mae

OpenMMLab Pre-training Toolbox and Benchmark

The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"

[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning