Skeleton-based action recognition has rapidly become one of the most popular and
essential research topics in computer vision. The task is to analyze the characteristics of …

We present a unified perspective on tackling various human-centric video tasks by learning
human motion representations from large-scale and heterogeneous data resources …

Contrastive learning has been successfully leveraged to learn action representations for
addressing the problem of semisupervised skeleton-based action recognition. However …

Most semi-supervised skeleton-based action recognition approaches aim to learn the
skeleton action representations only at the joint level, but neglect the crucial motion …

We propose a new transformer model for the task of unsupervised learning of skeleton
motion sequences. The existing transformer model utilized for unsupervised skeleton-based …

Visual tempo characterizes the dynamics and the temporal evolution, which helps describe
actions. Recent approaches directly perform visual tempo prediction on skeleton sequences …

For pursuing accurate skeleton-based action recognition, most prior methods combine
Graph Convolution Networks (GCNs) with attention-based methods in a serial way …

3D Skeleton-based human action recognition has attracted increasing attention in recent
years. Most of the existing work focuses on supervised learning which requires a large …

Self-supervised learning has proved effective for skeleton-based human action
understanding, which is an important yet challenging topic. Previous works mainly rely on …

Recently, action recognition has attracted considerable attention in the field of computer
vision. In dynamic circumstances and complicated backgrounds, there are some problems …