Lightweight Graph Convolutional Network For Efficient Skeleton Based Action Recognition

Video-based human action recognition is one of the most important and challenging areas of research in the field of computer vision. Human action recognition has found many pragmatic applications in video surveillance, human-computer interaction, entertainment, autonomous driving, etc. Owing to the recent development of deep learning methods for human action recognition, the performance of action recognition has significantly enhanced for challenging datasets. Deep learning techniques are mainly used for recognizing actions in images and videos comprising of Euclidean data. A recent development in deep learning methods is the extension of these techniques to non-Euclidean data or graph data with many nodes and edges. Human body skeleton resembles a graph, therefore, the graph convolutional network (GCN) is applicable to the non-Euclidean body skeleton. In the past few years, GCN has emerged as an important tool for skeleton-based action recognition. Therefore, we conduct a survey using GCN methods for action recognition. Herein, we present a comprehensive overview of recent GCN techniques for action recognition, propose a taxonomy for the categorization of GCN techniques for action recognition, carry out a detailed study of the benchmark datasets, enlist relevant resources and open-source codes, and finally provide an outline for future research directions and trends. To the best of authors' knowledge, this is the first survey for action recognition using GCN techniques.

Skeleton-based action recognition aims to project skeleton sequences to action categories, where skeleton sequences are derived from multiple forms of pre-detected points. Compared with earlier methods that focus on exploring single-form skeletons via Graph Convolutional Networks (GCNs), existing methods tend to improve GCNs by leveraging multi-form skeletons due to their complementary cues. However, these methods (either adapting structure of GCNs or model ensemble) require the co-existence of all forms of skeletons during both training and inference stages, while a typical situation in real life is the existence of only partial forms for inference. To tackle this issue, we present Adaptive Cross-Form Learning (ACFL), which empowers well-designed GCNs to generate complementary representation from single-form skeletons without changing model capacity. Specifically, each GCN model in ACFL not only learns action representation from the single-form skeletons, but also adaptively mimics useful representations derived from other forms of skeletons. In this way, each GCN can learn how to strengthen what has been learned, thus exploiting model potential and facilitating action recognition as well. Extensive experiments conducted on three challenging benchmarks, i.e., NTU-RGB+D 120, NTU-RGB+D 60 and UAV-Human, demonstrate the effectiveness and generalizability of the proposed method. Specifically, the ACFL significantly improves various GCN models (i.e., CTR-GCN, MS-G3D, and Shift-GCN), achieving a new record for skeleton-based action recognition.

Adaptive multi-view graph convolutional networks for skeleton-based action recognition

Human action recognition plays a vital role in video understanding. In recent years, skeleton-based action recognition approaches have gained widespread attention due to their robustness against environmental interferences. This paper compiles 102 skeleton-based human action recognition methods and comparatively analyzes their performance on nine public datasets. This paper introduces the manual feature and deep learning based methods according to learning paradigms. Specifically, the manual feature methods are divided into three categories, i.e., geometric, kinetic, and statistical representations, in the light of feature descriptor. Meanwhile, the deep learning based methods are classified into five subclasses by backbones, i.e., recurrent neural networks, convolutional neural networks, graph convolutional networks, Transformer, and hybrid networks. Through comprehensive analysis, we not only present the research status of skeleton-based action recognition but also conclude that the existing methods have limitations such as poor generalization ability and high computational cost. Finally, this paper looks into future research directions from the aspects of network structure design, similar action distinction, domain data set expansion, and multi-person interaction.

In skeleton-based action recognition, graph convolutional networks (GCNs) have achieved remarkable success. Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem for industrial deployment. In this paper, we rethink the spatial aggregation in existing GCN-based skeleton action recognition methods and discover that they are limited by coupling aggregation mechanism. Inspired by the decoupling aggregation mechanism in CNNs, we propose decoupling GCN to boost the graph modeling ability with no extra computation, no extra latency, no extra GPU memory cost, and less than 10% extra parameters. Another prevalent problem of GCNs is over-fitting. Although dropout is a widely used regularization technique, it is not effective for GCNs, due to the fact that activation units are correlated between neighbor nodes. We propose DropGraph to discard features in correlated nodes, which is particularly effective on GCNs. Moreover, we introduce an attention-guided drop mechanism to enhance the regularization effect. All our contributions introduce zero extra computation burden at deployment. We conduct experiments on three datasets (NTU-RGBD, NTU-RGBD-120, and Northwestern-UCLA) and exceed the state-of-the-art performance with less computation cost.

Graph convolutional networks (GCNs) have been proven to be effective for processing structured data, so that it can effectively capture the features of related nodes and improve the performance of model. More attention is paid to employing GCN in Skeleton-Based action recognition. But there are some challenges with the existing methods based on GCNs. First, the consistency of temporal and spatial features is ignored due to extracting features node by node and frame by frame. We design a generic representation of skeleton sequences for action recognition and propose a novel model called Temporal Graph Networks (TGN), which can obtain spatiotemporal features simultaneously. Secondly, the adjacency matrix of graph describing the relation of joints are mostly depended on the physical connection between joints. We propose a multi-scale graph strategy to appropriately describe the relations between joints in skeleton graph, which adopts a full-scale graph, part-scale graph and core-scale graph to capture the local features of each joint and the contour features of important joints. Extensive experiments are conducted on two large datasets including NTU RGB+D and Kinetics Skeleton. And the experiments results show that TGN with our graph strategy outperforms other state-of-the-art methods.

Graph convolutional networks (GCN), which can model the human body skeletons as spatial and temporal graphs, have shown remarkable potential in skeleton-based action recognition. However, in the existing GCN-based methods, graph-structured representation of the human skeleton makes it difficult to be fused with other modalities, especially in the early stages. This may limit their scalability and performance in action recognition tasks. In addition, the pose information, which naturally contains informative and discriminative clues for action recognition, is rarely explored together with skeleton data in existing methods. In this work, we proposed pose-guided GCN (PG-GCN), a multi-modal framework for high-performance human action recognition. In particular, a multi-stream network is constructed to simultaneously explore the robust features from both the pose and skeleton data, while a dynamic attention module is designed for early-stage feature fusion. The core idea of this module is to utilize a trainable graph to aggregate features from the skeleton stream with that of the pose stream, which leads to a network with more robust feature representation ability. Extensive experiments show that the proposed PG-GCN can achieve state-of-the-art performance on the NTU RGB+D 60 and NTU RGB+D 120 datasets.

Geometric deep learning provides a principled and universal way for the integration of imaging and non-imaging modes in the medical field. Graph Convolutional Networks (GCNs) have been widely explored in a variety of problems, such as disease prediction, segmentation, and matrix completion. Using large, multi-modal data sets, graphs can capture the interaction of individual elements represented as nodes in the graphs. In particular, in medical applications, nodes can represent individuals (patients or healthy controls) in a potentially large population and are accompanied by a set of features, while the edges of the graph contain the associations between subjects in an intuitive way. This representation allows the inclusion of rich imaging and non-imaging information as well as individual subject characteristics in the task of disease classification. This article gives an overview of graph convolutional neural networks, focusing on the application of graph convolutional neural networks in disease prediction, and discusses the challenges and prospects of graph convolutional neural networks in disease prediction.

LightGCAN: A lightweight graph convolutional attention network for user preference modeling and personalized recommendation

Exploring the optimization of communication strategies for animation films in the context of cross-cultural communication, this research integrates the Internet of Things (IoT) and convolutional networks. The research constructs a collaborative filtering (CF) movie recommendation model based on a graph convolutional neural network (GCN) and investigates its application in cross-cultural communication. The fusion of IoT and convolutional networks in movie communication is also analyzed, and the effectiveness of the proposed GCN-CF model is validated through comparative experiments. The results indicate that, compared to other models, the GCN-CF model achieves the lowest Root Mean Square Error (RMSE) on the MovieLens 100 K and MovieLens 1 M datasets, with values of 0.8762 and 0.8275, respectively. Compared to traditional models, the GCN-CF model exhibits significantly superior performance in terms of RMSE, with reductions ranging from 0.6 to 5.2%, highlighting its heightened detection accuracy and overall performance. Moreover, the performance of the GCN-CF model is enhanced after introducing attention mechanisms and auxiliary information on both datasets, showing an improvement of 0.4% compared to the scenario without these additions. This data demonstrates the effectiveness of attention mechanisms and auxiliary information. Finally, the research presents an animation film communication strategy based on IoT and convolutional networks, offering novel insights for film production and communication, along with positive implications for cultural exchange and the advancement of the global media industry.

Skeleton-based action recognition networks have widely adopted the approach of Graph Convolutional Networks (GCN) due to their superior capabilities in modeling data topology, but several key issues still require further investigation. Firstly, the graph convolutional network extracts action features by applying temporal convolution to each key point, which causes the model to ignore the temporal connections between different important points. Secondly, the local receptive field of graph convolutional networks limits their ability to capture correlations between non-adjacent joints. Motivated by the State Space Model (SSM), we propose an Action Spatio-temporal Aggregation Network, named ActionMamba. Specifically, we introduce a novel embedding module called the Action Characteristic Encoder (ACE), which enhances the coupling of temporal and spatial information in skeletal features by combining intrinsic spatio-temporal encoding with extrinsic space encoding. Additionally, we design an Action Perception Model (APM) based on Mamba and GCN. By effectively combining the excellent feature processing capabilities of GCN with the outstanding global information modeling capabilities of Mamba, APM is able to comprehend the hidden features between different joints and selectively filter information from various joints. Extensive experimental results demonstrate that ActionMamba achieves highly competitive performance on three challenging benchmark datasets: NTU-RGB+D 60, NTU-RGB+D 120, and UAV–Human.

In recent years, human action recognition has received increasing attention as a significant function of human–machine interaction. The human skeleton is one of the most effective representations of human actions because it is highly compact and informative. Many recent skeleton-based action recognition methods are based on graph convolutional networks (GCNs) as they preserve the topology of the human skeleton while extracting features. Although many of these methods give impressive results, there are some limitations in robustness, interoperability, and scalability. Furthermore, most of these methods ignore the underlying information of view direction and rely on the model to learn how to adjust the view from training data. In this work, we propose VW-SC3D, a spatial–temporal model with view weighting for skeleton-based action recognition. In brief, our model uses a sparse 3D CNN to extract spatial features for each frame and uses a transformer encoder to obtain temporal information within the frames. Compared to GCN-based methods, our method performs better in extracting spatial–temporal features and is more adaptive to different types of 3D skeleton data. The sparse 3D CNN makes our model more computationally efficient and more flexible. In addition, a learnable view weighting module enhances the robustness of the proposed model against viewpoint changes. A test on two different types of datasets shows a competitive result with SOTA methods, and the performance is even better in view-changing situations.

Local and global self-attention enhanced graph convolutional network for skeleton-based action recognition

Graph convolutional networks (GCNs) have proven their effectiveness and success in skeleton-based action recognition. Regular GCNs separate spatial and temporal operations. And for spatial graph convolution, the self-attention mechanism is commonly used to enable the generation of adaptive data-driven graphs, which limits the receptive field of each vertex. In order to address such a concern, we propose the graph involution network (GIN). A novel operation called graph involution is applied to offer each joint a global reception field, while also largely improving temporal-wise and channel-wise flexibility during the process of feature aggregation. We also find that predefined graphs that came from human natural skeleton structures restrict the remote information exchanges. Therefore we also propose a novel graph topology called spiral graph topology, connecting body joints spirally, which brings valuable additional information hints and improves feature aggregation efficiency. Experiments conducted on different benchmarks on two large-scale datasets show the effectiveness of our proposed network.

miRNAs are important regulators for many crucial biological processes. Many recent studies have shown that miRNAs are closely related to various human diseases and can be potential biomarkers or therapeutic targets for some diseases, such as cancers. Therefore, accurately predicting miRNA-disease associations is of great importance for understanding and curing diseases. However, how to efficiently utilize the characteristics of miRNAs and diseases and the information on known miRNA-disease associations for prediction is still not fully explored. In this study, we propose a novel computational method for predicting miRNA-disease associations. The proposed method combines the graph convolutional network and the hypergraph convolutional network. The graph convolutional network is utilized to extract the information from miRNA-similarity data as well as disease-similarity data. Based on the representations of miRNAs and diseases learned by the graph convolutional network, we further use the hypergraph convolutional network to capture the complex high-order interactions in the known miRNA-disease associations. We conduct comprehensive experiments with different datasets and predictive tasks. The results show that the proposed method consistently outperforms several other state-of-the-art methods. We also discuss the influence of hyper-parameters and model structures on the performance of our method. Some case studies also demonstrate that the predictive results of the method can be verified by independent experiments.