###### tags: `GAS-GCN`

# Gated Action-Specific Graph Convolutional Networks for Skeleton-Based Action Recognition

## About the paper
- [read](https://www.mdpi.com/1424-8220/20/12/3499)
- author: Wensong Chan ,Zhiqiang Tian, and Yang Wu
- published: 2020/6/21
- contributin
- ASGCN: combine structural and implicit edge
- Gated CNN: filter out useless temporal information
- Dataset:
- NTU-RGB + D 120
- 南洋理工大學蒐集的資料集
- RGB videos: 1920x1080
- depth map videos: 512*424
- IR videos (紅外線): 512*424
- ==3D== skeletal data: 25 個關節
- [download](https://github.com/shahroudy/NTURGB-D/tree/master)
- Kinetics
- 主要來自Youtube
- 分類: person, person-person, person-object
- 至少600個影片，一個影片10秒
- 有label
- [download](https://k4kan.medium.com/ntu-rgb-d-%E8%B3%87%E6%96%99%E9%9B%86%E4%BB%8B%E7%B4%B9-718e45554a61)
- [detail](https://zhuanlan.zhihu.com/p/347490726)
- Experiments Details
- PyTorch: implement GAS-GCN
- SGD: optimization strategy
- 2 NVIDIA 2080TI GPU with memory of 11GB
- NTU-RGB + D training
- T=300
- epoch=50, base learning rate:
- 1~29: 0.1
- 30~40: 0.1 x 0.1
- 41~50: 0.1 x 0.1 x 0.1
- batch size=28
- Kinetics
- T=150
- epoch=65, base learning rate:
- 1~44: 0.1
- 45~55: 0.1 x 0.1
- 56~65: 0.1 x 0.1 x 0.1
- batch size=64
- 𝜇=0.5

## GAS-GCN
- Gated Action-Specific Graph Convolutional Networks
- Why
- GCNs-based only focus on ajencent matrix (只有附近的joint，但是每個動作不一定只影響到一個關節附近)
- The connection between two joints is structural edge
- solution: action-specific graph convolutional module (ASGCM)
- generate the implicit edge
- decide the ratio of the combination of structural edge and implicit edges according to different action
- ==GAS-GCN==
- Skeleton-based recognition depends on the contexts and long-range dependencies in temporal dimension
- 但不是所有資訊都會用到action recognition上
- solution: Gated mechanism
- control the information flowing in RNN
- operates the time dimension
-

## Source code
- [Tian Lab](https://github.com/Tian-lab/gas-gcn/tree/master)
- [STA-GCN](https://www.semanticscholar.org/paper/Spatial-Temporal-Attention-Graph-Convolutional-with-Shiraki-Hirakawa/4280ab3111c6d4922a832f11f7a073afe062736d)
- [STA-GCN paper](https://openaccess.thecvf.com/content/ACCV2020/papers/Shiraki_Spatial_Temporal_Attention_Graph_Convolutional_Networks_with_Mechanics-Stream_for_Skeleton-based_ACCV_2020_paper.pdf)
-