Many skeletal action recognition models use GCNs to represent the human body by 3D
body joints connected body parts. GCNs aggregate one-or few-hop graph neighbourhoods …

Action Recognition aims to understand human behavior and predict a label for each action.
Recently, Vision Transformer (ViT) has achieved remarkable performance on action …

In videos, anomaly detection is challenging due to its diverse nature in different application
domains. Reconstruction and prediction-based methods have been widely employed to …

Land use and land cover change (LUCC) process exhibits spatial correlation and temporal
dependency. Accurate extraction of spatiotemporal features is important in enhancing the …

Transformer-based methods have emerged as the golden standard in 2D-3D human pose
estimation from video sequences, largely thanks to their powerful spatial–temporal feature …

Skeleton-based human recognition is a key technology for visual feedback, which can help
the Internet of Things (IoT) interact with humans in a non-contact manner outdoors. Graph …

With the development of deep neural networks, video action recognition has gradually
become a research hotspot in recent years. However, the additional temporal dimension in …

为提升模型对视频动作的细粒度区分能力, 提出一种基于对比学**的增**负例区分范式.
通过为每个视频生成增**负例集合, 以补充最难区分的视频-文本负例对. 为了进一步区分**负例 …

Self-supervised representation learning is fundamental in modern machine learning,
however, existing approaches often rely on conventional random image augmentations …