kenziyuliu / MS-G3D

[CVPR 2020 Oral] PyTorch implementation of "Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition"
https://arxiv.org/abs/2003.14111
MIT License
430 stars 96 forks source link

How to use it to predict an RGB video? #49

Closed hellogit-0 closed 2 years ago

kenziyuliu commented 2 years ago

Hi there, thanks for your interest! This repo only provides the code for skeleton-based action recognition, so it won't work with RGB videos directly. You could extend it with toolkits such as https://github.com/CMU-Perceptual-Computing-Lab/openpose that extracts skeletons from RGB videos.