Fast Temporal Graph Convolutional Model for Skeleton-Based Action Recognition

Human action recognition has a wide range of applications, including Ambient Intelligence systems and user assistance. Starting from the recognized actions performed by the user, a better human-computer interaction can be achieved, and improved assistance can be provided by social robots in real-time scenarios. In this context, the performance of the prediction system is a key aspect. The purpose of this paper is to introduce a neural network approach based on various types of convolutional layers that can achieve a good performance in recognizing actions but with a high inference speed. The experimental results show that our solution, based on a combination of graph convolutional networks (GCN) and temporal convolutional networks (TCN), is a suitable approach that reaches the proposed goal. In addition to the neural network model, we design a pipeline that contains two stages for obtaining relevant geometric features, data augmentation and data preprocessing, also contributing to an increased performance.

Comparison between Recurrent Networks and Temporal Convolutional Networks Approaches for Skeleton-Based Action Recognition

Action recognition plays an important role in various applications such as video monitoring, automatic video indexing, crowd analysis, human-machine interaction, smart homes and personal assistive robotics. In this paper, we propose improvements to some methods for human action recognition from videos that work with data represented in the form of skeleton poses. These methods are based on the most widely used techniques for this problem—Graph Convolutional Networks (GCNs), Temporal Convolutional Networks (TCNs) and Recurrent Neural Networks (RNNs). Initially, the paper explores and compares different ways to extract the most relevant spatial and temporal characteristics for a sequence of frames describing an action. Based on this comparative analysis, we show how a TCN type unit can be extended to work even on the characteristics extracted from the spatial domain. To validate our approach, we test it against a benchmark often used for human action recognition problems and we show that our solution obtains comparable results to the state-of-the-art, but with a significant increase in the inference speed.

Spatio-Temporal Features in Action Recognition Using 3D Skeletal Joints

Robust action recognition methods lie at the cornerstone of Ambient Assisted Living (AAL) systems employing optical devices. Using 3D skeleton joints extracted from depth images taken with time-of-flight (ToF) cameras has been a popular solution for accomplishing these tasks. Though seemingly scarce in terms of information availability compared to its RGB or depth image counterparts, the skeletal representation has proven to be effective in the task of action recognition. This paper explores different interpretations of both the spatial and the temporal dimensions of a sequence of frames describing an action. We show that rather intuitive approaches, often borrowed from other computer vision tasks, can improve accuracy. We report results based on these modifications and propose an architecture that uses temporal convolutions with results comparable to the state of the art.

Sign-independent synchronization in unidirectionally coupled chaotic systems

In this paper, a synchronization scheme independent of the sign of the driving signal is developed and analyzed. The corresponding synchronization phenomenon is termed sign-independent synchronization in this context. In our coupling scheme, an even coupling function is used at the response in an attempt to make the response independent of the sign of the driving signal. Furthermore, the Jacobian (and hence the stability) defined on the synchronization manifold of sign-independent synchronization systems can be made identical to that of a corresponding active-passive decomposition system. Hence the conditions for achieving stable sign-independent synchronization can be generally established as a trivial case in unidirectionally coupled chaotic systems where the method of active-passive decomposition is applicable. Through numerical experiments performed on both continuous and discrete systems, we demonstrate that in-phase synchronization can be maintained even if the phase of the driving signal is randomly inverted. We believe the proposed chaotic synchronization will find important application in digital communications.