Code for "Localization with Sampling-Argmax", NeurIPS 2021

Real-time VIBE: Frame by Frame Inference of VIBE (Video Inference for Human Body Pose and Shape Estimation)

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

Rotated Mask R-CNN: From Bounding Boxes to Rotated Bounding Boxes

The friendly PIL fork

RMPE: Regional Multi-person Pose Estimation, forked from Caffe. Research purpose only.

SJTU Jaccount Captcha auto recognize extension. 上海交通大学Jaccount登陆验证码自动识别插件。