Nguyen Hung-Cuong

About

Nguyen Hung-Cuong is a computer vision researcher whose work centers on human pose estimation, deep learning architectures, and real-time computer vision systems. His research has made significant contributions to both 2D and 3D pose estimation, tackling the critical challenge of balancing accuracy with computational efficiency for practical deployment. His most impactful work includes the development of the YOLOv5-HR-TCM framework (2022, 33 citations), a unified end-to-end system that advances 3D human pose estimation for real-time applications in sports analytics, robotics, and healthcare. Complementing this, his combined YOLOv5 and HRNet approach (2022, 20 citations) demonstrated notable improvements in 2D keypoint detection accuracy, pushing the boundaries of CNN-based pose estimation pipelines. His earlier survey on 3D hand skeleton and pose estimation using convolutional neural networks (2020, 17 citations) established a comprehensive foundation for researchers entering the gesture recognition and human-computer interaction space. With a cumulative citation count surpassing 70 across these key works, Nguyen Hung-Cuong has emerged as a meaningful contributor to applied deep learning research, particularly where precision and speed must coexist in demanding real-world environments.

Research Focus

Key Achievements

Top Papers

1. 1
   Unified End-to-End YOLOv5-HR-TCM Framework for Automatic 2D/3D Human Pose Estimation for Real-Time Applications

   33 citations · 2022
2. 2
   Combined YOLOv5 and HRNet for High Accuracy 2D Keypoint and Human Pose Estimation

   20 citations · 2022
3. 3
   A Survey on 3D Hand Skeleton and Pose Estimation by Convolutional Neural Network

   17 citations · 2020

Key Collaborators

Contact & Links