Social touch gesture recognition has been considered an important topic in touch morphology research, which can realize efficient and real touch human-computer interaction. This project investigates random forest, 2D CNN, and 3D CNN, and an ensemble classifier combines the three models for the social touch gesture recognition on the CoST dataset. What’s more, we compared two different methods to construct input data for CNN. The weighted average ensemble classifier outperformed the other models implemented in this experiment.
-
Notifications
You must be signed in to change notification settings - Fork 0
sathvikg/Social-Touch-Gesture-Classification
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
This project investigates random forest, 2D CNN, and 3D CNN, and an ensemble classifier combines the three models for the social touch gesture recognition on the CoST dataset.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published