Therefore, this paper takes the adaptive graph convolutional network (AGCN) as the baseline and uses the graph-pooling method to select the critical joints in the human moving process. We design two new networks: Pooling-AGCN and U-AGCN and use them to form the multi-stream P&U AGCNs for...
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19 Note PyTorch version should be 0.3! For PyTorch0.4 or higher, the codes need to be modified. Data Preparation Download the raw data fromNTU-RGB+DandSkeleton-Kinetics. Then put them under the data dir...
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19 - lshiwjx/2s-AGCN
Adaptive Graph Convolutional Neural Networks Ruoyu Li, Sheng Wang, Feiyun Zhu, Junzhou Huang The University of Texas at Arlington, Arlington, TX 76019, USA Tencent AI Lab, Shenzhen, 518057, 8 Abstract N 4 1 3 5 0 Graph Convolutional Neural Networks (Graph s) are 2 generalizations of classic...
In skeleton-based action recognition, graph convolutional networks (GCNs), which model the human body skeletons as spatiotemporal graphs, have achieved remarkable performance. However, in existing GCN-based methods, the topology of the graph is set manually, and it is fixed over all layers and in...
Due to the superior capability to process the topology of graphs, graph convolutional networks are gaining popularity in the field of action recognition based on skeleton data. However, it remains difficult to effectively extract features with more distinguishing information for both spatial and temporal...
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19 - LevelCA/2s-AGCN
Temporal adaptive graph convolution structureSpatia-temporal adaptive graph convolution networkSkeleton-based action recognition has recently achieved much attention since they can robustly convey the action information. Recently, many studies have shown that graph convolutional networks (GCNs), which generalize...
2s-AGCN Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19 Note PyTorch version should be 0.3! For PyTorch0.4 or higher, the codes need to be modified. Now we have updated the code to >=Pytorch0.4. A new model named AAGCN is added, which can...
Recently, many studies have shown that graph convolutional networks (GCNs), which generalize CNNs to more generic non-Euclidean structures, are more exactly extracts spatial feature. Nevertheless, how to effectively extract global temporal features is still a challenge. In this work, firstly, a ...