Sciweavers

Share
ICML
2009
IEEE

Deep learning from temporal coherence in video

10 years 1 days ago
Deep learning from temporal coherence in video
This work proposes a learning method for deep architectures that takes advantage of sequential data, in particular from the temporal coherence that naturally exists in unlabeled video recordings. That is, two successive frames are likely to contain the same object or objects. This coherence is used as a supervisory signal over the unlabeled data, and is used to improve the performance on a supervised task of interest. We demonstrate the effectiveness of this method on some pose invariant object and face recognition tasks.
Hossein Mobahi, Ronan Collobert, Jason Weston
Added 17 Nov 2009
Updated 17 Nov 2009
Type Conference
Year 2009
Where ICML
Authors Hossein Mobahi, Ronan Collobert, Jason Weston
Comments (0)
books