Deep Learning from Temporal Coherence in Video
published: Aug. 26, 2009, recorded: June 2009, views: 352
Slides
Related content
Report a problem or upload files
If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Description
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.
See Also:
Launch in a standalone WM Player
Switch to Windows Media Player
Download slides:
icml09_collobert_dlt_01.pdf (2.7 MB)
Join a Study Group
You reached a lecture within the PASCAL NoE project video collection. Click on the logo and go to the Computer Science classroom on OpenStudy. Through this classroom, you can meet other students interested in the same problems and work together on assignments, ask each other questions or just discuss the topics of the lecture.
Link this page
Would you like to put a link to this lecture on your homepage?Go ahead! Copy the HTML snippet !
Reviews and comments:
This is nice presentation because it chooses bit different way of learning from large unlabeled datasets, especially when they are sequential as videos. The results are attractive... however, the presentation seemed little bit too high level. It would be nice if more technical details would be involved.
Write your own review or comment: