zyh-uaiaaaa/Mine-Extra-Knowledge

Official implementation of the NeurIPS2023 paper: Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition

24
/ 100
Experimental

This project helps researchers and practitioners in affective computing improve the accuracy of facial expression recognition, especially for less common emotions like fear or disgust. It takes image datasets of faces with varying expressions and outputs a trained model that can more reliably identify all emotional states, even those underrepresented in typical datasets. This tool is for anyone building or evaluating systems that classify human facial expressions.

No commits in the last 6 months.

Use this if you are working with imbalanced facial expression datasets and need to improve the recognition accuracy for minority emotion classes.

Not ideal if your primary goal is general image classification unrelated to facial expressions or if your datasets are already perfectly balanced across all emotion categories.

facial-expression-recognition emotion-detection affective-computing imbalanced-data-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

32

Forks

3

Language

Python

License

Last pushed

Oct 30, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zyh-uaiaaaa/Mine-Extra-Knowledge"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.