Feng, Yan and Li, Ge and Yuan, Chunfeng (2018) Spatio-Temporal and View Attention Deep Network for Skeleton based View-invariant Human Action Recognition. In: 11th EAI International Conference on Mobile Multimedia Communications.
![[thumbnail of 28120.pdf]](http://eprints.eai.eu/style/images/fileicons/application_pdf.png "28120.pdf")
PDF
28120.pdf
Download (541kB)
Abstract
Skeleton-based human action recognition has been widely studied recently with the advancement of depth capturing devices. However, the skeleton data captured from a single camera is visually view-dependent and contains noise. In this paper, we propose a spatiao-temporal and view attention based deep
| Item Type: | Conference or Workshop Item (UNSPECIFIED) |
|---|---|
| Date Deposited: | 04 Mar 2026 11:30 |
| Last Modified: | 17 Apr 2026 15:35 |
| URI: | http://eprints.eai.eu/id/eprint/19314 |
Actions (login required)
- View Item