From 979ae914e38354655606523a4f4a219bb517aed9 Mon Sep 17 00:00:00 2001 From: sjyan Date: Mon, 25 Feb 2019 16:55:11 +0800 Subject: [PATCH] fix readme --- README.md | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/README.md b/README.md index a1885e2c7..91ddee970 100644 --- a/README.md +++ b/README.md @@ -93,9 +93,7 @@ A video as above will be generated and saved under ```data/demo_result/```. ## Data Preparation -We experimented on two skeleton-based action recognition datasts: **Kinetics-skeleton** and **NTU RGB+D**. The experiments on NTU RGB+D -is not currently supported in this new version. You can switch to the old version [v0.1.0](https://github.com/yysijie/st-gcn/tree/v0.1.0) -to acquire the full experimental setting. +We experimented on two skeleton-based action recognition datasts: **Kinetics-skeleton** and **NTU RGB+D**. ### Kinetics-skeleton [Kinetics](https://deepmind.com/research/open-source/open-source-datasets/kinetics/) is a video-based dataset for action recognition which only provide raw video clips without skeleton data. Kinetics dataset include To obatin the joint locations, we first resized all videos to the resolution of 340x256 and converted the frame rate to 30 fps. Then, we extracted skeletons from each frame in Kinetics by [Openpose](https://github.com/CMU-Perceptual-Computing-Lab/openpose). The extracted skeleton data we called **Kinetics-skeleton**(7.5GB) can be directly downloaded from [GoogleDrive](https://drive.google.com/open?id=1SPQ6FmFsjGg3f59uCWfdUWI-5HJM_YhZ) or [BaiduYun](https://pan.baidu.com/s/1dwKG2TLvG-R1qeIiE4MjeA#list/path=%2FShare%2FAAAI18%2Fkinetics-skeleton&parentPath=%2FShare).