From 6a5f18c16183e606a8837fb254519d1b8fcfefff Mon Sep 17 00:00:00 2001 From: Haodong Duan Date: Thu, 12 May 2022 16:01:59 +0800 Subject: [PATCH] Update README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 37b38483..7d5011c9 100644 --- a/README.md +++ b/README.md @@ -14,6 +14,7 @@ This repo is the official implementation of [PoseConv3D](https://arxiv.org/abs/2 ## News +- Support spatial augmentations and provide a benchmark on ST-GCN++ (**2022-05-12**). - Support skeleton action recognition demo with GCN algorithms (**2022-05-03**). - Release the skeleton annotations (generated by HRNet), config files, and pre-trained checkpoints for Kinetics-400. Note that Kinetics-400 is a large-scale dataset (even for skeleton) and you should have `memcached` and `pymemcache` installed for efficient training and testing on Kinetics-400 (**2022-05-01**). - Provide an example for processing a custom video dataset (we use diving48), generating 2D skeleton annotations, and using PoseC3D for skeleton-based action recognition. The tutorial for skeleton extraction part is available in [diving48_example](/examples/extract_diving48_skeleton/diving48_example.ipynb) (**2022-04-15**).