Rethinking the ST-GCNs for 3D skeleton-based human action recognition

Peng, Wei; Shi, Jingang; Varanka, Tuomas; Zhao, Guoying

doi:10.1016/j.neucom.2021.05.004

Cited by 45 publications

(20 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some works [173,174] proposed innovative two-stream fusion schemes, and some studies [175,176] set up pipelines to connect spatial and temporal information. Others [177][178][179] studied the spatial hierarchy and temporal series characteristics of skeleton. All in all, these works aim at recognizing the actions of interest that present in both space and time.…”

Section: Discussionmentioning

confidence: 99%

A Survey of Human Action Recognition and Posture Prediction

Cheung

et al. 2022

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

Human action recognition and posture prediction aim to recognize and predict respectively the action and postures of persons in videos. They are both active research topics in computer vision community, which have attracted considerable attention from academia and industry. They are also the precondition for intelligent interaction and human-computer cooperation, and they help the machine perceive the external environment. In the past decade, tremendous progress has been made in the field, especially after the emergence of deep learning technologies.Hence, it is necessary to make a comprehensive review of recent developments. In this paper, firstly, we attempt to present the background, and then discuss research progresses. Secondly, we introduce datasets, various typical feature representation methods, and explore advanced human action recognition and posture prediction algorithms.Finally, facing the challenges in the field, this paper puts forward the research focus, and introduces the importance of action recognition and posture prediction by taking interactive cognition in self-driving vehicle as an example.

show abstract

Section: Discussionmentioning

confidence: 99%

A Survey of Human Action Recognition and Posture Prediction

Cheung

et al. 2022

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Therefore, for one single approach, if the statistics are different in multiple papers, we choose the maximum value. The model complexity

is measured on NTU RGB+D, collected from [ 54 , 57 , 80 , 117 , 121 , 141 , 180 , 181 ]. The model size is summarized from [ 54 , 55 , 57 , 82 , 85 , 117 , 121 , 135 , 180 , 181 ].…”

Section: Datasetsmentioning

confidence: 99%

“…The model complexity

is measured on NTU RGB+D, collected from [ 54 , 57 , 80 , 117 , 121 , 141 , 180 , 181 ]. The model size is summarized from [ 54 , 55 , 57 , 82 , 85 , 117 , 121 , 135 , 180 , 181 ].…”

Section: Datasetsmentioning

confidence: 99%

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

“…We only review relevant works here. Handcrafted features usually model the human body in skeleton-based action recognition [18,19]. A Lie group can be used to encode the iterations and translations of the joints in the skeleton [20,21].…”

Section: Skeleton-based Action Recognitionmentioning

confidence: 99%

Extended Multi-Stream Adaptive Graph Convolutional Networks (EMS-AAGCN) for Skeleton-Based Human Action Recognition

Mehmood

Chen

et al. 2022

Preprint

View full text Add to dashboard Cite

Skeleton-based action recognition using graph convolutional networks (GCNs), which specify CNNs to a more flexible non-Euclidean frame, has shown outstanding results. However, many problems remain the same in the earlier GCN-based models. (I) All model layers and input data have the same graph structure. Given the GCN model’s hierarchy and the variety of action recognition input, this may not be appropriate. (II) Bone length and orientation are rarely studied because they are too helpful and different for human action recognition. This paper Article Title presents an extended multi-stream adaptive graph convolutional neu-ral network (EMS-AAGCN) for skeleton-based action recognition. The proposed model’s network topology can be trained uniformly or individually based on the input data. This approach is based on data, allowing the model to make graphs more flexible and quickly adapt to various datasets. In addition, a spatial-temporal channel attention module in the suggested adaptive graph convolutional layer allows it to focus more on joints, frames, and features. Furthermore, an enhanced multi-stream framework models joints,bones and their motion, improving recognition accuracy. Our method significances the state-of-the-art on the two massive datasets, NTU-RGBD and Kinetics-Skeleton.

show abstract

Rethinking the ST-GCNs for 3D skeleton-based human action recognition

Cited by 45 publications

References 13 publications

A Survey of Human Action Recognition and Posture Prediction

A Survey of Human Action Recognition and Posture Prediction

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

Extended Multi-Stream Adaptive Graph Convolutional Networks (EMS-AAGCN) for Skeleton-Based Human Action Recognition

Contact Info

Product

Resources

About