Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition

by   Shujian Liao, et al.

This paper contributes to the challenge of skeleton-based human action recognition in videos. The key step is to develop a generic network architecture to extract discriminative features for the spatio-temporal skeleton data. In this paper, we propose a novel module, namely Logsig-RNN, which is the combination of the log-signature layer and recurrent type neural networks (RNNs). The former one comes from the mathematically principled technology of signatures and log-signatures as representations for streamed data, which can manage high sample rate streams, non-uniform sampling and time series of variable length. It serves as an enhancement of the recurrent layer, which can be conveniently plugged into neural networks. Besides we propose two path transformation layers to significantly reduce path dimension while retaining the essential information fed into the Logsig-RNN module. Finally, numerical results demonstrate that replacing the RNN module by the Logsig-RNN module in SOTA networks consistently improves the performance on both Chalearn gesture data and NTU RGB+D 120 action data in terms of accuracy and robustness. In particular, we achieve the state-of-the-art accuracy on Chalearn2013 gesture data by combining simple path transformation layers with the Logsig-RNN. Codes are available at <https://github.com/steveliao93/GCN_LogsigRNN>.


Memory Attention Networks for Skeleton-based Action Recognition

Skeleton-based action recognition task is entangled with complex spatio-...

Skeleton-Based Relational Modeling for Action Recognition

With the fast development of effective and low-cost human skeleton captu...

Skeleton-based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module

The skeleton based gesture recognition is gaining more popularity due to...

Learning stochastic differential equations using RNN with log signature features

This paper contributes to the challenge of learning a function on stream...

Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks

Recently, skeleton based action recognition gains more popularity due to...

View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data

Skeleton-based human action recognition has recently attracted increasin...

A Spatio-Temporal Multilayer Perceptron for Gesture Recognition

Gesture recognition is essential for the interaction of autonomous vehic...

Please sign up or login with your details

Forgot password? Click here to reset