scholarly journals Graph CNNs with Motif and Variable Temporal Block for Skeleton-Based Action Recognition

2019 ◽  
Vol 33 ◽  
pp. 8989-8996 ◽  
Author(s):  
Yu-Hui Wen ◽  
Lin Gao ◽  
Hongbo Fu ◽  
Fang-Lue Zhang ◽  
Shihong Xia
Keyword(s):  
Spatial Structure ◽  
Action Recognition ◽  
Large Scale ◽  
Human Skeleton ◽  
Semantic Roles ◽  
Temporal Domain ◽  
Non Local ◽  
Novel Model ◽  
Local Block ◽  
Skeleton Structure

Hierarchical structure and different semantic roles of joints in human skeleton convey important information for action recognition. Conventional graph convolution methods for modeling skeleton structure consider only physically connected neighbors of each joint, and the joints of the same type, thus failing to capture highorder information. In this work, we propose a novel model with motif-based graph convolution to encode hierarchical spatial structure, and a variable temporal dense block to exploit local temporal information over different ranges of human skeleton sequences. Moreover, we employ a non-local block to capture global dependencies of temporal domain in an attention mechanism. Our model achieves improvements over the stateof-the-art methods on two large-scale datasets.

scholarly journals Global Co-Occurrence Feature and Local Spatial Feature Learning for Skeleton-Based Action Recognition

Entropy ◽  
2020 ◽  
Vol 22 (10) ◽  
pp. 1135
Author(s):  
Jun Xie ◽  
Wentian Xin ◽  
Ruyi Liu ◽  
Qiguang Miao ◽  
Lijie Sheng ◽  
...  
Keyword(s):  
Spatial Structure ◽  
Action Recognition ◽  
Large Scale ◽  
Recent Progress ◽  
Feature Fusion ◽  
Model Performance ◽  
Feature Learning ◽  
Learning Model ◽  
Spatial Feature ◽  
Convolutional Networks

Recent progress on skeleton-based action recognition has been substantial, benefiting mostly from the explosive development of Graph Convolutional Networks (GCN). However, prevailing GCN-based methods may not effectively capture the global co-occurrence features among joints and the local spatial structure features composed of adjacent bones. They also ignore the effect of channels unrelated to action recognition on model performance. Accordingly, to address these issues, we propose a Global Co-occurrence feature and Local Spatial feature learning model (GCLS) consisting of two branches. The first branch, based on the Vertex Attention Mechanism branch (VAM-branch), captures the global co-occurrence feature of actions effectively; the second, based on the Cross-kernel Feature Fusion branch (CFF-branch), extracts local spatial structure features composed of adjacent bones and restrains the channels unrelated to action recognition. Extensive experiments on two large-scale datasets, NTU-RGB+D and Kinetics, demonstrate that GCLS achieves the best performance when compared to the mainstream approaches.

scholarly journals Whole and Part Adaptive Fusion Graph Convolutional Networks for Skeleton-Based Action Recognition

Sensors ◽  
2020 ◽  
Vol 20 (24) ◽  
pp. 7149
Author(s):  
Qi Zuo ◽  
Lian Zou ◽  
Cien Fan ◽  
Dongqian Li ◽  
Hao Jiang ◽  
...  
Keyword(s):  
Action Recognition ◽  
Large Scale ◽  
Movement Patterns ◽  
Physical Structure ◽  
Human Skeleton ◽  
Spatiotemporal Features ◽  
Convolutional Networks ◽  
Skeleton Graph ◽  
Adaptive Fusion ◽  
Different Parts

Spatiotemporal graph convolution has made significant progress in skeleton-based action recognition in recent years. Most of the existing graph convolution methods take all the joints of the human skeleton as the overall modeling graph, ignoring the differences in the movement patterns of various parts of the human, and cannot well connect the relationship between the different parts of the human skeleton. To capture the unique features of different parts of human skeleton data and the correlation of different parts, we propose two new graph convolution methods: the whole graph convolution network (WGCN) and the part graph convolution network (PGCN). WGCN learns the whole scale skeleton spatiotemporal features according to the movement patterns and physical structure of the human skeleton. PGCN divides the human skeleton graph into several subgraphs to learn the part scale spatiotemporal features. Moreover, we propose an adaptive fusion module that combines the two features for multiple complementary adaptive fusion to obtain more effective skeleton features. By coupling these proposals, we build a whole and part adaptive fusion graph convolution neural network (WPGCN) that outperforms previous state-of-the-art methods on three large-scale datasets: NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400.

The Uncertainty Principle Derived by The Finite Transmission Speed of Light and Information

2014 ◽  
Vol 3 (3) ◽  
pp. 257-266 ◽  
Author(s):  
Piero Chiarelli
Keyword(s):  
Uncertainty Principle ◽  
Large Scale ◽  
Uncertainty Relations ◽  
Speed Of Light ◽  
Energy Fluctuation ◽  
Hydrodynamic Analogy ◽  
Non Local ◽  
Minimum Uncertainty ◽  
Quantum Hydrodynamic ◽  
Transmission Speed

This work shows that in the frame of the stochastic generalization of the quantum hydrodynamic analogy (QHA) the uncertainty principle is fully compatible with the postulate of finite transmission speed of light and information. The theory shows that the measurement process performed in the large scale classical limit in presence of background noise, cannot have a duration smaller than the time need to the light to travel the distance up to which the quantum non-local interaction extend itself. The product of the minimum measuring time multiplied by the variance of energy fluctuation due to presence of stochastic noise shows to lead to the minimum uncertainty principle. The paper also shows that the uncertainty relations can be also derived if applied to the indetermination of position and momentum of a particle of mass m in a quantum fluctuating environment.

scholarly journals NPU RGB+D Dataset and a Feature-Enhanced LSTM-DGCN Method for Action Recognition of Basketball Players

2021 ◽  
Vol 11 (10) ◽  
pp. 4426
Author(s):  
Chunyan Ma ◽  
Ji Fan ◽  
Jinghao Yao ◽  
Tao Zhang
Keyword(s):  
Action Recognition ◽  
Large Scale ◽  
Short Term Memory ◽  
Evaluation Criteria ◽  
Image Data ◽  
Basketball Player ◽  
Basketball Players ◽  
Convolutional Network ◽  
Atomic Actions ◽  
New Feature

Computer vision-based action recognition of basketball players in basketball training and competition has gradually become a research hotspot. However, owing to the complex technical action, diverse background, and limb occlusion, it remains a challenging task without effective solutions or public dataset benchmarks. In this study, we defined 32 kinds of atomic actions covering most of the complex actions for basketball players and built the dataset NPU RGB+D (a large scale dataset of basketball action recognition with RGB image data and Depth data captured in Northwestern Polytechnical University) for 12 kinds of actions of 10 professional basketball players with 2169 RGB+D videos and 75 thousand frames, including RGB frame sequences, depth maps, and skeleton coordinates. Through extracting the spatial features of the distances and angles between the joint points of basketball players, we created a new feature-enhanced skeleton-based method called LSTM-DGCN for basketball player action recognition based on the deep graph convolutional network (DGCN) and long short-term memory (LSTM) methods. Many advanced action recognition methods were evaluated on our dataset and compared with our proposed method. The experimental results show that the NPU RGB+D dataset is very competitive with the current action recognition algorithms and that our LSTM-DGCN outperforms the state-of-the-art action recognition methods in various evaluation criteria on our dataset. Our action classifications and this NPU RGB+D dataset are valuable for basketball player action recognition techniques. The feature-enhanced LSTM-DGCN has a more accurate action recognition effect, which improves the motion expression ability of the skeleton data.

scholarly journals Sliding Contacts in Planetary Magnetospheres

Symmetry ◽  
2021 ◽  
Vol 13 (2) ◽  
pp. 283
Author(s):  
Elena Belenkaya ◽  
Igor Alexeev
Keyword(s):  
Large Scale ◽  
Strong Field ◽  
Magnetized Plasma ◽  
Sliding Contacts ◽  
Radio Emissions ◽  
Planetary Magnetospheres ◽  
Current Task ◽  
Surrounding Space ◽  
Non Local ◽  
A Current

In the planetary magnetospheres there are specific places connected with velocity breakdown, reconnection, and dynamo processes. Here we pay attention to sliding layers. Sliding layers are formed in the ionosphere, on separatrix surfaces, at the magnetopauses and boundaries of stellar astrospheres, and at the Alfvén radius in the equatorial magnetosphere of rapidly rotating strongly magnetized giant planets. Although sliding contacts usually occur in thin local layers, their influence on the global structure of the surrounding space is very great. Therefore, they are associated with non-local processes that play a key role on a large scale. There can be an exchange between different forms of energy, a generation of strong field-aligned currents and emissions, and an amplification of magnetic fields. Depending on the conditions in the magnetosphere of the planet/exoplanet and in the flow of magnetized plasma passing it, different numbers of sliding layers with different configurations appear. Some are associated with regions of auroras and possible radio emissions. The search for planetary radio emissions is a current task in the detection of exoplanets.

scholarly journals Introducing Twitter Daily Estimates of Residents and Non-Residents at the County Level

2021 ◽  
Vol 10 (6) ◽  
pp. 227
Author(s):  
Yago Martín ◽  
Zhenlong Li ◽  
Yue Ge ◽  
Xiao Huang
Keyword(s):  
Large Scale ◽  
Local Population ◽  
External Validation ◽  
Population Estimates ◽  
County Level ◽  
Internal Validation ◽  
Population Movements ◽  
Dynamic Component ◽  
Home Location ◽  
Non Local

The study of migrations and mobility has historically been severely limited by the absence of reliable data or the temporal sparsity of available data. Using geospatial digital trace data, the study of population movements can be much more precisely and dynamically measured. Our research seeks to develop a near real-time (one-day lag) Twitter census that gives a more temporally granular picture of local and non-local population at the county level. Internal validation reveals over 80% accuracy when compared with users’ self-reported home location. External validation results suggest these stocks correlate with available statistics of residents/non-residents at the county level and can accurately reflect regular (seasonal tourism) and non-regular events such as the Great American Solar Eclipse of 2017. The findings demonstrate that Twitter holds the potential to introduce the dynamic component often lacking in population estimates. This study could potentially benefit various fields such as demography, tourism, emergency management, and public health and create new opportunities for large-scale mobility analyses.

A multi-objective sparse evolutionary framework for large-scale weapon target assignment based on a reward strategy

2021 ◽  
Vol 40 (5) ◽  
pp. 10043-10061
Author(s):  
Xiaoping Shi ◽  
Shiqi Zou ◽  
Shenmin Song ◽  
Rui Guo
Keyword(s):  
Large Scale ◽  
The Novel ◽  
Genetic Operators ◽  
Multi Objective ◽  
Target Assignment ◽  
Solution Selection ◽  
Battlefield Environment ◽  
Sparse Problems ◽  
Novel Model ◽  
Error Parameter

 The asset-based weapon target assignment (ABWTA) problem is one of the important branches of the weapon target assignment (WTA) problem. Due to the current large-scale battlefield environment, the ABWTA problem is a multi-objective optimization problem (MOP) with strong constraints, large-scale and sparse properties. The novel model of the ABWTA problem with the operation error parameter is established. An evolutionary algorithm for large-scale sparse problems (SparseEA) is introduced as the main framework for solving large-scale sparse ABWTA problem. The proposed framework (SparseEA-ABWTA) mainly addresses the issue that problem-specific initialization method and genetic operators with a reward strategy can generate solutions efficiently considering the sparsity of variables and an improved non-dominated solution selection method is presented to handle the constraints. Under the premise of constructing large-scale cases by the specific case generator, two numerical experiments on four outstanding multi-objective evolutionary algorithms (MOEAs) show Runtime of SparseEA-ABWTA is faster nearly 50% than others under the same convergence and the gap between MOEAs improved by the mechanism of SparseEA-ABWTA and SparseEA-ABWTA is reduced to nearly 20% in the convergence and distribution.

Sign in / Sign up

Export Citation Format

Share Document