[Document] Add description of PoseC3D dataset. (#1053)

docs/supported_datasets.md

@@ -22,6 +22,9 @@
   - [UCF101-24](/tools/data/ucf101_24/README.md) \[ [Homepage](http://www.thumos.info/download.html) \]
   - [JHMDB](/tools/data/jhmdb/README.md) \[ [Homepage](http://jhmdb.is.tue.mpg.de/) \]
 
+- Skeleton-based Action Recognition
+  - [PoseC3D Skeleton Dataset](/tools/data/skeleton/README.md) \[ [Homepage](https://kennymckormick.github.io/posec3d/) \]
+
 The supported datasets are listed above.
 We provide shell scripts for data preparation under the path `$MMACTION2/tools/data/`.
 Below is the detailed tutorials of data deployment for each dataset.

docs_zh_CN/supported_datasets.md

@@ -22,6 +22,9 @@
   - [UCF101-24](/tools/data/ucf101_24/README_zh-CN.md) \[ [主页](http://www.thumos.info/download.html) \]
   - [JHMDB](/tools/data/jhmdb/README_zh-CN.md) \[ [主页](http://jhmdb.is.tue.mpg.de/) \]
 
+- 基于人体骨架的动作识别数据集：
+  - [PoseC3D Skeleton Dataset](/tools/data/skeleton/README.md) \[ [主页](https://kennymckormick.github.io/posec3d/) \]
+
 MMAction2 目前支持的数据集如上所列。
 MMAction2 在 `$MMACTION2/tools/data/` 路径下提供数据集准备脚本。
 每个数据集的详细准备教程也在 [Readthedocs](https://mmaction2.readthedocs.io/zh_CN/latest/supported_datasets.html) 中给出。

tools/data/skeleton/README.md

@@ -27,6 +27,18 @@ bash download_annotations.sh ${DATASET}
 
 PS: Due to [Conditions of Use](http://rose1.ntu.edu.sg/Datasets/actionRecognition.asp) of the NTURGB-D dataset, we can not directly release the annotations used in our experiments. We will prepare a script for pose annotation generation ASAP. Once accomplished, you can use this script to generate all pose annotations used in our experiments.
 
+## The Format of PoseC3D Annotations
+
+Here we briefly introduce the format of PoseC3D Annotations, we will take `gym_train.pkl` as an example: the content of `gym_train.pkl` is a list of length 20484, each item is a dictionary that is the skeleton annotation of one video. Each dictionary has following fields:
+
+- kp: The keypoint coordinates, which is a numpy array of the shape N (#person) x T (temporal length) x K (#keypoints, 17 in our case) x 2 (x, y coordinate).
+- kpscore:  The keypoint confidence scores, which is a numpy array of the shape N (#person) x T (temporal length) x K (#keypoints, 17 in our case).
+- frame_dir: The corresponding video name.
+- label: The action category.
+- img_shape: The image shape of each frame.
+- original_shape: Same as above.
+- total_frames: The temporal length of the video.
+
 ## Visualization
 
 For skeleton data visualization, you need also to prepare the RGB videos. Please refer to [visualize_heatmap_volume](/demo/visualize_heatmap_volume.ipynb) for detailed process. Here we provide some visualization examples from NTU-60 and FineGYM.