Abstract Human Action Recognition (HAR) is a challenging task used in sports such as volleyball, basketball, soccer, and tennis to detect players and recognize their actions and …
Human motion modeling is important for many modern graphics applications, which typically require professional skills. In order to remove the skill barriers for laymen, recent motion …
Abstract Video Foundation Models (VFMs) have received limited exploration due to high computational costs and data scarcity. Previous VFMs rely on Image Foundation Models …
Human skeleton, as a compact representation of human action, has received increasing attention in recent years. Many skeleton-based action recognition methods adopt GCNs to …
We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources …
C Yang, Y Xu, J Shi, B Dai… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Visual tempo characterizes the dynamics and the temporal scale of an action. Modeling such visual tempos of different actions facilitates their recognition. Previous works often …
We present PYSKL: an open-source toolbox for skeleton-based action recognition based on PyTorch. The toolbox supports a wide variety of skeleton action recognition algorithms …
H Yan, Y Liu, Y Wei, Z Li, G Li… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Skeleton sequence representation learning has shown great advantages for action recognition due to its promising ability to model human joints and topology. However, the …
Video action recognition is one of the representative tasks for video understanding. Over the last decade, we have witnessed great advancements in video action recognition thanks to …