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 …

For the skeleton-based gesture recognition, graph convolutional networks (GCNs) have
achieved remarkable performance since the human skeleton is a natural graph. However …

Skeleton-based action recognition (SAR) in videos is an important but challenging task in
computer vision. The recent state-of-the-art models for SAR are primarily based on graph …

Gestures exhibit sparse joint variations and different time scales, making local dynamic
analysis and global spatio-temporal modeling important. Path signature provides …

During infancy, the human brain develops rapidly in terms of structure, function and
cognition. The tight connection between cognitive skills and brain morphology motivates us …

Gesture recognition is a challenging research topic, and also has a wide range of potential
applications in our daily life. With the development of hardware and advanced algorithms …

Precise wave forecasts are essential for many coastal communities as they help ensuring
safe maritime operations, mitigation of coastal hazards, and the enjoyment of marine …

Rough path theory, originated as a branch of stochastic analysis, is an emerging tool for
analysing complex sequential data in machine learning with increasing attention. This is …