Skeleton-based action recognition using sparse spatio-temporal GCN with edge effective resistance

Ahmad, Tasweer; Jin, Lianwen; Lin, Luojun; Tang, Guozhi

doi:10.1016/j.neucom.2020.10.096

Cited by 30 publications

(23 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from paying more attention to informative joints in the self-attention branch, the combination of these two branches also suppress the influence of joints that are less relevant to the context information. T. Ahmad et al [ 124 ] proposed a self-attention graph pooling to retain local properties and graph structures while pooling.…”

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

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: The Common Frameworkmentioning

confidence: 99%

“…T. Ahmad et al [ 124 ] performed spectral sparsification by exploiting similarity of the original graph, which is in Laplacian quadratic form, and that of the sparsed graph. It aims at discarding some redundant information by eliminating noisy nodes and edges.…”

Section: The Common Frameworkmentioning

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

“…Based on the graph convolutional neural network, Ahmad et al proposes a graph sparsity technique that uses effective edge resistance to better model global context information and eliminate redundant nodes and edges in the graph. In addition, they combined selfattention graph pools to preserve local attributes [3]. Xu proposes an edge computing based on a deep reasoning framework, which has the privacy of local differences in mobile data analysis.…”

Section: Related Workmentioning

confidence: 99%

The Application of Graph Neural Network Based on Edge Computing in English Teaching Mode Reform

Huang

Wang

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The latest developments in edge computing have paved the way for more efficient data processing especially for simple tasks and lightweight models on the edge of the network, sinking network functions from cloud to edge of the network closer to users. For the reform of English teaching mode, this is also an opportunity to integrate information technology, providing new ideas and new methods for the optimization of English teaching. It improves the efficiency of English reading teaching, stimulates the interest of English learning, enhances students’ autonomous learning ability, and creates favorable conditions for students’ learning and development. This paper designs a MEC-based GNN (GCN-GAN) user preference prediction recommendation model, which can recommend high-quality video or picture text content to the local MEC server based on user browsing history and user preferences. In the experiment, the LFU-LRU joint cache placement strategy used in this article has a cache hit rate of up to 99%. Comparing the GCN-GAN model with other traditional graph neural network models, it performs caching experiments on the Douban English book data and Douban video data sets. The GCN-GAN model has a higher score on the cache task, and the highest speculation accuracy value F1 can reach 86.7.

show abstract

“…Given a graph 𝐺 treated as a resistor network, the effective resistance 𝑅 𝐺 (𝑠, 𝑡) between two vertices 𝑠, 𝑡 in 𝐺 is the energy dissipation in the network when routing one unit of current from 𝑠 to 𝑡. It is well known that the effective resistance is inherently related to the behaviour of random walks on graphs 1 . Concretely, the effective resistance between 𝑠 and 𝑡 is proportional to the commute time 𝜅 (𝑠, 𝑡), defined as the expected number of steps a random walk starting at 𝑠 visits vertex 𝑡 and then goes back to 𝑠 [9].…”

Section: Introductionmentioning

confidence: 99%

“…Indeed, effective resistance has proven ubiquitous in numerous applications including graph clustering [2,16], recommender systems [22], measuring robustness of networks [15], spectral sparsification [36], graph convolutional networks [1], location-based advertising [37], among others. Moreover, in the theoretical computer science community, the use of effective resistance has led to a breakthrough line of work for provably speeding up the running time of many flow-based problems in combinatorial optimization [3,11,29].…”

Section: Introductionmentioning

confidence: 99%

Local Algorithms for Estimating Effective Resistance

Pan¹,

Lopatta²,

Yoshida³

et al. 2021

Preprint

View full text Add to dashboard Cite

Effective resistance is an important metric that measures the similarity of two vertices in a graph. It has found applications in graph clustering, recommendation systems and network reliability, among others. In spite of the importance of the effective resistances, we still lack efficient algorithms to exactly compute or approximate them on massive graphs.In this work, we design several local algorithms for estimating effective resistances, which are algorithms that only read a small portion of the input while still having provable performance guarantees. To illustrate, our main algorithm approximates the effective resistance between any vertex pair 𝑠, 𝑡 with an arbitrarily small additive error 𝜀 in time 𝑂 (poly(log 𝑛/𝜀)), whenever the underlying graph has bounded mixing time. We perform an extensive empirical study on several benchmark datasets, validating the performance of our algorithms. CCS CONCEPTS• Mathematics of computing → Graph algorithms; • Theory of computation → Sketching and sampling.

show abstract

Skeleton-based action recognition using sparse spatio-temporal GCN with edge effective resistance

Cited by 30 publications

References 23 publications

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

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

The Application of Graph Neural Network Based on Edge Computing in English Teaching Mode Reform

Local Algorithms for Estimating Effective Resistance

Contact Info

Product

Resources

About