Multi-stream slowFast graph convolutional networks for skeleton-based action recognition

2021 ◽  
Vol 109 ◽  
pp. 104141
Author(s):  
Ning Sun ◽  
Ling Leng ◽  
Jixin Liu ◽  
Guang Han
Keyword(s):  
Action Recognition ◽  
Convolutional Networks

Attention adjacency matrix based graph convolutional networks for skeleton-based action recognition

2021 ◽  
Vol 440 ◽  
pp. 230-239
Author(s):  
Jun Xie ◽  
Qiguang Miao ◽  
Ruyi Liu ◽  
Wentian Xin ◽  
Lei Tang ◽  
...  
Keyword(s):  
Action Recognition ◽  
Adjacency Matrix ◽  
Convolutional Networks

scholarly journals Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision

2021 ◽  
pp. 108170
Author(s):  
Lei Shi ◽  
Yifan Zhang ◽  
Jian Cheng ◽  
Hanqing Lu
Keyword(s):  
Action Recognition ◽  
Convolutional Networks

Skeleton-based Action Recognition with Focusing-Diffusion Graph Convolutional Networks

2021 ◽  
pp. 1-1
Author(s):  
Jialin Gao ◽  
Tong He ◽  
Xi Zhou ◽  
Shiming Ge
Keyword(s):  
Action Recognition ◽  
Convolutional Networks

Forward-reverse Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

2021 ◽  
Author(s):  
Zesheng Hu ◽  
Zihao Pan ◽  
Qiang Wang ◽  
Lei Yu ◽  
Shumin Fei
Keyword(s):  
Action Recognition ◽  
Convolutional Networks

scholarly journals Distinct Two-Stream Convolutional Networks for Human Action Recognition in Videos Using Segment-Based Temporal Modeling

Data ◽  
2020 ◽  
Vol 5 (4) ◽  
pp. 104
Author(s):  
Ashok Sarabu ◽  
Ajit Kumar Santra
Keyword(s):  
Action Recognition ◽  
Data Augmentation ◽  
Main Idea ◽  
Human Action Recognition ◽  
Human Action ◽  
Great Success ◽  
Temporal Modeling ◽  
Convolutional Networks ◽  
Temporal Features ◽  
Augmentation Techniques

The Two-stream convolution neural network (CNN) has proven a great success in action recognition in videos. The main idea is to train the two CNNs in order to learn spatial and temporal features separately, and two scores are combined to obtain final scores. In the literature, we observed that most of the methods use similar CNNs for two streams. In this paper, we design a two-stream CNN architecture with different CNNs for the two streams to learn spatial and temporal features. Temporal Segment Networks (TSN) is applied in order to retrieve long-range temporal features, and to differentiate the similar type of sub-action in videos. Data augmentation techniques are employed to prevent over-fitting. Advanced cross-modal pre-training is discussed and introduced to the proposed architecture in order to enhance the accuracy of action recognition. The proposed two-stream model is evaluated on two challenging action recognition datasets: HMDB-51 and UCF-101. The findings of the proposed architecture shows the significant performance increase and it outperforms the existing methods.

scholarly journals Skeleton-based Action Recognition with Two-Branch Graph Convolutional Networks

2021 ◽  
Vol 2030 (1) ◽  
pp. 012091
Author(s):  
Zhi Liu ◽  
Qici Xie ◽  
Yunhua Lu ◽  
Xian Wang
Keyword(s):  
Action Recognition ◽  
Convolutional Networks
Sign in / Sign up

Export Citation Format

Share Document