Nhat (Nathan) Vo
An experienced computer vision expert focusing on document image analysis, object segmentation, vision tracking, 2D/3D/4D facial image analysis, vision language model, video generation and mobile applications. In more than 10 years of experience in industrial and research projects, I have gained strong knowledge of doing research, implementing algorithms, and developing computer vision and Scientific AI applications on cloud services and smartphones. Experience from software development, academic research and industrial projects, including most recent experience as a SMTS Software Development Engineer at AMD Silo AI.
Specialties:
Programming: C/C++, MATLAB, Python, Java, C#.
O/S: Linux, Windows, Android.
Deep Learning Libraries: PyTorch, TensorFlow, Caffe.
Data Structures and Algorithm.
Vision Language Model, Diffusion Model for Image and Video Generation.
Facial Expression and Face Recognition.
Document Image Analysis, Vision tracking, and Video Coding.
Scientific AI, high-resolution weather forecasting models.
Elsewhere