Enhancing Action Recognition by Cross-Domain Dictionary Learning thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Enhancing Action Recognition by Cross-Domain Dictionary Learning

Published on Apr 03, 20142105 Views

We present a novel cross-dataset action recognition framework that utilizes relevant actions from other visual domains as auxiliary knowledge for enhancing the learning system in the target domain.

Related categories

Chapter list

Enhancing Action Recognition by Cross-Domain Dictionary Learning00:00
Regular action recognition00:14
Problem with insufficient training data01:35
Typical examples - 102:29
Typical examples - 203:07
Two facts of the human vision system03:19
A new action recognition framework05:04
Typical setting in transfer learning05:29
Figure 107:11
Figure 208:28
Dictionary learning09:12
The goal - 110:11
The goal - 211:41
The goal - 312:34
The goal - 412:59
The goal - 513:34
Experiments14:02
Table 114:51
References16:05
Conclusion16:31
Thank you!17:40