Tuan-Truong Vu

Hanoi University of Science and Technology
Bachelor of Computer Science.
CPA: 3.77/4.00

VinAI Research
AI Research Resident of Computer Vision team. Worked on object detection, segmentation and generative models.

Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation Create a dataset for object segmentation using pretrained text-to-image diffusion models.

LP-OVOD: Open-Vocabulary Object Detection by Linear Probing Address low-quality boxes of OVOD by training a sigmoid linear classifier on pseudo labels retrieved from the top relevant region proposals to the novel text.

Face Swapping as A Simple Arithmetic Operation We propose a novel high-fidelity face swapping method called Arithmetic Face Swapping (AFS) that explicitly disentangles the intermediate latent space W+ of a pretrained StyleGAN

Unsupervised image segmentation with robust virtual class contrast Propose a novel method for unsupervised image segmentation called Robust Virtual Class Contrast (RVCC), which characterizes foreground pixels based on their “virtual classes” rather than just saliency masks