Hoang-Son Vo
Browse
V2E Face disentangles head pose, landmarks, and emotion using separate supervised VQ codebooks and hierarchical attention fusion, achieving SOTA lip-sync and reconstruction on CREMA-D and MEAD while staying lightweight and real-time. Published in IEEE MultiMedia, 2026.
Audio-driven talking head generation presents significant challenges in creating realistic facial animations that accurately synchronize with audio signals. This paper introduces ATL-Diff, a novel approach that addresses key limitations in existing methods through an innovative three-component framework.
3D Dual-Domain Attention for Brain Tumor Segmentaion is a method which develope based on Attention mechanims with key idea is using a path-of-net to extract information about global of context, other one learning information about local of context.
My graduate thesis in HUFLIT: Brain Tumor Detection using Deep Learning
3D Brain Tumor Segmentaion using method 3D-Dual Fusion Attention base on Fusion method, Attention mechanism, and Residual learning.