Information Enhanced Graph Convolutional Networks for Skeleton-based Action Recognition

Sun, Dengdi; Zeng, Fanchen; Luo, Bin; Tang, Jin; Ding, Zhuanlian

doi:10.1109/ijcnn48605.2020.9207025

Cited by 3 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ST-GCN is a typical spatiotemporal approach since it performs GCN on spatiotemporal graph (STG) directly and therefore extracts spatiotemporal information simultaneously. Methods, such as [ 29 , 48 , 54 , 60 , 68 , 82 , 86 , 96 , 101 , 102 , 103 , 104 , 105 , 106 , 107 , 108 , 109 , 110 , 111 , 112 , 113 ] are all developed based on ST-GCN. Methods based on AGCN also work on STG, such as [ 66 , 73 , 93 , 114 ].…”

Section: A New Taxonomy For Skeleton-gnn-based Harmentioning

confidence: 99%

“…The first benefit has been proven by numerous papers using CNN or RNN. Methods, such as [ 51 , 61 , 67 , 91 , 107 , 110 , 113 , 120 , 121 , 122 , 123 , 126 , 128 , 132 , 133 , 134 , 135 ], all follow the basic architecture of skip connection. The second benefit was also discovered by multiple papers.…”

Section: The Common Frameworkmentioning

confidence: 99%

“…The method ST-GCN [ 13 ] and related methods [ 29 , 96 , 110 , 111 , 112 , 113 ] all adopt one-hop convolution. Methods [ 55 , 107 , 128 ] change one-hop to multi-hop, since the k -order of neighbors will capture more local information around the center node and also preserve the structural information around it.…”

Section: The Common Frameworkmentioning

confidence: 99%

See 2 more Smart Citations

Skeleton Graph-Neural-Network-Based Human Action Recognition: A Survey

Feng

Meunier

2022

Sensors

View full text Add to dashboard Cite

Human action recognition has been applied in many fields, such as video surveillance and human computer interaction, where it helps to improve performance. Numerous reviews of the literature have been done, but rarely have these reviews concentrated on skeleton-graph-based approaches. Connecting the skeleton joints as in the physical appearance can naturally generate a graph. This paper provides an up-to-date review for readers on skeleton graph-neural-network-based human action recognition. After analyzing previous related studies, a new taxonomy for skeleton-GNN-based methods is proposed according to their designs, and their merits and demerits are analyzed. In addition, the datasets and codes are discussed. Finally, future research directions are suggested.

show abstract

Section: A New Taxonomy For Skeleton-gnn-based Harmentioning

confidence: 99%

Section: The Common Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Skeleton Graph-Neural-Network-Based Human Action Recognition: A Survey

Feng

Meunier

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Later, bones, and the relative position and motion information of joints became common features in skeletonbased action recognition because they are easy to obtain and have a strong discrimination ability [18,21,23,26,29,30,44]. erefore, we first generate these three features at the data-processing level of the model.…”

Section: Point Levelmentioning

confidence: 99%

“…e ST-GCN model constructs the spatial structure of the human skeleton according to the adjacency between two joints in the human body, significantly improving the recognition performance of the model and reflecting the applicability and superiority of the GCN in this task. Graph convolution has gradually become a mainstream research method for skeleton recognition, and researchers have carried out specific research based on the idea of graph convolution [20][21][22][23][24][25][26][27][28][29][30][31][32]. Combining the graph convolution with excellent network structures, such as attention networks [33,34] or residual networks [35,36], can further improve the human skeleton recognition accuracy.…”

Section: Introductionmentioning

confidence: 99%

A Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition

Jiang

Yang

Liu

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

In skeleton-based human action recognition methods, human behaviours can be analysed through temporal and spatial changes in the human skeleton. Skeletons are not limited by clothing changes, lighting conditions, or complex backgrounds. This recognition method is robust and has aroused great interest; however, many existing studies used deep-layer networks with large numbers of required parameters to improve the model performance and thus lost the advantage of less computation of skeleton data. It is difficult to deploy previously established models to real-life applications based on low-cost embedded devices. To obtain a model with fewer parameters and a higher accuracy, this study designed a lightweight frame-level joints adaptive graph convolutional network (FLAGCN) model to solve skeleton-based action recognition tasks. Compared with the classical 2s-AGCN model, the new model obtained a higher precision with 1/8 of the parameters and 1/9 of the floating-point operations (FLOPs). Our proposed network characterises three main improvements. First, a previous feature-fusion method replaces the multistream network and reduces the number of required parameters. Second, at the spatial level, two kinds of graph convolution methods capture different aspects of human action information. A frame-level graph convolution constructs a human topological structure for each data frame, whereas an adjacency graph convolution captures the characteristics of the adjacent joints. Third, the model proposed in this study hierarchically extracts different levels of action sequence features, making the model clear and easy to understand; further, it reduces the depth of the model and the number of parameters. A large number of experiments on the NTU RGB + D 60 and 120 data sets show that this method has the advantages of few required parameters, low computational costs, and fast speeds. It also has a simple structure and training process that make it easy to deploy in real-time recognition systems based on low-cost embedded devices.

show abstract

Graph convolutional networks and LSTM for first-person multimodal hand action recognition

Wang

2022

Machine Vision and Applications

View full text Add to dashboard Cite

Information Enhanced Graph Convolutional Networks for Skeleton-based Action Recognition

Cited by 3 publications

References 26 publications

Skeleton Graph-Neural-Network-Based Human Action Recognition: A Survey

Skeleton Graph-Neural-Network-Based Human Action Recognition: A Survey

A Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition

Graph convolutional networks and LSTM for first-person multimodal hand action recognition

Contact Info

Product

Resources

About