Two-stream adaptive-attentional subgraph convolution networks for skeleton-based action recognition

Li, Xianshan; Meng, Fengchan; Zhao, Fengda; Guo, Dingding; Lou, Fengwei; Jing, Rong

doi:10.1007/s11042-021-11026-4

Cited by 7 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The action is then predicted using the training and testing phase by the prediction module. The authors of [18] presented an adaptive sub-graph convolution module that can learn the relationships among sub-graphs and adaptively infer the high-level spatial characteristics of each sub-graph. They created a two-stream architecture to combine bone and joint characteristics, which improves the model's capacity for recognition.…”

Section: Related Workmentioning

confidence: 99%

Enhanced Two-Stream Bayesian Hyper Parameter Optimized 3D-CNN Inception-v3 Based Drop-ConvLSTM2D Deep Learning Model for Human Action Recognition

Jeyanthi,

Visumathi,

Heltin Genitha

2024

ITC

View full text Add to dashboard Cite

Human Action Recognition (HAR) has grown to be the toughest and most attractive concern in the domains of computer vision, communication between a person and the surroundings, and video surveillance. In variation to the conventional methods that usually make use of the Long Short Term Memory model (LSTM) for training, this work designed dropout variant Drop-ConvLSTM2D, to provide more effectiveness in regularization for deep Convolution Neural Networks (CNNs).In addition, to speed up the runtime performance of the Deep Learning model, Bayesian Hyper Parameter Optimization (BHPO) is also introduced to autonomously optimize, the hyperparameters of the trained architecture. In this study, a two-stream Bayesian Hyper Parameter optimized Drop-ConvLSTM2D model is designed for HAR to overcome the current research deficiencies. In one stream, an Inception-v3 model extracts the temporal characteristics from the optical frames which are generated through the dense flow process. In another stream, a 3D-CNN involves the mining of the spatial-temporal characteristics from the RGB frames. Finally, the features of Inception-v3 and 3D-CNN are fused using which the Drop-ConvLSTM2D model is trained to recognize human behavior. On perceptive public video datasets UCF-101, and HMDB51, the quantitative assessments are conducted on the Drop-ConvLSTM2D BHPO model. For all hyperparameters, the built model explicitly obtains optimized values in this process, which can save time and improve performance. The experimental outcome shows that with a precision of at least 3%, the designed model beats the traditional two-stream model.

show abstract

Section: Related Workmentioning

confidence: 99%

Enhanced Two-Stream Bayesian Hyper Parameter Optimized 3D-CNN Inception-v3 Based Drop-ConvLSTM2D Deep Learning Model for Human Action Recognition

Jeyanthi,

Visumathi,

Heltin Genitha

2024

ITC

View full text Add to dashboard Cite

show abstract

“…They also suggested a hierarchically decomposed GCN [17] that extracts major structural edges and uses them to construct a hierarchically decomposed graph. Other follow-up works include multi-scale modelling [18,19], graph routing [20] and so on [21,22]. Attention mechanism has been successfully applied to various tasks due to the effectiveness of modelling long-range dependencies.…”

Section: Skeleton-based Action Recognitionmentioning

confidence: 99%

“…They also suggested a hierarchically decomposed GCN [17] that extracts major structural edges and uses them to construct a hierarchically decomposed graph. Other follow‐up works include multi‐scale modelling [18, 19], graph routing [20] and so on [21, 22].…”

Section: Related Workmentioning

confidence: 99%

Position‐aware spatio‐temporal graph convolutional networks for skeleton‐based action recognition

Yang

Wang

Chen

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

Graph Convolutional Networks (GCNs) have been widely used in skeleton‐based action recognition. Though significant performance has been achieved, it is still challenging to effectively model the complex dynamics of skeleton sequences. A novel position‐aware spatio‐temporal GCN for skeleton‐based action recognition is proposed, where the positional encoding is investigated to enhance the capacity of typical baselines for comprehending the dynamic characteristics of action sequence. Specifically, the authors’ method systematically investigates the temporal position encoding and spatial position embedding, in favour of explicitly capturing the sequence ordering information and the identity information of nodes that are used in graphs. Additionally, to alleviate the redundancy and over‐smoothing problems of typical GCNs, the authors’ method further investigates a subgraph mask, which gears to mine the prominent subgraph patterns over the underlying graph, letting the model be robust against the impaction of some irrelevant joints. Extensive experiments on three large‐scale datasets demonstrate that our model can achieve competitive results comparing to the previous state‐of‐art methods.

show abstract

“…SGN [18] 2020 79.2 81.5 ST-GDN [19] 2020 80.8 82.3 2S-AASGCN [17] 2021 82.6 83.1 4S-Shift-GCN [20] 2021 85.9 87.6…”

Section: Comparison With the State Of The Art (Sota)mentioning

confidence: 99%

Multi-modality dense graph convolution network for skeleton-based action recognition

Sun,

Guo,

Luo

et al. 2023

Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023)

View full text Add to dashboard Cite

Skeleton-based human action recognition has emerged as a vibrant area of research in recent years.. In action recognition based on skeleton, the method based on graph convolution network is through modeling space to explore physical dependence between body joints, has obtained the remarkable performance, however, most GCN method uses the stratification to aggregate a wide range of field information, which makes the joint characteristics in long distance transmission is weakened. In this paper, dense graph convolutional networks are proposed to overcome these shortcomings. To enhance the informative skeleton features and create a compact representation at an early fusion stage, an MMF is developed. Then, Our proposed method utilizes a dense graph convolution operation to improve the local context information of each joint. Finally, feature channels and action classes are specific, In our model, it is crucial to assign weights to important features and focus on the relevant information. Therefore, To improve the identification of features in our model, we introduce a channel joint attention module. A large number of experiments on three large datasets (NTU-RGB+D, NTU-RGB+D120 and Kinetics) have demonstrated the performance of the proposed MMD-GCN for skeleton-based action recognition.

show abstract

Two-stream adaptive-attentional subgraph convolution networks for skeleton-based action recognition

Cited by 7 publications

References 35 publications

Enhanced Two-Stream Bayesian Hyper Parameter Optimized 3D-CNN Inception-v3 Based Drop-ConvLSTM2D Deep Learning Model for Human Action Recognition

Enhanced Two-Stream Bayesian Hyper Parameter Optimized 3D-CNN Inception-v3 Based Drop-ConvLSTM2D Deep Learning Model for Human Action Recognition

Position‐aware spatio‐temporal graph convolutional networks for skeleton‐based action recognition

Multi-modality dense graph convolution network for skeleton-based action recognition

Contact Info

Product

Resources

About