Machine Vision and Intelligence Group @ SJTU

Spatio-Temporal Action Localization System

MVIG-SJTU

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

MVIG-SJTU

Code for CVPR'18 spotlight "Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer"

MVIG-SJTU

a module for 3D semantic segmentation in point clouds.

MVIG-SJTU

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

MVIG-SJTU

Code for "DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection" (AAAI 2021)

MVIG-SJTU