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

Fully Convolutional Instance-aware Semantic Segmentation

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

TCSVT2018 Pedestrian Alignment Network for Large-scale Person Re-identification

Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade