zyh-uaiaaaa/Relative-Uncertainty-Learning

Official implementation of our NeurIPS2021 paper: Relative Uncertainty Learning for Facial Expression Recognition

27
/ 100
Experimental

This project helps behavioral researchers and marketers accurately interpret facial expressions, even when expressions are ambiguous or inconsistently labeled. It takes images of faces as input and outputs a more reliable classification of emotions (like happy, sad, angry) by accounting for the inherent uncertainty in facial cues. The primary users are researchers or practitioners working with human emotion data from facial analysis.

No commits in the last 6 months.

Use this if you need to classify facial expressions with high confidence from image data, especially when dealing with ambiguous expressions or noisy labeling in your datasets.

Not ideal if your primary goal is general object recognition or if you require real-time, low-latency facial expression analysis for streaming video.

facial-emotion-recognition behavioral-science human-computer-interaction market-research emotion-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

55

Forks

6

Language

Python

License

Last pushed

Oct 21, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zyh-uaiaaaa/Relative-Uncertainty-Learning"

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