12 search results - page 3 / 3 » Aligning Sequences and Actions by Maximizing Space-Time Corr... |
TCSV
2008
13 years 5 months ago
2008
We present a compressed domain scheme that is able to recognize and localize actions in real-time1 . The recognition problem is posed as performing an action video query on a test ...
ICCV
2009
IEEE
14 years 10 months ago
2009
IEEE
In this paper, we present a Deformable Action Template
(DAT) model that is learnable from cluttered real-world
videos with weak supervisions. In our generative model,
an action ...