The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

GPU Accelerated t-SNE for CUDA with Python bindings

Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016.

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

Integral Human Pose Regression

CNN accelerated by cuda. Test on mnist and finilly get 99.76%