scholarly journals Dual Attention-Guided Multiscale Dynamic Aggregate Graph Convolutional Networks for Skeleton-Based Human Action Recognition

Symmetry ◽  
2020 ◽  
Vol 12 (10) ◽  
pp. 1589
Author(s):  
Zeyuan Hu ◽  
Eung-Joo Lee
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Great Success ◽  
Semantic Features ◽  
Convolutional Networks ◽  
Temporal Correlations ◽  
Semantic Relevance ◽  
High Level ◽  
Relationship Of

Traditional convolution neural networks have achieved great success in human action recognition. However, it is challenging to establish effective associations between different human bone nodes to capture detailed information. In this paper, we propose a dual attention-guided multiscale dynamic aggregate graph convolution neural network (DAG-GCN) for skeleton-based human action recognition. Our goal is to explore the best correlation and determine high-level semantic features. First, a multiscale dynamic aggregate GCN module is used to capture important semantic information and to establish dependence relationships for different bone nodes. Second, the higher level semantic feature is further refined, and the semantic relevance is emphasized through a dual attention guidance module. In addition, we exploit the relationship of joints hierarchically and the spatial temporal correlations through two modules. Experiments with the DAG-GCN method result in good performance on the NTU-60-RGB+D and NTU-120-RGB+D datasets. The accuracy is 95.76% and 90.01%, respectively, for the cross (X)-View and X-Subon the NTU60dataset.

scholarly journals Distinct Two-Stream Convolutional Networks for Human Action Recognition in Videos Using Segment-Based Temporal Modeling

Data ◽  
2020 ◽  
Vol 5 (4) ◽  
pp. 104
Author(s):  
Ashok Sarabu ◽  
Ajit Kumar Santra
Keyword(s):  
Action Recognition ◽  
Data Augmentation ◽  
Main Idea ◽  
Human Action Recognition ◽  
Human Action ◽  
Great Success ◽  
Temporal Modeling ◽  
Convolutional Networks ◽  
Temporal Features ◽  
Augmentation Techniques

The Two-stream convolution neural network (CNN) has proven a great success in action recognition in videos. The main idea is to train the two CNNs in order to learn spatial and temporal features separately, and two scores are combined to obtain final scores. In the literature, we observed that most of the methods use similar CNNs for two streams. In this paper, we design a two-stream CNN architecture with different CNNs for the two streams to learn spatial and temporal features. Temporal Segment Networks (TSN) is applied in order to retrieve long-range temporal features, and to differentiate the similar type of sub-action in videos. Data augmentation techniques are employed to prevent over-fitting. Advanced cross-modal pre-training is discussed and introduced to the proposed architecture in order to enhance the accuracy of action recognition. The proposed two-stream model is evaluated on two challenging action recognition datasets: HMDB-51 and UCF-101. The findings of the proposed architecture shows the significant performance increase and it outperforms the existing methods.

scholarly journals A Hierarchical Learning Approach for Human Action Recognition

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4946
Author(s):  
Nicolas Lemieux ◽  
Rita Noumeir
Keyword(s):  
Action Recognition ◽  
Inertial Sensor ◽  
Computational Cost ◽  
Human Action Recognition ◽  
Human Action ◽  
Practical Applications ◽  
Learning Framework ◽  
Sensor Signals ◽  
High Level ◽  
Computational Resources

In the domain of human action recognition, existing works mainly focus on using RGB, depth, skeleton and infrared data for analysis. While these methods have the benefit of being non-invasive, they can only be used within limited setups, are prone to issues such as occlusion and often need substantial computational resources. In this work, we address human action recognition through inertial sensor signals, which have a vast quantity of practical applications in fields such as sports analysis and human-machine interfaces. For that purpose, we propose a new learning framework built around a 1D-CNN architecture, which we validated by achieving very competitive results on the publicly available UTD-MHAD dataset. Moreover, the proposed method provides some answers to two of the greatest challenges currently faced by action recognition algorithms, which are (1) the recognition of high-level activities and (2) the reduction of their computational cost in order to make them accessible to embedded devices. Finally, this paper also investigates the tractability of the features throughout the proposed framework, both in time and duration, as we believe it could play an important role in future works in order to make the solution more intelligible, hardware-friendly and accurate.

scholarly journals Drone-Action: An Outdoor Recorded Drone Video Dataset for Action Recognition

Drones ◽  
2019 ◽  
Vol 3 (4) ◽  
pp. 82 ◽  
Author(s):  
Asanka G. Perera ◽  
Yee Wei Law ◽  
Javaan Chahl
Keyword(s):  
Action Recognition ◽  
Situational Awareness ◽  
Human Action Recognition ◽  
Human Action ◽  
Machine Learning Techniques ◽  
High Definition ◽  
Human Actions ◽  
Research Areas ◽  
Indoor Scenes ◽  
High Level

Aerial human action recognition is an emerging topic in drone applications. Commercial drone platforms capable of detecting basic human actions such as hand gestures have been developed. However, a limited number of aerial video datasets are available to support increased research into aerial human action analysis. Most of the datasets are confined to indoor scenes or object tracking and many outdoor datasets do not have sufficient human body details to apply state-of-the-art machine learning techniques. To fill this gap and enable research in wider application areas, we present an action recognition dataset recorded in an outdoor setting. A free flying drone was used to record 13 dynamic human actions. The dataset contains 240 high-definition video clips consisting of 66,919 frames. All of the videos were recorded from low-altitude and at low speed to capture the maximum human pose details with relatively high resolution. This dataset should be useful to many research areas, including action recognition, surveillance, situational awareness, and gait analysis. To test the dataset, we evaluated the dataset with a pose-based convolutional neural network (P-CNN) and high-level pose feature (HLPF) descriptors. The overall baseline action recognition accuracy calculated using P-CNN was 75.92%.

scholarly journals An Attention Enhanced Spatial–Temporal Graph Convolutional LSTM Network for Action Recognition in Karate

2021 ◽  
Vol 11 (18) ◽  
pp. 8641
Author(s):  
Jianping Guo ◽  
Hong Liu ◽  
Xi Li ◽  
Dahong Xu ◽  
Yihan Zhang
Keyword(s):  
Artificial Intelligence ◽  
Action Recognition ◽  
Structural Information ◽  
Human Action Recognition ◽  
Human Action ◽  
Competitive Sports ◽  
Convolutional Networks ◽  
Convolution Model ◽  
Artificial Intelligence Technology ◽  
Temporal Graph

With the increasing popularity of artificial intelligence applications, artificial intelligence technology has begun to be applied in competitive sports. These applications have promoted the improvement of athletes’ competitive ability, as well as the fitness of the masses. Human action recognition technology, based on deep learning, has gradually been applied to the analysis of the technical actions of competitive sports athletes, as well as the analysis of tactics. In this paper, a new graph convolution model is proposed. Delaunay’s partitioning algorithm was used to construct a new spatiotemporal topology which can effectively obtain the structural information and spatiotemporal features of athletes’ technical actions. At the same time, the attention mechanism was integrated into the model, and different weight coefficients were assigned to the joints, which significantly improved the accuracy of technical action recognition. First, a comparison between the current state-of-the-art methods was undertaken using the general datasets of Kinect and NTU-RGB + D. The performance of the new algorithm model was slightly improved in comparison to the general dataset. Then, the performance of our algorithm was compared with spatial temporal graph convolutional networks (ST-GCN) for the karate technique action dataset. We found that the accuracy of our algorithm was significantly improved.

scholarly journals Modeling Interactions between Low-Level and High-Level Features for Human Action Recognition

2013 ◽  
Vol E96.D (12) ◽  
pp. 2896-2899
Author(s):  
Wen ZHOU ◽  
Chunheng WANG ◽  
Baihua XIAO ◽  
Zhong ZHANG ◽  
Yunxue SHAO
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Low Level ◽  
Modeling Interactions ◽  
High Level
Sign in / Sign up

Export Citation Format

Share Document