From 88db950c56f512424c693b2f86d41e2bb35ad83c Mon Sep 17 00:00:00 2001 From: sjyan Date: Thu, 22 Aug 2019 21:11:34 +0800 Subject: [PATCH] update readme --- README.md | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) diff --git a/README.md b/README.md index b2dce4d46..5d4fdcc1c 100644 --- a/README.md +++ b/README.md @@ -1,23 +1,20 @@ -# Spatial Temporal Graph Convolutional Networks (ST-GCN) -A graph convolutional network for skeleton-based action recognition. +# MMSkeleton -
- -
+## News -This repository holds the codebase, dataset and models for the paper> +ST-GCN has joined into the [open-mmlab](https://github.com/open-mmlab) project in charge of [Multimedia Laboratory, CUHK](http://mmlab.ie.cuhk.edu.hk/). +The new ST-GCN will be named as **MMSkeleton**. +It is going to be an open source toolbox for skeleton-based human understanding, +including but not limited to pose estimation, action recognition and skeleton sequence generation. -**Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition** Sijie Yan, Yuanjun Xiong and Dahua Lin, AAAI 2018. +## Introduction +This repository holds the codebase, dataset and models for the paper: -[[Arxiv Preprint]](https://arxiv.org/abs/1801.07455) +**Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition** Sijie Yan, Yuanjun Xiong and Dahua Lin, AAAI 2018. [[Arxiv Preprint]](https://arxiv.org/abs/1801.07455) -## News & Updates -- Aug. 6, 2019 - End-to-end action recognizer with Openpose Python API. -- Aug. 5, 2019 - We complete the PyTorch 1.0 migration. -- July. 10, 2019 - We provide processed data on NTU-RGB+D and kinetics-skeleton. -- Feb. 21, 2019 - We provide pretrained models and training scripts on **NTU-RGB+D** and **kinetics-skeleton** datasets. So that you can achieve the performance we mentioned in the paper. -- June. 5, 2018 - A demo for feature visualization and skeleton based action recognition is released. -- June. 1, 2018 - We update our code base and complete the PyTorch 0.4.0 migration. +
+ +
## Visulization of ST-GCN in Action Our demo for skeleton-based action recognition: