Sparse F-IncSFA for action recognition
High dimensional input streams and unsupervised learning are two important factors in the area of humanoids and processes of the actions and movements of human. Our Fast Incremental Slow Feature Analysis (F-IncSFA) can learn and extract the few significant features of the complex sensory input seque...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2012
|
| Subjects: | |
| Online Access: | http://eprints.um.edu.my/14089/1/1A1-P04.pdf http://eprints.um.edu.my/14089/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|