Graph Convolutional Neural Network for Human Action Recognition: A Comprehensive Survey

Ahmad, Tasweer; Jin, Lianwen; Zhang, Xin; Lai, Songxuan; Tang, Guozhi; Lin, Luojun

doi:10.1109/tai.2021.3076974

Cited by 66 publications

(24 citation statements)

References 101 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Papers on methodologies, where [ 32 ] dived into GCN-based approaches [ 23 , 33 , 34 , 35 , 36 , 37 ] collected DL-based methods, and [ 38 ] collected both handcrafted-based methods and learning-based methods. Specifically [ 36 , 37 ] only summarized CNN-based approaches, while others analyzed all kinds of DL approaches.…”

Section: Previous Workmentioning

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

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: Previous Workmentioning

confidence: 99%

“…Although these surveys attempted to review the new emergence of HAR, only Tasweer et al [ 32 ] focused on GCN-based approaches. Papers [ 26 , 29 ] mention GCN-based methods but do not take them as their main purpose.…”

Section: Previous Workmentioning

confidence: 99%

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

Feng

Meunier

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…From the perspective of application, GNNs are widely applied to various real-world problems, ranging from traffic forecasting [112], social recommendation [67], action recognition [13], to natural language processing (NLP) [281], but no survey work has yet focused on the applications of GNN in IoT. To be specific, Wu et al [283] provided a taxonomy of GNN-based recommendation models according to the types of information and recommendation tasks.…”

Section: Autonomousmentioning

confidence: 99%

“…Wu et al [281] systematically organized existing research of GNNs for NLP into a new paradigm consisting of graph construction, graph representation learning, and graph-based encoder-decoder, especially for NLP problems that can be best represented with graph structures. In addition, Ahmad et al [13] summarized the applications of GNNs in human action recognition work, where graph models are applied to represent the non-Euclidean body skeleton.…”

Section: Autonomousmentioning

confidence: 99%

Graph Neural Networks in IoT: A Survey

Dong¹,

Tang²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

The Internet of Things (IoT) boom has revolutionized almost every corner of people's daily lives: healthcare, home, transportation, manufacturing, supply chain, and so on. With the recent development of sensor and communication technologies, IoT devices including smart wearables, cameras, smartwatches, and autonomous vehicles can accurately measure and perceive their surrounding environment. Continuous sensing generates massive amounts of data and presents challenges for machine learning. Deep learning models (e.g., convolution neural networks and recurrent neural networks) have been extensively employed in solving IoT tasks by learning patterns from multi-modal sensory data. Graph Neural Networks (GNNs), an emerging and fast-growing family of neural network models, can capture complex interactions within sensor topology and have been demonstrated to achieve state-of-the-art results in numerous IoT learning tasks. In this survey, we present a comprehensive review of recent advances in the application of GNNs to the IoT field, including a deep dive analysis of GNN design in various IoT sensing environments, an overarching list of public data and source code from the collected publications, and future research directions. To keep track of newly published works, we collect representative papers and their open-source implementations and create a Github repository at GNN4IoT. CCS Concepts: • Human-centered computing → Ubiquitous and mobile computing systems and tools; • Computing methodologies → Neural networks.

show abstract

“…In this work we try to push the state of the art on grammatical facial expression recognition systems fed with non-RGB data, namely Action Units or facial landmarks, casting these inputs as graphs. Recently, Graph Neural Networks (GNN) and their convolutional extension to Graph Convolutional Networks (GCN) [ 15 ] stand out for their flexibility and their good performance in Human Action Recognition. Furthermore, some works have already combined GNNs and facial landmarks [ 16 ] as well as AUs [ 17 ], obtaining SOTA results in FER.…”

Section: Introductionmentioning

confidence: 99%

Facial Motion Analysis beyond Emotional Expressions

Porta-Lorenzo

Vázquez-Enríquez

Pérez-Pérez

et al. 2022

Sensors

View full text Add to dashboard Cite

Facial motion analysis is a research field with many practical applications, and has been strongly developed in the last years. However, most effort has been focused on the recognition of basic facial expressions of emotion and neglects the analysis of facial motions related to non-verbal communication signals. This paper focuses on the classification of facial expressions that are of the utmost importance in sign languages (Grammatical Facial Expressions) but also present in expressive spoken language. We have collected a dataset of Spanish Sign Language sentences and extracted the intervals for three types of Grammatical Facial Expressions: negation, closed queries and open queries. A study of several deep learning models using different input features on the collected dataset (LSE_GFE) and an external dataset (BUHMAP) shows that GFEs can be learned reliably with Graph Convolutional Networks simply fed with face landmarks.

show abstract

Graph Convolutional Neural Network for Human Action Recognition: A Comprehensive Survey

Cited by 66 publications

References 101 publications

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

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

Graph Neural Networks in IoT: A Survey

Facial Motion Analysis beyond Emotional Expressions

Contact Info

Product

Resources

About