MFGCN: an efficient graph convolutional network based on multi-order feature information for human skeleton action recognition

Qi, Yongfeng; Hu, J. Michelle; Han, Xinyu; Liang, Hu; Zhao, Zhijin

doi:10.1007/s00521-023-08814-4

Cited by 2 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the network simplifies the network by considering the context term of each vertex by integrating the information of all other vertices in addition to computing the local graph convolution, thus achieving a performance comparable to the then optimal network. Ye et al [107] [59] proposed an efficient graph convolutional network based on multi-order feature information (MFGCN) for human skeletal action recognition, which introduces angular features (called fourth-order features), which are implicitly embedded into other third-order features by encoding the angular features in order to robustly capture detailed features in the spatiotemporal dimension and enhance the ability to differentiate between similar actions; second, a content-adaptive approach is used to construct an adjacency matrix to dynamically learning the topology between skeleton joints; finally, a spatio-temporal information sliding extraction module (STISE) is developed to improve the interconnectivity of spatio-temporal information.…”

Section: Based On Skeletal Joint Points With Graph Convolutionmentioning

confidence: 99%

An Overview of Behavioral Recognition

Xie,

Xiang,

et al. 2024

ITC

View full text Add to dashboard Cite

Human behavior recognition has become a popular research topic in the field of computer vision. With the introduction of deep learning and attention mechanisms, this field has been further promoted. However, issues such as dataset acquisition and preprocessing operations on multimodal datasets, modeling of long time information in videos, and fusion of temporal and spatial information still exist. In this paper, we first outline some video action recognition datasets and related preprocessing techniques, including frame extraction, optical flow extraction, and skeletal feature acquisition. Then, the relevant models are classified and parsed according to their characteristics and the types of input data modalities. In addition, we evaluate the performance of the models on several benchmark datasets to gain a deeper understanding of the model development process. Finally, we summarized the current challenges faced in the field of video behavior recognition, including model timeliness, data set subjectivity and effective fusion of multi-modal features, and proposed possible future improvement directions in order to provide more ideas and methods for subsequent research.

show abstract

Section: Based On Skeletal Joint Points With Graph Convolutionmentioning

confidence: 99%

An Overview of Behavioral Recognition

Xie,

Xiang,

et al. 2024

ITC

View full text Add to dashboard Cite

show abstract

“…Ref. [ 23 ] notes that high-order encoding features can be easily incorporated into the existing action recognition framework, complementing joint and skeletal features. However, coordination could be designed to include these higher-order features for understanding motion characteristics, something that is not considered in existing models.…”

Section: Introductionmentioning

confidence: 99%

Action Recognition Based on Multi-Level Topological Channel Attention of Human Skeleton

Hu,

Shen,

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

In action recognition, obtaining skeleton data from human poses is valuable. This process can help eliminate negative effects of environmental noise, including changes in background and lighting conditions. Although GCN can learn unique action features, it fails to fully utilize the prior knowledge of human body structure and the coordination relations between limbs. To address these issues, this paper proposes a Multi-level Topological Channel Attention Network algorithm: Firstly, the Multi-level Topology and Channel Attention Module incorporates prior knowledge of human body structure using a coarse-to-fine approach, effectively extracting action features. Secondly, the Coordination Module utilizes contralateral and ipsilateral coordinated movements in human kinematics. Lastly, the Multi-scale Global Spatio-temporal Attention Module captures spatiotemporal features of different granularities and incorporates a causal convolution block and masked temporal attention to prevent non-causal relationships. This method achieved accuracy rates of 91.9% (Xsub), 96.3% (Xview), 88.5% (Xsub), and 90.3% (Xset) on NTU-RGB+D 60 and NTU-RGB+D 120, respectively.

show abstract

MFGCN: an efficient graph convolutional network based on multi-order feature information for human skeleton action recognition

Cited by 2 publications

References 48 publications

An Overview of Behavioral Recognition

An Overview of Behavioral Recognition

Action Recognition Based on Multi-Level Topological Channel Attention of Human Skeleton

Contact Info

Product

Resources

About