Neural controlled differential equations for irregular time series
Neural ordinary differential equations are an attractive option for modelling temporal
dynamics. However, a fundamental issue is that the solution to an ordinary differential …
dynamics. However, a fundamental issue is that the solution to an ordinary differential …
Deep learning for human activity recognition on 3d human skeleton: survey and comparative study
Human activity recognition (HAR) is an important research problem in computer vision. This
problem is widely applied to building applications in human–machine interactions …
problem is widely applied to building applications in human–machine interactions …
Neural rough differential equations for long time series
Neural controlled differential equations (CDEs) are the continuous-time analogue of
recurrent neural networks, as Neural ODEs are to residual networks, and offer a memory …
recurrent neural networks, as Neural ODEs are to residual networks, and offer a memory …
Sig-Wasserstein GANs for time series generation
H Ni, L Szpruch, M Sabate-Vidales, B ** the path signature methodology and its application to landmark-based human action recognition
Landmark-based human action recognition in videos is a challenging task in computer
vision. One key step is to design a generic approach that generates discriminative features …
vision. One key step is to design a generic approach that generates discriminative features …
Monitoring and prediction of landslide-related deformation based on the GCN-LSTM algorithm and SAR imagery
A key component of disaster management and infrastructure organization is predicting
cumulative deformations caused by landslides. One of the critical points in predicting …
cumulative deformations caused by landslides. One of the critical points in predicting …
Framing RNN as a kernel method: A neural ODE approach
Building on the interpretation of a recurrent neural network (RNN) as a continuous-time
neural differential equation, we show, under appropriate conditions, that the solution of a …
neural differential equation, we show, under appropriate conditions, that the solution of a …
A generalised signature method for multivariate time series feature extraction
The'signature method'refers to a collection of feature extraction techniques for multivariate
time series, derived from the theory of controlled differential equations. There is a great deal …
time series, derived from the theory of controlled differential equations. There is a great deal …
Summarization of videos with the signature transform
This manuscript presents a new benchmark for assessing the quality of visual summaries
without the need for human annotators. It is based on the Signature Transform, specifically …
without the need for human annotators. It is based on the Signature Transform, specifically …