun, though practical implications can emerge." - Zhi-Hua Zhou
"Without the love of research, mere knowledge and intelligence cannot make a scientist." - Irène Joliot-Curie
"In the end, when it’s over, all that matters is what you’ve done." - Alexander the Great

(* indicates equal contribution)

NeIn: Telling What You Don't Want

Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2025) SyntaGen

🏆 Best Paper Award

Nhat-Tan Bui, Dinh-Hieu Hoang, Quoc-Huy Trinh, Minh-Triet Tran, Truong Nguyen, Susan Gauch

TLDR: First Large-Scale Vision-Language Negation Dataset for Text-Guided Image Editing

[Paper] [Project Page]

TSRNet: Simple Framework for Real-time ECG Anomaly Detection with Multimodal Time and Spectrogram Restoration Network

International Symposium on Biomedical Imaging (ISBI 2024)

Nhat-Tan Bui*, Dinh-Hieu Hoang*, Thinh Phan, Minh-Triet Tran, Brijesh Patel, Donald Adjeroh, Ngan Le

TLDR: Time-Spectrogram Fusion with Cross-Attention Mechanism and Prioritizing R-peaks during Inference

[Paper] [Code]

SAM3D: Segment Anything Model in Volumetric Medical Images

International Symposium on Biomedical Imaging (ISBI 2024)

Nhat-Tan Bui*, Dinh-Hieu Hoang*, Minh-Triet Tran, Gianfranco Doretto, Donald Adjeroh, ..., Ngan Le

TLDR: Frozen SAM’s Encoder, Stack Output Slice Embeddings, and Decode with a 3D CNN Decoder

[Paper] [Code]

MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation

Winter Conference on Applications of Computer Vision (WACV 2024)

Nhat-Tan Bui, Dinh-Hieu Hoang, Quang-Thuc Nguyen, Minh-Triet Tran, Ngan Le

TLDR: Laplacian-based Edge Information Fused with Attention Mechanism for UNet Skip Connection

[Paper] [Code]

Documents

"What I cannot create, I do not understand." - Richard Feynman

Credits/Misc