-
Notifications
You must be signed in to change notification settings - Fork 9
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Anshul Sood
authored
Jan 19, 2020
1 parent
9069bd5
commit a768427
Showing
1 changed file
with
8 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,2 +1,8 @@ | ||
# Teaching-Quality-Evaluation-Using-Gaze-And-Pose-Estimation | ||
Cool stuff coming up! | ||
# Teaching-Quality-Evaluation-Using-Engagement-Intensity-Prediction | ||
|
||
## Introduction | ||
The idea for this project is based on the belief that "What your students learn depends on how you teach". Specifically, in the case of MOOCs where a student enrolls by his/her own will and interest, if the student drops out or does not complete the course, mostly the teacher is at fault. | ||
The idea is simple: Students will allow the MOOC platform to capture their video using the webcam in their pc/tablet/mobile. This video need not be saved. Real-time analysis will be done and only engagement data will be stored. This data will help educators to track their students' engagement levels throughout a lecture. Data gathered at the end of the lecture from numerous students will give the teacher an idea of parts where most of the students were highly engaged and where students were not so engaged. The teacher can then improve the corresponding parts of the lecture to increase engagement levels. | ||
|
||
## Functioning | ||
The project uses a modified approach proposed by the award winning team [1] for the engagement prediction task, a sub-challenge of the Emotion Recognition in the Wild Challenge (EmotiW 2019). |