In this paper, we uncover the untapped potential of diffusion U-Net, whi...
Existing skeleton-based action recognition methods typically follow a
ce...
Conventional centralised deep learning paradigms are not feasible when d...
In self-supervised learning, multi-granular features are heavily desired...
Transformers have shown great potential in computer vision tasks. A comm...
Few-shot learning is a challenging task since only few instances are giv...
We consider the problem of semi-supervised 3D action recognition which h...
Few-shot learning aims to learn to generalize a classifier to novel clas...
Skeleton-based action recognition is an important task that requires the...
Person search with natural language aims to retrieve the corresponding p...
Recently, pose-based action recognition has gained more and more attenti...
Skeleton-based action recognition has made great progress recently, but ...